Search

Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employed that exploits the advantages of complex-valued representations, achieving better generalization capability on perceptual feature learning than real-valued ones. To learn more discriminative features to analyze the perceptual quality of dehazed images, we design a dual-stream CV-CNN architecture. The dual-stream model comprises a distortion-sensitive stream that operates on the dehazed RGB image, and a haze-aware stream on a novel dark channel difference image. The distortion-sensitive stream accounts for perceptual distortion artifacts, while the haze-aware stream addresses the possible presence of residual haze. Experimental results on three publicly available dehazed image quality assessment (DQA) databases demonstrate the effectiveness and generalization of our proposed CV-CNN DQA model as compared to state-of-the-art no-reference image quality assessment algorithms. [ABSTRACT FROM AUTHOR]

This paper focuses on the facial micro-expression (FME) generation task, which has potential application in enlarging digital FME datasets, thereby alleviating the lack of training data with labels in existing micro-expression datasets. Despite obvious progress in the image animation task, FME generation remains challenging because existing image animation methods can hardly encode subtle and short-term facial motion information. To this end, we present a facial-prior-guided FME generation framework that takes advantage of facial priors for facial motion generation. Specifically, we first estimate the geometric locations of action units (AUs) with detected facial landmarks. We further calculate an adaptive weighted prior (AWP) map, which alleviates the estimation error of AUs while efficiently capturing subtle facial motion patterns. To achieve smooth and realistic synthesis results, we use our proposed facial prior module to guide motion representation and generation modules in mainstream image animation frameworks. Extensive experiments on three benchmark datasets consistently show that our proposed facial prior module can be adopted in image animation frameworks and significantly improve their performance on micro-expression generation. Moreover, we use the generation technique to enlarge existing datasets, thereby improving the performance of general action recognition backbones on the FME recognition task. Our code is available at https://github.com/sysu19351158/FPB-FOMM. [ABSTRACT FROM AUTHOR]

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]

Most researchers focus on designing accurate crowd counting models with heavy parameters and computations but ignore the resource burden during the model deployment. A real-world scenario demands an efficient counting model with low-latency and high-performance. Knowledge distillation provides an elegant way to transfer knowledge from a complicated teacher model to a compact student model while maintaining accuracy. However, the student model receives the wrong guidance with the supervision of the teacher model due to the inaccurate information understood by the teacher in some cases. In this paper, we propose a dual-knowledge distillation (DKD) framework, which aims to reduce the side effects of the teacher model and transfer hierarchical knowledge to obtain a more efficient counting model. First, the student model is initialized with global information transferred by the teacher model via adaptive perspectives. Then, the self-knowledge distillation forces the student model to learn the knowledge by itself, based on intermediate feature maps and target map. Specifically, the optimal transport distance is utilized to measure the difference of feature maps between the teacher and the student to perform the distribution alignment of the counting area. Extensive experiments are conducted on four challenging datasets, demonstrating the superiority of DKD. When there are only approximately 6% of the parameters and computations from the original models, the student model achieves a faster and more accurate counting performance as the teacher model even surpasses it. [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]

Recent research advances in salient object detection (SOD) could largely be attributed to ever-stronger multi-scale feature representation empowered by the deep learning technologies. The existing SOD deep models extract multi-scale features via the off-the-shelf encoders and combine them smartly via various delicate decoders. However, the kernel sizes in this commonly-used thread are usually “fixed”. In our new experiments, we have observed that kernels of small size are preferable in scenarios containing tiny salient objects. In contrast, large kernel sizes could perform better for images with large salient objects. Inspired by this observation, we advocate the “dynamic” scale routing (as a brand-new idea) in this paper. It will result in a generic plug-in that could directly fit the existing feature backbone. This paper’s key technical innovations are two-fold. First, instead of using the vanilla convolution with fixed kernel sizes for the encoder design, we propose the dynamic pyramid convolution (DPConv), which dynamically selects the best-suited kernel sizes w.r.t. the given input. Second, we provide a self-adaptive bidirectional decoder design to accommodate the DPConv-based encoder best. The most significant highlight is its capability of routing between feature scales and their dynamic collection, making the inference process scale-aware. As a result, this paper continues to enhance the current SOTA performance. Both the code and dataset are publicly available at https://github.com/wuzhenyubuaa/DPNet. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG). To detect co-saliency (segmentation) accurately, the core problem is to well model inter-image relations between an image group. Some methods design sophisticated modules, such as recurrent neural network (RNN), to address this problem. However, order-sensitive problem is the major drawback of RNN, which heavily affects the stability of proposed CoSOD (CoSEG) model. In this paper, inspired by RNN-based model, we first propose a multi-path stable recurrent unit (MSRU), containing dummy orders mechanisms (DOM) and recurrent unit (RU). Our proposed MSRU not only helps CoSOD (CoSEG) model captures robust inter-image relations, but also reduces order-sensitivity, resulting in a more stable inference and training process. Moreover, we design a cross-order contrastive loss (COCL) that can further address order-sensitive problem by pulling close the feature embedding generated from different input orders. We validate our model on five widely used CoSOD datasets (CoCA, CoSOD3k, Cosal2015, iCoseg and MSRC), and three widely used datasets (Internet, iCoseg and PASCAL-VOC) for object co-segmentation, the performance demonstrates the superiority of the proposed approach as compared to the state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

