Search

Small moving objects at far distance always occupy only one or a few pixels in image and exhibit extremely limited visual features, which bring great challenges to motion detection. Highly evolved visual systems endow flying insects with remarkable ability to pursue tiny mates and prey, providing a good template to develop image processing method for small target motion detection. The insects’ excellent sensitivity to small moving objects is believed to come from a class of specific neurons called small target motion detectors (STMDs). However, existing STMD-based methods often experience performance degradation when coping with complex natural scenes. In this paper, we propose a bio-inspired visual system with spatio-temporal feedback mechanism (called Spatio-Temporal Feedback STMD) to suppress false positive background movement while enhancing system responses to small targets. Specifically, the proposed visual system is composed of two complementary subnetworks and a feedback loop. The first subnetwork is designed to extract spatial and temporal movement patterns of cluttered background by neuronal ensemble coding. The second subnetwork is developed to capture small target motion information where its output and signal from the first subnetwork are integrated together via the feedback loop to filter out background false positives in a recurrent manner. Experimental results demonstrate that the proposed spatio-temporal feedback visual system is more competitive than existing methods in discriminating small moving targets from complex natural environments. [ABSTRACT FROM AUTHOR]

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method. Code and data are available at https://github.com/danieljf24/hybrid_space. [ABSTRACT FROM AUTHOR]

Co-salient object detection (CoSOD) aims to detect common salient objects sharing the same attributes in an image group. The key issue of CoSOD is how to model the inter-saliency relations within an image group. The major limitation of previous methods is that they pre-define the group-to-one relations within an image group. In this paper, we propose a new concept of structural inter-saliency relations and solve the CoSOD with deep reinforcement learning framework. Firstly, we design a semantic relation graph (SRG) to model the structural inter-saliency relations. Then the feature selecting agent (FS-agent) aims to select the informative features, which can help the SRG effectively model structural inter-saliency relations. Finally, relation updating agent (RU-agent) progressively updates the SRG to focus on the co-salient relations like human decision-making process. Extensive experiments on co-saliency datasets show that because of well modeling inter-saliency relations in image group, our proposed method achieves superior performance compared to the state-of-the-art methods. We hope that this paper can motivate future research for visual co-analysis tasks. [ABSTRACT FROM AUTHOR]

The vanilla Few-shot Learning (FSL) learns to build a classifier for a new concept from one or very few target examples, with the general assumption that source and target classes are sampled from the same domain. Recently, the task of Cross-Domain Few-Shot Learning (CD-FSL) aims at tackling the FSL where there is a huge domain shift between the source and target datasets. Extensive efforts on CD-FSL have been made via either directly extending the meta-learning paradigm of vanilla FSL methods, or employing massive unlabeled target data to help learn models. In this paper, we notice that in the CD-FSL task, the few labeled target images have never been explicitly leveraged to inform the model in the training stage. However, such a labeled target example set is very important to bridge the huge domain gap. Critically, this paper advocates a more practical training scenario for CD-FSL. And our key insight is to utilize a few labeled target data to guide the learning of the CD-FSL model. Technically, we propose a novel Generalized Meta-learning based Feature-Disentangled Mixup network, namely GMeta-FDMixup. We make three key contributions of utilizing GMeta-FDMixup to address CD-FSL. Firstly, we present two mixup modules – mixup-P and mixup-M that help facilitate utilizing the unbalanced and disjoint source and target datasets. These two novel modules enable diverse image generation for training the model on the source domain. Secondly, to narrow the domain gap explicitly, we contribute a novel feature disentanglement module that learns to decouple the domain-irrelevant and domain-specific features. By stripping the domain-specific features, we alleviate the negative effects caused by the domain inductive bias. Finally, we repurpose a new contrastive learning module, dubbed ConL. ConL prevents the model from only capturing category-related features via introducing contrastive loss. Thus, the generalization ability on novel categories is improved. Extensive experimental results on two benchmarks show the superiority of our setting and the effectiveness of our method. Code and models will be released. [ABSTRACT FROM AUTHOR]

Extracting robust and discriminative local features from images plays a vital role for long term visual localization, whose challenges are mainly caused by the severe appearance differences between matching images due to the day-night illuminations, seasonal changes, and human activities. Existing solutions resort to jointly learning both keypoints and their descriptors in an end-to-end manner, leveraged on large number of annotations of point correspondence which are harvested from the structure from motion and depth estimation algorithms. While these methods show improved performance over non-deep methods or those two-stage deep methods, i.e., detection and then description, they are still struggled to conquer the problems encountered in long term visual localization. Since the intrinsic semantics are invariant to the local appearance changes, this paper proposes to learn semantic-aware local features in order to improve robustness of local feature matching for long term localization. Based on a state of the art CNN architecture for local feature learning, i.e., ASLFeat, this paper leverages on the semantic information from an off-the-shelf semantic segmentation network to learn semantic-aware feature maps. The learned correspondence-aware feature descriptors and semantic features are then merged to form the final feature descriptors, for which the improved feature matching ability has been observed in experiments. In addition, the learned semantics embedded in the features can be further used to filter out noisy keypoints, leading to additional accuracy improvement and faster matching speed. Experiments on two popular long term visual localization benchmarks (Aachen Day and Night v1.1, Robotcar Seasons) and one challenging indoor benchmark (InLoc) demonstrate encouraging improvements of the localization accuracy over its counterpart and other competitive methods. [ABSTRACT FROM AUTHOR]

Since gait can be utilized to identify individuals from a far distance without their interaction and coordination, recently many gait recognition methods have been proposed. However, due to a real-world scenario of clothing changes, a degradation occurs for most of these methods. Thus in this paper, a more efficient gait recognition method is proposed to address the problem of clothing variances. First, part-based gait features are formulated from two different perspectives, i.e., the separated body parts that are more robust to clothing changes and the estimated human skeleton key-point regions. It is reasonable to formulate such features for cloth-changing gait recognition, because these two perspectives are both less vulnerable to clothing changes. Given that each feature has its own advantages and disadvantages, a more efficient gait feature is generated in this paper by assembling these two features together. Moreover, since local features are more discriminative than global features, in this paper more attention is focused on the local short-range features. Also, unlike most methods, in our method we treat the estimated key-point features as a set of word embeddings, and a transformer encoder is specifically used to learn the dependence of each correlative key-points. The robustness and effectiveness of our proposed method are certified by experiments on CASIA Gait Dataset B, and it has achieved the state-of-the-art performance on this dataset. [ABSTRACT FROM AUTHOR]