Previous 2D saliency detection methods extract salient cues from a single view and directly predict the expected results. Both traditional and deep-learning-based 2D methods do not consider geometric information of 3D scenes. Therefore the relationship between scene understanding and salient objects cannot be effectively established. This limits the performance of 2D saliency detection in challenging scenes. In this paper, we show for the first time that saliency detection problem can be reformulated as two sub-problems: light field synthesis from a single view and light-field-driven saliency detection. This paper first introduces a high-quality light field synthesis network to produce reliable 4D light field information. Then a novel light-field-driven saliency detection network is proposed, in which a Direction-specific Screening Unit (DSU) is tailored to exploit the spatial correlation among multiple viewpoints. The whole pipeline can be trained in an end-to-end fashion. Experimental results demonstrate that the proposed method outperforms the state-of-the-art 2D, 3D and 4D saliency detection methods. Our code is publicly available at https://github.com/OIPLab-DUT/ESCNet. [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]

In this paper, a Multi-scale Contrastive Graph Convolutional Network (MC-GCN) method is proposed for unconstrained face recognition with image sets, which takes a set of media (orderless images and videos) as a face subject instead of single media (an image or video). Due to factors such as illumination, posture, media source, etc., there are huge intra-set variances in a face set, and the importance of different face prototypes varies considerably. How to model the attention mechanism according to the relationship between prototypes or images in a set is the main content of this paper. In this work, we formulate a framework based on graph convolutional network (GCN), which considers face prototypes as nodes to build relations. Specifically, we first present a multi-scale graph module to learn the relationship between prototypes at multiple scales. Moreover, a Contrastive Graph Convolutional (CGC) block is introduced to build attention control model, which focuses on those frames with similar prototypes (contrastive information) between pair of sets instead of simply evaluating the frame quality. The experiments on IJB-A, YouTube Face, and an animal face dataset clearly demonstrate that our proposed MC-GCN outperforms the state-of-the-art methods significantly. [ABSTRACT FROM AUTHOR]

Identifying the same persons across different views plays an important role in many vision applications. In this paper, we study this important problem, denoted as Multi-view Multi-Human Association (MvMHA), on multi-view images that are taken by different cameras at the same time. Different from previous works on human association across two views, this paper is focused on more general and challenging scenarios of more than two views, and none of these views are fixed or priorly known. In addition, each involved person may be present in all the views or only a subset of views, which are also not priorly known. We develop a new end-to-end deep-network based framework to address this problem. First, we use an appearance-based deep network to extract the feature of each detected subject on each image. We then compute pairwise-similarity scores between all the detected subjects and construct a comprehensive affinity matrix. Finally, we propose a Deep Assignment Network (DAN) to transform the affinity matrix into an assignment matrix, which provides a binary assignment result for MvMHA. We build both a synthetic dataset and a real image dataset to verify the effectiveness of the proposed method. We also test the trained network on other three public datasets, resulting in very good cross-domain performance. [ABSTRACT FROM AUTHOR]

The paper proposes a solution based on Generative Adversarial Network (GAN) for solving jigsaw puzzles. The problem assumes that an image is divided into equal square pieces, and asks to recover the image according to information provided by the pieces. Conventional jigsaw puzzle solvers often determine the relationships based on the boundaries of pieces, which ignore the important semantic information. In this paper, we propose JigsawGAN, a GAN-based auxiliary learning method for solving jigsaw puzzles with unpaired images (with no prior knowledge of the initial images). We design a multi-task pipeline that includes, (1) a classification branch to classify jigsaw permutations, and (2) a GAN branch to recover features to images in correct orders. The classification branch is constrained by the pseudo-labels generated according to the shuffled pieces. The GAN branch concentrates on the image semantic information, where the generator produces the natural images to fool the discriminator, while the discriminator distinguishes whether a given image belongs to the synthesized or the real target domain. These two branches are connected by a flow-based warp module that is applied to warp features to correct the order according to the classification results. The proposed method can solve jigsaw puzzles more efficiently by utilizing both semantic information and boundary information simultaneously. Qualitative and quantitative comparisons against several representative jigsaw puzzle solvers demonstrate the superiority 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]