The content based image retrieval aims to find the similar images from a large scale dataset against a query image. Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval. In early days, various hand designed feature descriptors have been investigated based on the visual cues such as color, texture, shape, etc. that represent the images. However, the deep learning has emerged as a dominating alternative of hand-designed feature engineering from a decade. It learns the features automatically from the data. This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval. The categorization of existing state-of-the-art methods from different perspectives is also performed for greater understanding of the progress. The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type. A performance analysis is also performed using the state-of-the-art methods. The insights are also presented for the benefit of the researchers to observe the progress and to make the best choices. The survey presented in this paper will help in further research progress in image retrieval using deep learning. [ABSTRACT FROM AUTHOR]

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning. [ABSTRACT FROM AUTHOR]

Visualization charts are widely utilized for presenting structured data. Under many circumstances, people want to digitalize the data in the charts collected from various sources (e.g., papers and websites), in oder to further analyze the data or create new charts. However, existing automatic and semi-automatic approaches are not always effective due to the variety of charts. In this paper, we introduce a crowdsourcing approach that leverages human ability to extract data from visualization charts. There are several challenges. The first is how to avoid tedious human interaction with charts and design effective crowdsourcing tasks. Second, it is challenging to evaluate worker’s quality for truth inference, because workers may not only provide inaccurate values but also misalign values to wrong data series. Third, to guarantee quality, one may assign a task to many workers, leading to a high crowdsourcing cost. To address these challenges, we design an effective crowdsourcing task scheme that splits a chart into simple micro-tasks. We introduce a novel worker quality model by considering worker’s accuracy and task difficulty. We also devise effective task assignment and early-termination mechanisms to save the cost. We evaluate our approach on real-world datasets on real crowdsourced platforms, and the results demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for obtaining precise object contrast information. For this reason, we in this paper propose a simple and effective “U-Net in U-Net” framework, UIU-Net for short, and detect small objects in infrared images. As the name suggests, UIU-Net embeds a tiny U-Net into a larger U-Net backbone, enabling the multi-level and multi-scale representation learning of objects. Moreover, UIU-Net can be trained from scratch, and the learned features can enhance global and local contrast information effectively. More specifically, the UIU-Net model is divided into two modules: the resolution-maintenance deep supervision (RM-DS) module and the interactive-cross attention (IC-A) module. RM-DS integrates Residual U-blocks into a deep supervision network to generate deep multi-scale resolution-maintenance features while learning global context information. Further, IC-A encodes the local context information between the low-level details and high-level semantic features. Extensive experiments conducted on two infrared single-frame image datasets, i.e., SIRST and Synthetic datasets, show the effectiveness and superiority of the proposed UIU-Net in comparison with several state-of-the-art infrared small object detection methods. The proposed UIU-Net also produces powerful generalization performance for video sequence infrared small object datasets, e.g., ATR ground/air video sequence dataset. The codes of this work are available openly at https://github.com/danfenghong/IEEE [ABSTRACT FROM AUTHOR]

Recent studies of video action recognition can be classified into two categories: the appearance-based methods and the pose-based methods. The appearance-based methods generally cannot model temporal dynamics of large motion well by virtue of optical flow estimation, while the pose-based methods ignore the visual context information such as typical scenes and objects, which are also important cues for action understanding. In this paper, we tackle these problems by proposing a Pose-Appearance Relational Network (PARNet), which models the correlation between human pose and image appearance, and combines the benefits of these two modalities to improve the robustness towards unconstrained real-world videos. There are three network streams in our model, namely pose stream, appearance stream and relation stream. For the pose stream, a Temporal Multi-Pose RNN module is constructed to obtain the dynamic representations through temporal modeling of 2D poses. For the appearance stream, a Spatial Appearance CNN module is employed to extract the global appearance representation of the video sequence. For the relation stream, a Pose-Aware RNN module is built to connect pose and appearance streams by modeling action-sensitive visual context information. Through jointly optimizing the three modules, PARNet achieves superior performances compared with the state-of-the-arts on both the pose-complete datasets (KTH, Penn-Action, UCF11) and the challenging pose-incomplete datasets (UCF101, HMDB51, JHMDB), demonstrating its robustness towards complex environments and noisy skeletons. Its effectiveness on NTU-RGBD dataset is also validated even compared with 3D skeleton-based methods. Furthermore, an appearance-enhanced PARNet equipped with a RGB-based I3D stream is proposed, which outperforms the Kinetics pre-trained competitors on UCF101 and HMDB51. The better experimental results verify the potentials of our framework by integrating various modules. [ABSTRACT FROM AUTHOR]

Channel attention mechanisms have been commonly applied in many visual tasks for effective performance improvement. It is able to reinforce the informative channels as well as to suppress the useless channels. Recently, different channel attention modules have been proposed and implemented in various ways. Generally speaking, they are mainly based on convolution and pooling operations. In this paper, we propose Gaussian process embedded channel attention (GPCA) module and further interpret the channel attention schemes in a probabilistic way. The GPCA module intends to model the correlations among the channels, which are assumed to be captured by beta distributed variables. As the beta distribution cannot be integrated into the end-to-end training of convolutional neural networks (CNNs) with a mathematically tractable solution, we utilize an approximation of the beta distribution to solve this problem. To specify, we adapt a Sigmoid-Gaussian approximation, in which the Gaussian distributed variables are transferred into the interval [0,1]. The Gaussian process is then utilized to model the correlations among different channels. In this case, a mathematically tractable solution is derived. The GPCA module can be efficiently implemented and integrated into the end-to-end training of the CNNs. Experimental results demonstrate the promising performance of the proposed GPCA module. Codes are available at https://github.com/PRIS-CV/GPCA. [ABSTRACT FROM AUTHOR]

Visual question generation task aims to generate meaningful questions about an image targeting an answer. Existing methods focus on the visual concepts in the image for question generation. However, humans inevitably use their knowledge related to visual objects in images to construct questions. In this paper, we propose a knowledge-based visual question generation model that can integrate visual concepts and non-visual knowledge to generate questions. To obtain visual concepts, we utilize a pre-trained object detection model to obtain object-level features of each object in the image. To obtain useful non-visual knowledge, we first retrieve the knowledge from the knowledge-base related to the visual objects in the image. Considering that not all retrieved knowledge is helpful for this task, we introduce an answer-aware module to capture the candidate knowledge related to the answer from the retrieved knowledge, which ensures that the generated content can be targeted at the answer. Finally, object-level representations containing visual concepts and non-visual knowledge are sent to a decoder module to generate questions. Extensive experiments on the FVQA and KBVQA datasets show that the proposed model outperforms the state-of-the-art models. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) is an important task of image processing and has diverse applications, such as image super-resolution reconstruction, image transmission and monitoring systems. This paper proposes a perceptual hashing algorithm with complementary color wavelet transform (CCWT) and compressed sensing (CS) for reduced-reference (RR) IQA. The CCWT is exploited to decompose input color image into different sub-bands. Since the calculation of CCWT uses all color channels without discarding any information, the distortions introduced by digital operations on color channels are preserved in the CCWT sub-bands. The block-based CS is used to extract features from the CCWT sub-bands. As the Euclidean distance between the block-based CS features is slightly influenced by content-preserving operations, perceptual features constructed by Euclidean distances are robust, discriminative and compact. Hash sequence is finally determined by quantifying the perceptual features. Effectiveness of the proposed hashing is verified by various experiments on four open image databases. Experimental results demonstrate that the proposed hashing is superior to some state-of-the-art algorithms in terms of classification and RR IQA application. [ABSTRACT FROM AUTHOR]