Skeleton data have been extensively used for action recognition since they can robustly accommodate dynamic circumstances and complex backgrounds. To guarantee the action-recognition performance, we prefer to use advanced and time-consuming algorithms to get more accurate and complete skeletons from the scene. However, this may not be acceptable in time- and resource-stringent applications. In this paper, we explore the feasibility of using low-quality skeletons, which can be quickly and easily estimated from the scene, for action recognition. While the use of low-quality skeletons will surely lead to degraded action-recognition accuracy, in this paper we propose a structural knowledge distillation scheme to minimize this accuracy degradations and improve recognition model’s robustness to uncontrollable skeleton corruptions. More specifically, a teacher which observes high-quality skeletons obtained from a scene is used to help train a student which only sees low-quality skeletons generated from the same scene. At inference time, only the student network is deployed for processing low-quality skeletons. In the proposed network, a graph matching loss is proposed to distill the graph structural knowledge at an intermediate representation level. We also propose a new gradient revision strategy to seek a balance between mimicking the teacher model and directly improving the student model’s accuracy. Experiments are conducted on Kenetics400, NTU RGB+D and Penn action recognition datasets and the comparison results demonstrate the effectiveness of our scheme. [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]

Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. Existing methods mainly focus on learning modality-shared representations by embedding images from different modalities into a common feature space, in which some discriminative modality information is discarded. Different from these methods, in this paper, we propose a novel Modality-Specific Memory Network (MSMNet) to complete the missing modality information and aggregate visible and infrared modality features into a unified feature space for the VI-ReID task. The proposed model enjoys several merits. First, it can exploit the missing modality information to alleviate the modality discrepancy when only the single-modality input is provided. To the best of our knowledge, this is the first work to exploit the missing modality information completion and alleviate the modality discrepancy with the memory network. Second, to guide the learning process of the memory network, we design three effective learning strategies, including feature consistency, memory representativeness and structural alignment. By incorporating these learning strategies in a unified model, the memory network can be well learned to propagate identity-related information between modalities and boost the VI-ReID performance. Extensive experimental results on two standard benchmarks (SYSU-MM01 and RegDB) demonstrate that the proposed MSMNet performs favorably against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Human-Object Interaction (HOI) detection recognizes how persons interact with objects, which is advantageous in autonomous systems such as self-driving vehicles and collaborative robots. However, current HOI detectors are often plagued by model inefficiency and unreliability when making a prediction, which consequently limits its potential for real-world scenarios. In this paper, we address these challenges by proposing ERNet, an end-to-end trainable convolutional-transformer network for HOI detection. The proposed model employs an efficient multi-scale deformable attention to effectively capture vital HOI features. We also put forward a novel detection attention module to adaptively generate semantically rich instance and interaction tokens. These tokens undergo pre-emptive detections to produce initial region and vector proposals that also serve as queries which enhances the feature refinement process in the transformer decoders. Several impactful enhancements are also applied to improve the HOI representation learning. Additionally, we utilize a predictive uncertainty estimation framework in the instance and interaction classification heads to quantify the uncertainty behind each prediction. By doing so, we can accurately and reliably predict HOIs even under challenging scenarios. Experiment results on the HICO-Det, V-COCO, and HOI-A datasets demonstrate that the proposed model achieves state-of-the-art performance in detection accuracy and training efficiency. Codes are publicly available at https://github.com/Monash-CyPhi-AI-Research-Lab/ernet. [ABSTRACT FROM AUTHOR]

Efficient action recognition aims to classify a video clip into a specific action category with a low computational cost. It is challenging since the integrated spatial-temporal calculation (e. g., 3D convolution) introduces intensive operations and increases complexity. This paper explores the feasibility of the integration of channel splitting and filter decoupling for efficient architecture design and feature refinement by proposing a novel spatio-temporal collaborative (STC) module. STC splits the video feature channels into two groups and separately learns spatio-temporal representations in parallel with decoupled convolutional operators. Particularly, STC consists of two computation-efficient blocks, i.e., $\text {S}_{\mathrm{ T}}$ and $\text {T}_{\mathrm{ S}}$ , where they extract either spatial (${S}_{\cdot }$) or temporal (${T}_{\cdot }$) features and further refine their features with either temporal ($\cdot _{T}$) or spatial ($\cdot _{S}$) contexts globally. The spatial/temporal context refers to information dynamics aggregated from temporal/spatial axis. To thoroughly examine our method’s performance in video action recognition tasks, we conduct extensive experiments using five video benchmark datasets requiring temporal reasoning. Experimental results show that the proposed STC networks achieve a competitive trade-off between model efficiency and effectiveness. [ABSTRACT FROM AUTHOR]

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. [ABSTRACT FROM AUTHOR]

Hyperspectral videos can provide the spatial, spectral, and motion information of targets, which makes it possible to track camouflaged targets that are similar to the background. However, hyperspectral object tracking is a challenging task, due to the huge hyperspectral video data dimension and the “data hungry” problem for the model training. Insufficient training data can seriously interfere with the accuracy and generalization of the tracking models. In this paper, a dual deep Siamese network framework for hyperspectral object tracking (SiamHYPER) is proposed for learning a hyperspectral tracker from a pretrained RGB tracker in the case of the “data hungry” problem. Specifically, in addition to a pretrained RGB-based Siamese tracker, a hyperspectral target-aware module is designed to mine the spectral information during the target prediction, and a spatial-spectral cross-attention module is introduced to further fuse the deep spatial and spectral features extracted from the RGB tracker and the hyperspectral target-aware module. Benefiting from the guidance training of the RGB tracker, a robust hyperspectral object tracker can be trained effectively with only a small number of hyperspectral video samples, to overcome the “data hungry” problem. In the experiments conducted in this study, the SiamHYPER framework was verified using SiamBAN and SiamRPN++, with 13 000 frames of hyperspectral videos for training, and achieved the best performance on the publicly available hyperspectral dataset released as part of the WHISPERS Hyperspectral Object Tracking Challenge. The area under the curve (AUC) of SiamHYPER was increased by nearly 8.9% and 7.2%, respectively, when compared with the current state-of-the-art RGB-based and hyperspectral trackers. In addition, the processing speed of SiamHYPER was 19 FPS, which is much higher than that of the current state-of-the-art hyperspectral trackers. The source code is available at zhenliuzhenqi/HOT: Hyperspectral object tracking (github.com). [ABSTRACT FROM AUTHOR]

As an important field in information retrieval, fine-grained cross-modal retrieval has received great attentions from researchers. Existing fine-grained cross-modal retrieval methods made several improvements in capturing the fine-grained interplay between vision and language, failing to consider the fine-grained correspondences between the features in the image latent space and the text latent space respectively, which may lead to inaccurate inference of intra-modal relations or false alignment of cross-modal information. Considering that object detection can get the fine-grained correspondences of image region features and the corresponding semantic features, this paper proposed a novel latent space semantic supervision model based on knowledge distillation (L3S-KD), which trains classifiers supervised by the fine-grained correspondences obtained from an object detection model by using knowledge distillation for image latent space fine-grained alignment, and by the labels of objects and attributes for text latent space fine-grained alignment. Compared with existing fine-grained correspondence matching methods, L3S-KD can learn more accurate semantic similarities for local fragments in image-text pairs. Extensive experiments on MS-COCO and Flickr30K datasets demonstrate that the L3S-KD model consistently outperforms state-of-the-art methods for image-text matching. [ABSTRACT FROM AUTHOR]

Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

As a multivariate data analysis tool, canonical correlation analysis (CCA) has been widely used in computer vision and pattern recognition. However, CCA uses Euclidean distance as a metric, which is sensitive to noise or outliers in the data. Furthermore, CCA demands that the two training sets must have the same number of training samples, which limits the performance of CCA-based methods. To overcome these limitations of CCA, two novel canonical correlation learning methods based on low-rank learning are proposed in this paper for image representation, named robust canonical correlation analysis (robust-CCA) and low-rank representation canonical correlation analysis (LRR-CCA). By introducing two regular matrices, the training sample numbers of the two training datasets can be set as any values without any limitation in the two proposed methods. Specifically, robust-CCA uses low-rank learning to remove the noise in the data and extracts the maximization correlation features from the two learned clean data matrices. The nuclear norm and $L_{1}$ -norm are used as constraints for the learned clean matrices and noise matrices, respectively. LRR-CCA introduces low-rank representation into CCA to ensure that the correlative features can be obtained in low-rank representation. To verify the performance of the proposed methods, five publicly image databases are used to conduct extensive experiments. The experimental results demonstrate the proposed methods outperform state-of-the-art CCA-based and low-rank learning methods. [ABSTRACT FROM AUTHOR]