Multi-object tracking (MOT), which is crucial for computer vision and video processing, has immense potential for improvement. Traditional tracking-by-detection approaches include feature-based object re-identification methods that use trained features, but these methods suffer from a lack of suitable training data. In training datasets used for MOT, every object in a video sequence must have its own location and ID. However, assigning IDs to each object in every sequence is considerably labor-intensive, and hence current MOT datasets are unsuitable for training re-identification networks. To resolve this issue, this paper proposes a novel self-supervised learning method using several short videos that contain no human-added labels, based on the idea that each video is a set of temporally corresponding image frames. We then describe how to improve tracking performance using a re-identification network trained in a self-supervised manner. In addition, ablation studies were conducted in order to define the optimal parameters, such as number of clips, data augmentation, and appropriate matching algorithms. The proposed approach achieved competitive performance compared with current best-practice methods including supervised methods, achieving MOT accuracy = 62.0% and ID F1-score = 62.7% on the MOT17 benchmark. [ABSTRACT FROM AUTHOR]

Correlation filters with Convolutional Neural Networks (CNNs) features have obtained tremendous attention and success in visual tracking. However, redundant and noisy feature channels existed in CNN features may cause severe over-fitting and greatly limit the discriminative power of the tracking model. To tackle the issue, in this paper, we develop a new and effective channel-aware correlation filters (CACF) method for boosting the tracking performance. Our CACF method aims to dynamically select representative and discriminative feature channels from high-dimensional CNN features to reduce the model complexity and better distinguish the target object from the background. Moreover, the CACF model is solved by the alternating direction method of multipliers (ADMM) to learn correlation filters. By retaining reliable feature channels, our CACF tracking method can reach better generalization ability and discriminative ability to accurately localize the target object. Comprehensive experiments are conducted on challenging tracking datasets, and the experiment results prove that our CACF method obtains favorable tracking accuracy compared to several popular tracking methods. [ABSTRACT FROM AUTHOR]

In this paper, we conduct an extensive study on the use of pre-trained convolutional neural networks (CNNs) for omnidirectional image quality assessment (IQA). To cope with the lack of available IQA databases, transfer learning from seven pre-trained CNN models is investigated over retraining on standard 2D databases. In addition, we explore the influence of various image representations and training strategies on the model’s performance. A comparison of the use of projected versus radial content, and multichannel CNN versus patch-wise training is also covered. The experimental results on two publicly available databases are used to draw conclusions about which strategy best fits the visual quality prediction and at which computational cost. The analysis shows that retraining CNN models on 2D IQA databases improves the prediction accuracy. The latter and the required computational time are found to be significantly affected by the training strategy. Cross-database evaluations demonstrate that the nature and variety of the content impact the generalization ability of the models. Finally, we show that conclusions coming from other image processing communities may not hold for IQA. The provided discussion shall provide insights and recommendations when using pre-trained CNNs for omnidirectional IQA. [ABSTRACT FROM AUTHOR]

Image captioning has made significant achievement through developing feature extractor and model architecture. Recently, the image region features extracted by object detector prevail in most existing models. However, region features are criticized for the lacking of background and full contextual information. This problem can be remedied by providing some complementary visual information from patch features. In this paper, we propose a Double-Stream Position Learning Transformer Network (DSPLTN) which exploits the advantages of region features and patch features. Specifically, the region-stream encoder utilizes a Transformer encoder with Relative Position Learning (RPL) module to enhance the representations of region features through modeling the relationships between regions and positions respectively. As for the patch-stream encoder, we introduce convolutional neural network into the vanilla Transformer encoder and propose a novel Convolutional Position Learning (CPL) module to encode the position relationships between patches. CPL improves the ability of relationship modeling by combining the position and visual content of patches. Incorporating CPL into the Transformer encoder can synthesize the benefits of convolution in local relation modeling and self-attention in global feature fusion, thereby compensating for the information loss caused by the flattening operation of 2D feature maps to 1D patches. Furthermore, an Adaptive Fusion Attention (AFA) mechanism is proposed to balance the contribution of enhanced region and patch features. Extensive experiments on MSCOCO demonstrate the effectiveness of the double-stream encoder and CPL, and show the superior performance of DSPLTN. [ABSTRACT FROM AUTHOR]

Medical images contain various abnormal regions, most of which are closely related to the lesions or diseases. The abnormality or lesion is one of the major concerns during clinical practice and therefore becomes the key in answering questions about medical images. However, the recent efforts still focus on constructing a generic Visual Question Answering framework for medical-domain tasks, which is not adequate for practical medical requirements and applications. In this paper, we present two novel medical-specific modules named multiplication anomaly sensitive module and residual anomaly sensitive module to utilize weakly supervised anomaly localization information in medical Visual Question Answering. Firstly, the proposed multiplication anomaly sensitive module designed for anomaly-related questions can mask the feature of the whole image according to the anomaly location map. Secondly, the residual anomaly sensitive module could learn a flexible anomaly feature while preserving the information of the original questioned image, which is more helpful in answering anomaly-unrelated questions. Thirdly, the transformer decoder and multi-task learning strategy are combined to further enhance the question-reasoning ability and the model generalization performance. Finally, qualitative and quantitative experiments on a variety of medical datasets exhibit the superiority of the proposed approaches compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Medical visual question answering (VQA) aims to correctly answer a clinical question related to a given medical image. Nevertheless, owing to the expensive manual annotations of medical data, the lack of labeled data limits the development of medical VQA. In this paper, we propose a simple yet effective data augmentation method, VQAMix, to mitigate the data limitation problem. Specifically, VQAMix generates more labeled training samples by linearly combining a pair of VQA samples, which can be easily embedded into any visual-language model to boost performance. However, mixing two VQA samples would construct new connections between images and questions from different samples, which will cause the answers for those new fabricated image-question pairs to be missing or meaningless. To solve the missing answer problem, we first develop the Learning with Missing Labels (LML) strategy, which roughly excludes the missing answers. To alleviate the meaningless answer issue, we design the Learning with Conditional-mixed Labels (LCL) strategy, which further utilizes language-type prior to forcing the mixed pairs to have reasonable answers that belong to the same category. Experimental results on the VQA-RAD and PathVQA benchmarks show that our proposed method significantly improves the performance of the baseline by about 7% and 5% on the averaging result of two backbones, respectively. More importantly, VQAMix could improve confidence calibration and model interpretability, which is significant for medical VQA models in practical applications. All code and models are available at https://github.com/haifangong/VQAMix. [ABSTRACT FROM AUTHOR]

As an instance-level recognition problem, re-identification (re-ID) requires models to capture diverse features. However, with continuous training, re-ID models pay more and more attention to the salient areas. As a result, the model may only focus on few small regions with salient representations and ignore other important information. This phenomenon leads to inferior performance, especially when models are evaluated on small inter-identity variation data. In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image. ES-Net proposes a novel method to locate the salient areas by the confidence of objects and erases them efficiently in a training batch. Meanwhile, to mitigate the over-erasing problem, this paper uses a trainable pooling layer P-pooling that generalizes global max and global average pooling. Experiments are conducted on two specific re-identification tasks (i.e., Person re-ID, Vehicle re-ID). Our ES-Net outperforms state-of-the-art methods on three Person re-ID benchmarks and two Vehicle re-ID benchmarks. Specifically, mAP / Rank-1 rate: 88.6% / 95.7% on Market1501, 78.8% / 89.2% on DuckMTMC-reID, 57.3% / 80.9% on MSMT17, 81.9% / 97.0% on Veri-776, respectively. Rank-1 / Rank-5 rate: 83.6% / 96.9% on VehicleID (Small), 79.9% / 93.5% on VehicleID (Medium), 76.9% / 90.7% on VehicleID (Large), respectively. Moreover, the visualized salient areas show human-interpretable visual explanations for the ranking results. [ABSTRACT FROM AUTHOR]

Domain adaptation aims to alleviate the distribution discrepancy between source and target domains. Most conventional methods focus on one target domain setting adapted from one or multiple source domains while neglecting the multi-target domain setting. We argue that different target domains also have complementary information, which is very important for performance improvement. In this paper, we propose an Attention-guided Multiple source-and-target Domain Adaptation (AMDA) method to capture the context dependency information on transferable regions among multiple source and target domains. The innovation points of this paper are as follows: (1) We use numerous adversarial strategies to harvest sufficient information from multiple source and target domains, which extends the generalization and robustness of the feature pools. (2) We propose an intra-domain and inter-domain attention module to explore transferable context information. The proposed attention module can learn domain-invariant representations and reduce the negative transfer by focusing on transferable knowledge. Extensive experiments validate the effectiveness of our method with achieving state-of-the-art performance on several unsupervised domain adaptation datasets. [ABSTRACT FROM AUTHOR]

Deep learning based models have excelled in many computer vision tasks and appear to surpass humans’ performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories, some of which are with a large number of instances, but with only a few manually annotated. Learning from such extremely limited labeled examples is known as Few-Shot Learning (FSL). Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm to predict pseudo-labels of unlabeled instances with an initial classifier trained from the few shot and then select the most confident ones to augment the training set to re-train the classifier. This is achieved by constructing a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of the corresponding pseudo-labeled instance. We rank the credibility of pseudo-labeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances. This process is repeated until all the unlabeled samples are included in the expanded training set. Theoretically, under the conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show the effectiveness of our approach on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Code and models are released at https://github.com/Yikai-Wang/ICI-FSL. [ABSTRACT FROM AUTHOR]

Few-shot action recognition classifies new actions with only few training samples, of which the mainstream methods adopt class means to obtain prototypes as the representations of each category. However, affected by sample capacity and extreme samples, mean-of-class prototypes can’t well represent the average level of samples. In this paper, we enhance the prototypes from multiple dimensions for better classification. We firstly propose a novel similarity optimization mechanism where Prototype Aggregation Adaptive Loss (PAAL) is designed to deeply mine the similarity between samples and prototypes for enhancing the ability of inter-class differential detail identification. Secondly, for mitigating the impact of the samples on class prototypes, we refactor the prototype calculation formula with Cross-Enhanced Prototype (CEP) to narrow intra-class differences in which Reweighted Similarity Attention (RSA) is designed to update prototypes. Finally, Dynamic Temporal Transformation (DTT) is proposed to alleviate inconsistent distribution of temporal information for obtaining better video-level descriptors. Extensive experiments on standard benchmark datasets demonstrate that our proposed method achieves the state-of-the-art results. [ABSTRACT FROM AUTHOR]

Feature Pyramid (FP) is typically a fundamental component for detecting multi-scale objects. However, as the network deepens, FP faces two problems: (1) Information loss caused by channel reduction. (2) The insufficient effective receptive field due to convolution with the sliding window mode. We found that the above problems can be alleviated by increasing the semantics extraction weights of the off-centered feature map. In this paper, a new feature pyramid architecture named Off-Centered Semantics Refinement Feature Pyramid Network (OSR-FPN) is proposed. Specifically, OSR-FPN contains two components exploiting the Off-Centered Semantics Refinement (OSR) mechanism: Features Supplement Module (FSM) and Receptive Field Enlargement Module (RFEM). FSM and RFEM are respectively designed to complement the lost context at the highest pyramid level and enrich the semantics by expanding the receptive field. In addition, we propose the Sigmoid-interpolation Padding method to enhance our OSR. Experiments on MS COCO dataset and UAVDT object detection benchmarks demonstrate the effectiveness of our method. As a result, OSR-FPN achieves a better accuracy of complex object detection. [ABSTRACT FROM AUTHOR]