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone framework, namely CBNet, to construct high-performance detectors using existing open-source pre-trained backbones under the pre-training fine-tuning paradigm. In particular, CBNet architecture groups multiple identical backbones, which are connected through composite connections. Specifically, it integrates the high- and low-level features of multiple identical backbone networks and gradually expands the receptive field to more effectively perform object detection. We also propose a better training strategy with auxiliary supervision for CBNet-based detectors. CBNet has strong generalization capabilities for different backbones and head designs of the detector architecture. Without additional pre-training of the composite backbone, CBNet can be adapted to various backbones (i.e., CNN-based vs. Transformer-based) and head designs of most mainstream detectors (i.e., one-stage vs. two-stage, anchor-based vs. anchor-free-based). Experiments provide strong evidence that, compared with simply increasing the depth and width of the network, CBNet introduces a more efficient, effective, and resource-friendly way to build high-performance backbone networks. Particularly, our CB-Swin-L achieves 59.4% box AP and 51.6% mask AP on COCO test-dev under the single-model and single-scale testing protocol, which are significantly better than the state-of-the-art results (i.e., 57.7% box AP and 50.2% mask AP) achieved by Swin-L, while reducing the training time by $6\times $. With multi-scale testing, we push the current best single model result to a new record of 60.1% box AP and 52.3% mask AP without using extra training data. Code is available at https://github.com/VDIGPKU/CBNetV2 . [ABSTRACT FROM AUTHOR]

Recently, deep learning based multispectral (MS) and panchromatic (PAN) image fusion methods have been proposed, which extracted features automatically and hierarchically by a series of non-linear transformations to model the complicated imaging discrepancy. But they always pay more attention to the extraction and compensation of spatial details and use the mean squared error or mean absolute error as a loss function, regardless of the preservation of spectral information contained in multispectral images. For the sake of the improvements in both spatial and spectral resolution, this paper presents a novel fusion model that takes the spectral preservation into consideration, and learns the spectral cues from the process of generating a spectrally refined multispectral image, which is constrained by a spectral loss between the generated image and the reference image. Then these spectral cues are used to modulate the PAN features to obtain final fusion result. Experimental results on reduced-resolution and full-resolution datasets demonstrate that the proposed method can obtain a better fusion result in terms of visual inspection and evaluation indices when compared with current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Camouflaged object detection (COD) aims to detect/segment camouflaged objects embedded in the environment, which has attracted increasing attention over the past decades. Although several COD methods have been developed, they still suffer from unsatisfactory performance due to the intrinsic similarities between the foreground objects and background surroundings. In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection. Specifically, we propose a Boundary Guidance Module (BGM) to explicitly model the boundary characteristic, which can provide boundary-enhanced features to boost the COD performance. To capture the scale variations of the camouflaged objects, we propose a Multi-scale Feature Aggregation Module (MFAM) to characterize the multi-scale information from each layer and obtain the aggregated feature representations. Furthermore, we propose a Cross-level Fusion and Propagation Module (CFPM). In the CFPM, the feature fusion part can effectively integrate the features from adjacent layers to exploit the cross-level correlations, and the feature propagation part can transmit valuable context information from the encoder to the decoder network via a gate unit. Finally, we formulate a unified and end-to-end trainable framework where cross-level features can be effectively fused and propagated for capturing rich context information. Extensive experiments on three benchmark camouflaged datasets demonstrate that our FAP-Net outperforms other state-of-the-art COD models. Moreover, our model can be extended to the polyp segmentation task, and the comparison results further validate the effectiveness of the proposed model in segmenting polyps. The source code and results will be released at https://github.com/taozh2017/FAPNet. [ABSTRACT FROM AUTHOR]

Visible-infrared person re-identification (VI-ReID) task aims to retrieve the same person between visible and infrared images. VI-ReID is challenging as the images captured by different spectra present large cross-modality discrepancy. Many methods adopt a two-stream network and design additional constraint conditions to extract shared features for different modalities. However, the interaction between the feature extraction processes of different modalities is rarely considered. In this paper, a partially interactive collaboration method is proposed to exploit the complementary information of different modalities to reduce the modality gap for VI-ReID. Specifically, the proposed method is achieved in a partially interactive-shared architecture: collaborative shallow layers and shared deep layers. The collaborative shallow layers consider the interaction between modality-specific features of different modalities, encouraging the feature extraction processes of different modalities constrain each other to enhance feature representations. The shared deep layers further embed the modality-specific features to a common space to endow them the same identity discriminability. To ensure the interactive collaborative learning implement effectively, the conventional loss and collaborative loss are utilized jointly to train the whole network. Extensive experiments on two publicly available VI-ReID datasets verify the superiority of the proposed PIC method. Specifically, the proposed method achieves a rank-1 accuracy of 83.6% and 57.5% on RegDB and SYSU-MM01 datasets, respectively. [ABSTRACT FROM AUTHOR]

Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multi-scale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically leads to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deblurring via a single forward pass. Our BANet utilizes region-based self-attention with multi-kernel strip pooling to disentangle blur patterns of different magnitudes and orientations and cascaded parallel dilated convolution to aggregate multi-scale content features. Extensive experimental results on the GoPro and RealBlur benchmarks demonstrate that the proposed BANet performs favorably against the state-of-the-arts in blurred image restoration and can provide deblurred results in real-time. [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]