Modeling 3D visual saliency has received great attention due to the development of emerging 3D display technologies. Traditional methods relying on low-level features may not be efficient in interpreting 3D visual content from high-level semantic perspective. Despite numerous efforts dedicated to this area, existing 3D visual saliency detection methods do not necessarily excel in exploring the stereoscopic image saliency driven by the intra-view and inter-view dependencies among left and right views. In this paper, we propose a visual saliency detection method for stereoscopic images grounded on adaptive viewpoint feature enhancement via binocular vision. More specifically, the correlation among left and right views is investigated through a delicately designed binocular stereoscopic saliency feature aggregation module, enabling the generation of more representative saliency features towards binocular vision. Subsequently, to further aggregate the saliency features in multiple scales, we design a progressive attention-based saliency feature pyramid extraction module to effectively integrate the features from top-level to down-level based on the network hierarchy mechanism. The saliency maps are ultimately produced for stereoscopic images by evaluating the obtained saliency features. In addition, we create a stereoscopic image saliency dataset (SIS-3D) that includes 1086 stereoscopic image pairs with various content and their corresponding human eye fixation annotations, aiming to further facilitate the research on visual saliency detection for stereoscopic images. Extensive experiments demonstrate that our proposed method improves CC by an average of 4.02% compared to representative counterparts on the newly built saliency dataset and another publicly available dataset. [ABSTRACT FROM AUTHOR]

It has been recognized that texture patterns with abundant high-frequency components, such as grass and water, produce visual masking effects, and the distortion in textures is hard to be perceived by human eyes than structure regions. However, modern video codecs in a rate-distortion optimized manner usually consume a lot of bits to encode textures, leading to the insufficiency in perceptual coding performance. Nowadays, with the rapid development of deep learning, learning based texture synthesis methods have been proposed to replace the coding process of prediction residuals to reduce the rate cost. In this paper, we present a deep texture synthesizer named edge-based texture synthesis framework (ETSF). At encoder side, the framework detects texture regions by semantic and fidelity classification criteria, and the detected regions are quantized coarsely by the hybrid coding framework. In texture characterization, ETSF extracts low-level edge features representing pixel intensity variation. Feature processing tools are developed to remove the spatiotemporal redundancy of edges. The processed edge information is compressed and transmitted. To effectively recover textures, we design an edge-based texture synthesis generative adversarial network (ETSGAN) at the decoder of ETSF, which can incorporate edge information into convolutional layers and generate realistic textures. Experimental results on a collected texture dataset show that the proposed ETSF can achieve an average of -12.8%, -14.2% and -9.6% MOS BD-rate under lowdelay_B, lowdelay_P and random_access configurations of VVC coding, respectively. [ABSTRACT FROM AUTHOR]

Automated radiographic report generation is challenging in at least two aspects. First, medical images are very similar to each other and the visual differences of clinic importance are often fine-grained. Second, the disease-related words may be submerged by many similar sentences describing the common content of the images, causing the abnormal to be misinterpreted as the normal in the worst case. To tackle these challenges, this paper proposes a pure transformer-based framework to jointly enforce better visual-textual alignment, multi-label diagnostic classification, and word importance weighting, to facilitate report generation. To the best of our knowledge, this is the first pure transformer-based framework for medical report generation, which enjoys the capacity of transformer in learning long range dependencies for both image regions and sentence words. Specifically, for the first challenge, we design a novel mechanism to embed an auxiliary image-text matching objective into the transformer’s encoder-decoder structure, so that better correlated image and text features could be learned to help a report to discriminate similar images. For the second challenge, we integrate an additional multi-label classification task into our framework to guide the model in making correct diagnostic predictions. Also, a term-weighting scheme is proposed to reflect the importance of words for training so that our model would not miss key discriminative information. Our work achieves promising performance over the state-of-the-arts on two benchmark datasets, including the largest dataset MIMIC-CXR. [ABSTRACT FROM AUTHOR]

Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit feature interaction and fusion between visual and linguistic modalities in a one-stage manner. However, human tends to solve the referring problem in a progressive manner based on informative words in the expression, i.e., first roughly locating candidate entities and then distinguishing the target one. In this paper, we propose a cross-modal progressive comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models. For image data, our CMPC-I module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the target entity as well as suppress other irrelevant ones by spatial graph reasoning. For video data, our CMPC-V module further exploits action words based on CMPC-I to highlight the correct entity matched with the action cues by temporal graph reasoning. In addition to the CMPC, we also introduce a simple yet effective Text-Guided Feature Exchange (TGFE) module to integrate the reasoned multimodal features corresponding to different levels in the visual backbone under the guidance of textual information. In this way, multi-level features can communicate with each other and be mutually refined based on the textual context. Combining CMPC-I or CMPC-V with TGFE can form our image or video version referring segmentation frameworks and our frameworks achieve new state-of-the-art performances on four referring image segmentation benchmarks and three referring video segmentation benchmarks respectively. Our code is available at https://github.com/spyflying/CMPC-Refseg. [ABSTRACT FROM AUTHOR]

As a challenging task of high-level video understanding, weakly supervised temporal action localization has attracted more attention recently. With only video-level category labels, this task should indistinguishably identify the background and action categories frame by frame. However, it is non-trivial to achieve this in untrimmed videos, due to the unconstrained background, complex and multi-label actions. With the observation that these difficulties are mainly brought by the large variations within background and actions, we propose to address these challenges from the perspective of modeling variations. Moreover, it is desired to further reduce the variations, or learn compact features, so as to cast the problem of background identification as rejecting background and alleviate the contradiction between classification and detection. Accordingly, in this paper, we propose a two-branch relational prototypical network. The first branch, namely action-branch, adopts class-wise prototypes and mainly acts as an auxiliary to introduce priori knowledge about label dependencies and be a guide for the second branch. Meanwhile, the second branch, namely sub-branch, starts with multiple prototypes, namely sub-prototypes, to enable a powerful ability of modeling variations. As a further benefit, we elaborately design a multi-label clustering loss based on the sub-prototypes to learn compact features under the multi-label setting. The two branches are associated using the correspondences between two types of prototypes, leading to a special two-stage classifier in the s-branch, on the other hand, the two branches serve as regularization terms to each other, improving the final performance. Ablation studies find that the proposed model is capable of modeling classes with large variations and learning compact features. Extensive experimental evaluations on Thumos14, MultiThumos and ActivityNet datasets demonstrate the effectiveness of the proposed method and superior performance over state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

This paper generalizes the Attention in Attention (AiA) mechanism, in P. Fang et al., 2019 by employing explicit mapping in reproducing kernel Hilbert spaces to generate attention values of the input feature map. The AiA mechanism models the capacity of building inter-dependencies among the local and global features by the interaction of inner and outer attention modules. Besides a vanilla AiA module, termed linear attention with AiA, two non-linear counterparts, namely, second-order polynomial attention and Gaussian attention, are also proposed to utilize the non-linear properties of the input features explicitly, via the second-order polynomial kernel and Gaussian kernel approximation. The deep convolutional neural network, equipped with the proposed AiA blocks, is referred to as Attention in Attention Network (AiA-Net). The AiA-Net learns to extract a discriminative pedestrian representation, which combines complementary person appearance and corresponding part features. Extensive ablation studies verify the effectiveness of the AiA mechanism and the use of non-linear features hidden in the feature map for attention design. Furthermore, our approach outperforms current state-of-the-art by a considerable margin across a number of benchmarks. In addition, state-of-the-art performance is also achieved in the video person retrieval task with the assistance of the proposed AiA blocks. [ABSTRACT FROM AUTHOR]