Arbitrary style transfer aims at migrating the style of a reference style painting to a target content image. Existing methods find it challenging to achieve good content fidelity and style migration at the same time. Moreover, they all rely on manually defined content and style, which is of limited universality and robustness. In this paper, we propose to introduce contrastive learning into style transfer, instructing the network to automatically learn to model the structural content and artistic style based on natural contrastive relationships in style transfer. Compared with existing methods, our learned modeling of content and style is more robust and universal. In addition, we further propose instance-wise contrastive style losses and a patch-wise contrastive content loss to guide style transfer. Combining the proposed contrastive losses and two self-reconstruction strategies, we develop a new style transfer framework, which is pluggable and can be flexibly applied to various style transfer modules. Experimental results demonstrate that our method has strong flexibility and synthesizes stylized images with higher quality. [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]

Generation of a 3D model of an object from multiple views has a wide range of applications. Different parts of an object would be accurately captured by a particular view or a subset of views in the case of multiple views. In this paper, a novel coarse-to-fine network (C2FNet) is proposed for 3D point cloud generation from multiple views. C2FNet generates subsets of 3D points that are best captured by individual views with the support of other views in a coarse-to-fine way, and then fuses these subsets of 3D points to a whole point cloud. It consists of a coarse generation module where coarse point clouds are constructed from multiple views by exploring the cross-view spatial relations, and a fine generation module where the coarse point cloud features are refined under the guidance of global consistency in appearance and context. Extensive experiments on the benchmark datasets have demonstrated that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Contrastive self-supervised learning (CSSL) has achieved promising results in extracting visual features from unlabeled data. Most of the current CSSL methods are used to learn global image features with low-resolution that are not suitable or efficient for pixel-level tasks. In this paper, we propose a coarse-to-fine CSSL framework based on a novel contrasting strategy to address this problem. It consists of two stages, one for encoder pre-training to learn global features and the other for decoder pre-training to derive local features. Firstly, the novel contrasting strategy takes advantage of the spatial structure and semantic meaning of different regions and provides more cues to learn than that relying only on data augmentation. Specifically, a positive pair is built from two nearby patches sampled along the direction of the texture if they fall into the same cluster. A negative pair is generated from different clusters. When the novel contrasting strategy is applied to the coarse-to-fine CSSL framework, global and local features are learned successively by forcing the positive pair close to each other and the negative pair apart in an embedding space. Secondly, a discriminant constraint is incorporated into the per-pixel classification model to maximize the inter-class distance. It makes the classification model more competent at distinguishing between different categories that have similar appearance. Finally, the proposed method is validated on four SAR images for land-cover classification with limited labeled data and substantially improves the experimental results. The effectiveness of the proposed method is demonstrated in pixel-level tasks after comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Existing crowd counting designs usually exploit multi-branch structures to address the scale diversity problem. However, branches in these structures work in a competitive rather than collaborative way. In this paper, we focus on promoting collaboration between branches. Specifically, we propose an attention-guided collaborative counting module (AGCCM) comprising an attention-guided module (AGM) and a collaborative counting module (CCM). The CCM promotes collaboration among branches by recombining each branch’s output into an independent count and joint counts with other branches. The AGM capturing the global attention map through a transformer structure with a pair of foreground-background related loss functions can distinguish the advantages of different branches. The loss functions do not require additional labels and crowd division. In addition, we design two kinds of bidirectional transformers (Bi-Transformers) to decouple the global attention to row attention and column attention. The proposed Bi-Transformers are able to reduce the computational complexity and handle images in any resolution without cropping the image into small patches. Extensive experiments on several public datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art crowd counting methods. [ABSTRACT FROM AUTHOR]

With the help of convolutional neural networks (CNNs), deep learning-based methods have achieved remarkable performance in face super-resolution (FSR) task. Despite their success, most of the existing methods neglect non-local correlations of face images, leaving much room for improvement. In this paper, we introduce a novel end-to-end trainable attention-driven graph neural network (AD-GNN) for more discriminative feature extraction and feature relation modeling. This is achieved by two major components. The first component is a cross-scale dynamic graph (CDG) block. The CDG block considers cross-scale relationships of patches in distant areas and employs two dynamic graphs to construct enhanced features. The second component is a series of channel attention and spatial dynamic graph (CASDG) blocks. A CASDG block has a channel-wise attention unit and a spatial-aware dynamic graph (SDG) unit. The SDG unit extracts informative features by exploring spatial non-local self-similarity information of the patches using dynamic graph convolution. Using these two components, facial details can be effectively reconstructed with the help of information supplemented by similar but spatially remote patches and structural information of faces. Extensive experiments on two public benchmarks demonstrate the superiority of AD-GNN over the state-of-the-art FSR methods. [ABSTRACT FROM AUTHOR]