In complex real-world situations, problems such as illumination changes, facial occlusion, and variant poses make facial expression recognition (FER) a challenging task. To solve the robustness problem, this paper proposes an adaptive multilayer perceptual attention network (AMP-Net) that is inspired by the facial attributes and the facial perception mechanism of the human visual system. AMP-Net extracts global, local, and salient facial emotional features with different fine-grained features to learn the underlying diversity and key information of facial emotions. Different from existing methods, AMP-Net can adaptively guide the network to focus on multiple finer and distinguishable local patches with robustness to occlusion and variant poses, improving the effectiveness of learning potential facial diversity information. In addition, the proposed global perception module can learn different receptive field features in the global perception domain, and AMP-Net also supplements salient facial region features with high emotion correlation based on prior knowledge to capture key texture details and avoid important information loss. Many experiments show that AMP-Net achieves good generalizability and state-of-the-art results on several real-world datasets, including RAF-DB, AffectNet-7, AffectNet-8, SFEW 2.0, FER-2013, and FED-RO, with accuracies of 89.25%, 64.54%, 61.74%, 61.17%, 74.48%, and 71.75%, respectively. All codes and training logs are publicly available at https://github.com/liuhw01/AMP-Net. [ABSTRACT FROM AUTHOR]

Numerous tracking approaches attempt to improve target representation through target-aware or distractor-aware. However, the unbalanced considerations of target or distractor information make it diffcult for these methods to benefit from the two aspects at the same time. In this paper, we propose a target-distractor aware model with discriminative enhancement learning loss to learn target representation, which can better distinguish the target in complex scenes. Firstly, to enlarge the gap between the target and distractor, we design a discriminative enhancement learning loss. By highlighting the hard negatives that are similar to the target and shrinking the easy negatives that are pure background, the features sensitive to the target or distractor representation can be more conveniently mined. On this basis, we further propose a target-distractor aware model. Unlike existing methods of preference target or distractor, we construct the target-specific feature space by activating the target-sensitive and the distractor-silence feature. Therefore, the appearance model can not only represent the target well but also suppress the background distractor. Finally, the target-distractor aware target representation model is integrated with a Siamese matching network for visual tracking for achieving robust and realtime visual tracking. Extensive experiments are performed on eight tracking benchmarks show that the proposed algorithm achieves favorable performance. [ABSTRACT FROM AUTHOR]

Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded surfaces, and cluttered background of metal part images. Affected by these factors, bounding boxes generated by most existing methods could not locate low-contrast text areas very well. In this paper, we propose a refined feature-attentive network (RFN) to solve the inaccurate localization problem. Specifically, we first design a parallel feature integration mechanism to construct an adaptive feature representation from multi-resolution features, which enhances the perception of multi-scale texts at each scale-specific level to generate a high-quality attention map. Then, an attentive proposal refinement module is developed by the attention map to rectify the location deviation of candidate boxes. Besides, a re-scoring mechanism is designed to select text boxes with the best rectified location. To promote the research towards industrial scene text detection, we contribute two industrial scene text datasets, including a total of 102156 images and 1948809 text instances with various character structures and metal parts. Extensive experiments on our dataset and four public datasets demonstrate that our proposed method achieves the state-of-the-art performance. Both code and dataset are available at: https://github.com/TongkunGuan/RFN. [ABSTRACT FROM AUTHOR]

Image captioning is a challenging task, i.e., given an image machine automatically generates natural language that matches its semantic content and has attracted much attention in recent years. However, most existing models are designed manually, and their performance depends heavily on the expert experience of the designer. In addition, the computational flow of the model is predefined, and hard and easy samples will share the same coding path and easily interfere with each other, thus confusing the learning of the model. In this paper, we propose a Dynamic Transformer to change the encoding procedure from sequential to adaptive, i.e., data-dependent computing paths. Specifically, we design three different types of visual feature extraction blocks and deploy them in parallel at each layer to construct a multi-layer routing space in a fully connected manner. Each block contains a calculation unit that performs the corresponding operations and a routing gate that learns to adaptively select the direction to pass the signal based on the input image. Thus, our model can achieve a robust visual representation by exploring potential visual feature extraction paths. We evaluate our method quantitatively and qualitatively using a benchmark MSCOCO image caption dataset and perform extensive ablation studies to investigate the reasons behind its effectiveness. The experimental results show that our method is significantly superior to previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a deep neural network-based no-reference (NR) video quality assessment (VQA) method with spatiotemporal feature fusion and hierarchical information integration to evaluate the perceptual quality of videos. First, a feature extraction model is proposed by using 2D and 3D convolutional layers to gradually extract spatiotemporal features from raw video clips. Second, we design a hierarchical branching network to fuse multiframe features, and the feature vectors at each hierarchical level are comprehensively considered during the process of network optimization. Finally, these two modules and quality regression are synthesized into an end-to-end architecture. Experimental results obtained on benchmark VQA databases demonstrate the superiority of our method over other state-of-the-art algorithms. The source code is available online. [ABSTRACT FROM AUTHOR]

In this paper, we propose a weakly-supervised approach called Order-Constrained Representation Learning (OCRL) to predict future actions from instructional videos by observing incomplete steps of actions. Most conventional methods focus on predicting actions based on partially observed video frames, which mainly study low-level semantics such as motion consistency. Unlike performing a single action, completing a task in an instructional video usually requires several steps of action and longer periods. Motivated by the fact that the order of action steps is key to learning task semantics, we develop a new frame of contrastive loss, called StepNCE, to integrate the shared semantic information between step order and task semantics under the framework of the memory bank-based momentum-updating algorithm. Specifically, we learn the video representations from step order-rearranged trimmed video clips based on the proposed task-consistency rule and order-consistency rule. Our StepNCE loss can be used to pre-train a video feature encoder, which is then fine-tuned to carry out the instructional video prediction task. Our approach digs deeper into the sequential logic between different action steps with respect to a certain task, which is able to promote the video understanding methods to a new semantic level. We evaluate our method on five popular instructional video and action prediction datasets: COIN, CrossTask, UT-Interaction, BIT-Interaction, and ActivityNet v1.2, and the results show that our approach gains improvements from conventional prediction methods. [ABSTRACT FROM AUTHOR]

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is available at https://github.com/LiJiaBei-7/rivrl. [ABSTRACT FROM AUTHOR]

Reversible data hiding with contrast enhancement (RDH-CE) is proposed to aim at improving the contrast of images while embedding data. After deeply analyzing and studying the RDH-CE method proposed by Jafar et al., it is found that there are three main problems in their method. Firstly, their method ignores the fact that the left-bottom neighbors of a pixel contribute to increasing the accuracy of the local-complexity evaluation. Secondly, Jafar et al.’s method employs K-means clustering in combination with one single feature to split pixels into five classes, leading to a weak clustering performance. Finally, Jafar et al.’s method uniformly embedded 1 bit into each pixel irrespective of the local complexity, and thus, the embedding capacity is limited. To this end, an improved RDH-CE method is proposed in this paper. Considering that the complexity evaluation plays a vital role in both contrast enhancement and payload increase, we improve embedding performance by including left-bottom neighbors of a pixel into complexity evaluation. Compared with one single feature in Jafar et al.’s method, we extract multiple features to assist K-means clustering such that a better cluster performance is obtained. In addition, our method provides an adaptive pixel modification strategy based on the local complexity, in which we can adaptively embed 1 or 2 bits into a pixel according to the corresponding complexity. By these three improvements, our method is capable of achieving high capacity while enhancing contrast. The experimental results also show that our method achieves higher accuracy of the complexity evaluation, larger payload, and better local contrast enhancement than those existing RDH-CE related methods. [ABSTRACT FROM AUTHOR]

Human beings can concentrate on the most semantically relevant visual information when performing action recognition, so as to make reasonable and interpretable predictions. However, most existing approaches, which are applied to address visual tasks, neglect to explicitly imitate such ability for improving the performance and reliability of models. In this paper, we propose an interpretable action recognition framework that can not only improve the performance but also enhance the visual interpretability of 3D CNNs. Specifically, we design a semantic-aware attention module to learn correlative spatial-temporal attention for different action categories. To further leverage the rich semantics of features extracted from different layers, we design a hierarchical semantic fusion module with the help of the learned attention. The proposed two modules can enhance and complement each other, meanwhile, the semantic-aware attention module enjoys the plug-and-play merit. We evaluate our method on different benchmarks with comprehensive ablation studies and visualization analysis. Experimental results demonstrate the effectiveness of our method, showing favorable accuracy against state-of-the-arts while enhancing the semantic interpretability (Code will be available at this link https://github.com/PHDJieFu). [ABSTRACT FROM AUTHOR]

Most existing RGB-D salient detection models pay more attention to the quality of the depth images, while in some special cases, the quality of RGB images may even have greater impacts on saliency detection, which has long been ignored and underestimated. To address this problem, in this paper, we present a Bi-directional Progressive Guidance Network (BPGNet) for RGB-D salient object detection, where the qualities of both RGB and depth images are involved. Since it is usually difficult to determine which modality data have low quality in advance, a bi-directional framework based on progressive guidance (PG) strategy is employed to extract and enhance the unimodal features with the aid of another modality data via the alternative interactions between the saliency prediction results and the extracted features from the multi-modality input data. Specifically, the proposed PG strategy is achieved by using the proposed Global Context Awareness (GCA), Auxiliary Feature Extraction (AFE) and Cross-modality Feature Enhancement (CFE) modules. Benefiting from the proposed PG strategy, the disturbing information within the input RGB and depth images can be well suppressed, while the discriminative information within the input images gets enhanced. On top of that, a Fusion Prediction Module (FPM) is further designed to adaptively select those features with higher discriminability as well as enhancing the common information for the final saliency prediction. Experimental results demonstrate that our proposed model is comparable to those of state-of-the-art RGB-D SOD models. [ABSTRACT FROM AUTHOR]

Nowadays the problem of image quality assessment (IQA) for screen content images (SCIs) has become a research hotspot as they are ubiquitous in multimedia applications. Although the quality assessment of natural images (NIs) has been continuously developed in the past few decades, few NI-oriented IQA methods can be directly applied on SCIs due to different visual characteristics between them. In this paper, we present a no-reference quality prediction approach considering the content information of SCIs, which is based on dual-channel multi-task convolutional neural network. First, we segment a SCI into small patches and classify them as the textual patches and the pictorial patches. Then, we devise a novel dual-channel convolutional neural network (CNN) to predict the quality of textual patches and pictorial patches. Finally, we propose an effective adaptive weighting strategy for quality score aggregation. The proposed CNN is built on an end-to-end multi-task learning framework, which assists the SCI quality prediction task through the histogram of oriented gradient (HOG) feature prediction task to learn a better mapping between the input patch and its quality score. The adaptive weighting strategy further improves the representation ability of each SCI patch. Experimental results on two largest SCI-oriented databases demonstrate that the proposed method outperforms most of the state-of-the-art no-reference IQA methods and the full-reference IQA methods. [ABSTRACT FROM AUTHOR]

It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details. Existing deep learning works almost neglect the inherent structural information of images, which acts as an important role for visual perception of SR results. In this paper, we design a hierarchical feature exploitation network to probe and preserve structural information in a multi-scale feature fusion manner. First, we propose a cross convolution upon traditional edge detectors to localize and represent edge features. Then, cross convolution blocks (CCBs) are designed with feature normalization and channel attention to consider the inherent correlations of features. Finally, we leverage multi-scale feature fusion group (MFFG) to embed the cross convolution blocks and develop the relations of structural features in different scales hierarchically, invoking a lightweight structure-preserving network named as Cross-SRN. Experimental results demonstrate the Cross-SRN achieves competitive or superior restoration performances against the state-of-the-art methods with accurate and clear structural details. Moreover, we set a criterion to select images with rich structural textures. The proposed Cross-SRN outperforms the state-of-the-art methods on the selected benchmark, which demonstrates that our network has a significant advantage in preserving edges. [ABSTRACT FROM AUTHOR]