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos. At the same time, the method also won the first place in the MSU Deinterlacer Benchmark. The code is available at: https://github.com/anymyb/MFDIN. [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]

Many computer vision applications rely on feature detection and description, hence the need for computationally efficient and robust 4D light field (LF) feature detectors and descriptors. In this paper, we propose a novel light field feature descriptor based on the Fourier disparity layer representation, for light field imaging applications. After the Harris feature detection in a scale-disparity space, the proposed feature descriptor is then extracted using a circular neighborhood rather than a square neighborhood. It is shown to yield more accurate feature matching, compared with the LiFF LF feature, with a lower computational complexity. In order to evaluate the feature matching performance with the proposed descriptor, we generated a synthetic stereo LF dataset with ground truth matching points. Experimental results with synthetic and real-world dataset show that our solution outperforms existing methods in terms of both feature detection robustness and feature matching accuracy. [ABSTRACT FROM AUTHOR]

Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-point, and similar clothing still bring great challenges. In order to tackle these challenges, extracting discriminative feature representation is crucial. Most of the existing methods focus on extracting ReID features from individual images separately. However, when matching two images, we propose that the ReID features of a query image should be dynamically adjusted based on the contextual information from the gallery image it matches. We call this type of ReID features conditional feature embedding. In this paper, we propose a novel ReID framework that extracts conditional feature embedding based on the aligned visual clues between image pairs, called Clue Alignment based Conditional Embedding (CACE-Net). CACE-Net applies an attention module to build a detailed correspondence graph between crucial visual clues in image pairs and uses discrepancy-based GCN to embed the obtained complex correspondence information into the conditional features. The experiments show that CACE-Net achieves state-of-the-art performance on three public datasets [ABSTRACT FROM AUTHOR]

Reading arbitrary-shaped text in an end-to-end fashion has received particularly growing interested in computer vision. In this paper, we study the problem of scene text spotting, which aims to detect and recognize text from cluttered images simultaneously and propose an end-to-end trainable neural network named Boundary TextSpotter. Different from existing methods that describe the shape of text instance with bounding box or shape mask, Boundary TextSpotter formulates it as a set of boundary points. Besides, the representation of such boundary points provides the order of reading text. Benefiting from the representation on both detection and recognition, Boundary TextSpotter can easily deal with the text of arbitrary shapes. Further, to efficiently detect the boundary points of the text, a single-stage text detector is proposed, which can almost perform at a real-time speed. Experiments on three challenging datasets, including ICDAR2015, Total-Text and CTW1500 demonstrate that the proposed method achieves state-of-the-art or competitive results, meanwhile significantly improving the inference speed. [ABSTRACT FROM AUTHOR]

In this paper, a full-reference video quality assessment (VQA) model is designed for the perceptual quality assessment of the screen content videos (SCVs), called the hybrid spatiotemporal feature-based model (HSFM). The SCVs are of hybrid structure including screen and natural scenes, which are perceived by the human visual system (HVS) with different visual effects. With this consideration, the three dimensional Laplacian of Gaussian (3D-LOG) filter and three dimensional Natural Scene Statistics (3D-NSS) are exploited to extract the screen and natural spatiotemporal features, based on the reference and distorted SCV sequences separately. The similarities of these extracted features are then computed independently, followed by generating the distorted screen and natural quality scores for screen and natural scenes. After that, an adaptive screen and natural quality fusion scheme through the local video activity is developed to combine them for arriving at the final VQA score of the distorted SCV under evaluation. The experimental results on the Screen Content Video Database (SCVD) and Compressed Screen Content Video Quality (CSCVQ) databases have shown that the proposed HSFM is more in line with the perceptual quality assessment of the SCVs perceived by the HVS, compared with a variety of classic and latest IQA/VQA models. [ABSTRACT FROM AUTHOR]

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns – typically the combination of selective characteristics and its variations, are too highly dependent on the network’s non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder’s design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD. [ABSTRACT FROM AUTHOR]

Text-based person search aims at retrieving the target person in an image gallery using a descriptive sentence of that person. The core of this task is to calculate a similarity score between the pedestrian image and description, which requires inferring the complex latent correspondence between image sub-regions and textual phrases at different scales. Transformer is an intuitive way to model the complex alignment by its self-attention mechanism. Most previous Transformer-based methods simply concatenate image region features and text features as input and learn a cross-modal representation in a brute force manner. Such weakly supervised learning approaches fail to explicitly build alignment between image region features and text features, causing an inferior feature distribution. In this paper, we present CFLT, Conditional Feature Learning based Transformer. It maps the sub-regions and phrases into a unified latent space and explicitly aligns them by constructing conditional embeddings where the feature of data from one modality is dynamically adjusted based on the data from the other modality. The output of our CFLT is a set of similarity scores for each sub-region or phrase rather than a cross-modal representation. Furthermore, we propose a simple and effective multi-modal re-ranking method named Re-ranking scheme by Visual Conditional Feature (RVCF). Benefit from the visual conditional feature and better feature distribution in our CFLT, the proposed RVCF achieves significant performance improvement. Experimental results show that our CFLT outperforms the state-of-the-art methods by 7.03% in terms of top-1 accuracy and 5.01% in terms of top-5 accuracy on the text-based person search dataset. [ABSTRACT FROM AUTHOR]