Accurate estimation and quantification of the corneal nerve fiber tortuosity in corneal confocal microscopy (CCM) is of great importance for disease understanding and clinical decision-making. However, the grading of corneal nerve tortuosity remains a great challenge due to the lack of agreements on the definition and quantification of tortuosity. In this paper, we propose a fully automated deep learning method that performs image-level tortuosity grading of corneal nerves, which is based on CCM images and segmented corneal nerves to further improve the grading accuracy with interpretability principles. The proposed method consists of two stages: 1) A pre-trained feature extraction backbone over ImageNet is fine-tuned with a proposed novel bilinear attention (BA) module for the prediction of the regions of interest (ROIs) and coarse grading of the image. The BA module enhances the ability of the network to model long-range dependencies and global contexts of nerve fibers by capturing second-order statistics of high-level features. 2) An auxiliary tortuosity grading network (AuxNet) is proposed to obtain an auxiliary grading over the identified ROIs, enabling the coarse and additional gradings to be finally fused together for more accurate final results. The experimental results show that our method surpasses existing methods in tortuosity grading, and achieves an overall accuracy of 85.64% in four-level classification. We also validate it over a clinical dataset, and the statistical analysis demonstrates a significant difference of tortuosity levels between healthy control and diabetes group. We have released a dataset with 1500 CCM images and their manual annotations of four tortuosity levels for public access. The code is available at: https://github.com/iMED-Lab/TortuosityGrading. [ABSTRACT FROM AUTHOR]

This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial location and dominant direction of the largest motion, the spatial location and dominant color of the largest color diversity along the temporal axis, etc. Then a neural network is built and trained to yield the statistical summaries given the video frames as inputs. In order to alleviate the learning difficulty, we employ several spatial partitioning patterns to encode rough spatial locations instead of exact spatial Cartesian coordinates. Our approach is inspired by the observation that human visual system is sensitive to rapidly changing contents in the visual field, and only needs impressions about rough spatial locations to understand the visual contents. To validate the effectiveness of the proposed approach, we conduct extensive experiments with four 3D backbone networks, i.e., C3D, 3D-ResNet, R(2+1)D and S3D-G. The results show that our approach outperforms the existing approaches across these backbone networks on four downstream video analysis tasks including action recognition, video retrieval, dynamic scene recognition, and action similarity labeling. The source code is publicly available at: https://github.com/laura-wang/video_repres_sts. [ABSTRACT FROM AUTHOR]

We consider the problem of referring segmentation in images and videos with natural language. Given an input image (or video) and a referring expression, the goal is to segment the entity referred by the expression in the image or video. In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the visual input. We further propose a gated multi-level fusion (GMLF) module to selectively integrate self-attentive cross-modal features corresponding to different levels of visual features. This module controls the feature fusion of information flow of features at different levels with high-level and low-level semantic information related to different attentive words. Besides, we introduce cross-frame self-attention (CFSA) module to effectively integrate temporal information in consecutive frames which extends our method in the case of referring segmentation in videos. Experiments on benchmark datasets of four referring image datasets and two actor and action video segmentation datasets consistently demonstrate that our proposed approach outperforms existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Human-object interaction (HOI) Detection is an important problem to understand how humans interact with objects. In this paper, we explore Interactiveness Knowledge which indicates whether human and object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets and alleviate the gap between diverse HOI category settings. Our core idea is to exploit an Interactiveness Network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression before HOI classification in inference. On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We utilize the human instance and body part features together to learn the interactiveness in hierarchical paradigm, i.e., instance-level and body part-level interactivenesses. Thereafter, a consistency task is proposed to guide the learning and extract deeper interactive visual clues. We extensively evaluate the proposed method on HICO-DET, V-COCO, and a newly constructed HAKE-HOI dataset. With the learned interactiveness, our method outperforms state-of-the-art HOI detection methods, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network. [ABSTRACT FROM AUTHOR]

Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limited number of paired underwater images with undistorted images as reference, training deep enhancement models for diverse degradation types is quite difficult. To boost the performance of data-driven approaches, it is essential to establish more effective learning mechanisms that mine richer supervised information from limited training sample resources. In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance via region-wise enhancement feature learning. Accordingly, we propose semantic region-wise enhancement module to better learn local enhancement features for semantic regions with multi-scale perception. After using them as complementary features and feeding them to the main branch, which extracts the global enhancement features on the original image scale, the fused features bring semantically consistent and visually superior enhancements. Extensive experiments on the publicly available datasets and our proposed dataset demonstrate the impressive performance of SGUIE-Net. The code and proposed dataset are available at https://trentqq.github.io/SGUIE-Net.html . [ABSTRACT FROM AUTHOR]

Recently, the Part-Object Relational (POR) saliency underpinned by the Capsule Network (CapsNet) has been demonstrated to be an effective modeling mechanism to improve the saliency detection accuracy. However, it is widely known that the current capsule routing operations have huge computational complexity, which seriously limited the usability of the POR saliency models in real-time applications. To this end, this paper takes an early step towards a fast POR saliency inference by proposing a novel disentangled part-object relational network. Concretely, we disentangle horizontal routing and vertical routing from the original omnidirectional capsule routing, thus generating Disentangled Capsule Routing (DCR). This mechanism enjoys two advantages. On one hand, DCR that disentangles orthogonal 1D (i.e., vertical and horizontal) routing greatly reduces parameters and routing complexity, resulting in much faster inference than omnidirectional 2D routing adopted by existing CapsNets. On the other hand, thanks to the light POR cues explored by DCR, we could conveniently integrate the part-object routing process to different feature layers in CNN, rather than just applying it to the small-scaled one as in previous works. This helps to increase saliency inference accuracy. Compared to previous POR saliency detectors, DPORTNet infers visual saliency $\left ({{5 \sim 9} }\right) \times $ faster, and is more accurate. DPORTNet is available under the open-source license at https://github.com/liuyi1989/DCR. [ABSTRACT FROM AUTHOR]

Most existing salient object detection (SOD) methods are designed for RGB images and do not take advantage of the abundant information provided by light fields. Hence, they may fail to detect salient objects of complex structures and delineate their boundaries. Although some methods have explored multi-view information of light field images for saliency detection, they require tedious pixel-level manual annotations of ground truths. In this paper, we propose a novel weakly-supervised learning framework for salient object detection on light field images based on bounding box annotations. Our method has two major novelties. First, given an input light field image and a bounding-box annotation indicating the salient object, we propose a ground truth label hallucination method to generate a pixel-level pseudo saliency map, to avoid heavy cost of pixel-level annotations. This method generates high quality pseudo ground truth saliency maps to help supervise the training, by exploiting information obtained from the light field (including depths and RGB images). Second, to exploit the multi-view nature of the light field data in learning, we propose a fusion attention module to calibrate the spatial and channel-wise light field representations. It learns to focus on informative features and suppress redundant information from the multi-view inputs. Based on these two novelties, we are able to train a new salient object detector with two branches in a weakly-supervised manner. While the RGB branch focuses on modeling the color contrast in the all-in-focus image for locating the salient objects, the Focal branch exploits the depth and the background spatial redundancy of focal slices for eliminating background distractions. Extensive experiments show that our method outperforms existing weakly-supervised methods and most fully supervised methods. [ABSTRACT FROM AUTHOR]