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework is rooted in the view that the perceptually meaningful features could be well exploited to characterize the visual quality, and the natural image statistical behaviors are exploited in an effort to deliver the accurate predictions. Herein, the PR features from the distorted images are learned by a mutual learning scheme with the pristine reference as the supervision, and the discriminative characteristics of PR features are further ensured with the triplet constraints. Given a distorted image for quality inference, the feature level disentanglement is performed with an invertible neural layer for final quality prediction, leading to the PR and the corresponding distortion features for comparison. The effectiveness of our proposed method is demonstrated on four popular IQA databases, and superior performance on cross-database evaluation also reveals the high generalization capability of our method. The implementation of our method is publicly available on https://github.com/Baoliang93/FPR. [ABSTRACT FROM AUTHOR]

Multi-object tracking and segmentation (MOTS) is a derivative task of multi-object tracking (MOT). The new setting encourages the learning of more discriminative high-quality embeddings. In this paper, we focus on the problem of exploring the relationship between the segmenter and the tracker, and propose an efficient Object Point set Inductive Tracker (OPITrack) based on it. First, we discover that after a single attention layer, the high-dimensional, key point embedding will show feature averaging. To alleviate this phenomenon, we propose an embedding generalization training strategy for sparse training and dense testing. This strategy allows the network to increase randomness in training and encourages the tracker to learn more discriminative features. In addition, to learn the desired embedding space, we propose a general Trip-hard sample augmentation loss. The loss uses patches that are not distinguishable by the segmenter to join the feature learning and force the embedding network to learn the difference between false positives and true positives. Our method was validated on two MOTS benchmark datasets and achieved promising results. In addition, our OPITrack can achieve better performance for the raw model while costing less video memory (VRAM) at training time. [ABSTRACT FROM AUTHOR]

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR. [ABSTRACT FROM AUTHOR]

With the dramatic increase in the amount of multimedia data, cross-modal similarity retrieval has become one of the most popular yet challenging problems. Hashing offers a promising solution for large-scale cross-modal data searching by embedding the high-dimensional data into the low-dimensional similarity preserving Hamming space. However, most existing cross-modal hashing usually seeks a semantic representation shared by multiple modalities, which cannot fully preserve and fuse the discriminative modal-specific features and heterogeneous similarity for cross-modal similarity searching. In this paper, we propose a joint specifics and consistency hash learning method for cross-modal retrieval. Specifically, we introduce an asymmetric learning framework to fully exploit the label information for discriminative hash code learning, where 1) each individual modality can be better converted into a meaningful subspace with specific information, 2) multiple subspaces are semantically connected to capture consistent information, and 3) the integration complexity of different subspaces is overcome so that the learned collaborative binary codes can merge the specifics with consistency. Then, we introduce an alternatively iterative optimization to tackle the specifics and consistency hashing learning problem, making it scalable for large-scale cross-modal retrieval. Extensive experiments on five widely used benchmark databases clearly demonstrate the effectiveness and efficiency of our proposed method on both one-cross-one and one-cross-two retrieval tasks. [ABSTRACT FROM AUTHOR]

Domain adaptation leverages rich knowledge from a related source domain so that it can be used to perform tasks in a target domain. For more knowledge to be obtained under relaxed conditions, domain adaptation methods have been widely used in pattern recognition and image classification. However, most of the existing domain adaptation methods only consider how to minimize different distributions of the source and target domains, which neglects what should be transferred for a specific task and suffers negative transfer by distribution outliers. To address these problems, in this paper, we propose a novel domain adaptation method called weighted correlation embedding learning (WCEL) for image classification. In the WCEL approach, we seamlessly integrated correlation learning, graph embedding, and sample reweighting into a unified learning model. Specifically, we extracted the maximum correlated features from the source and target domains for image classification tasks. In addition, two graphs were designed to preserve the discriminant information from interclass samples and neighborhood relations in intraclass samples. Furthermore, to prevent the negative transfer problem, we developed an efficient sample reweighting strategy to predict the target with different confidence levels. To verify the performance of the proposed method in image classification, extensive experiments were conducted with several benchmark databases, verifying the superiority of the WCEL method over other state-of-the-art domain adaptation algorithms. [ABSTRACT FROM AUTHOR]