Search

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key challenge is to measure the semantic similarity across different modalities. Although significant progress has been achieved, existing approaches typically suffer from two major limitations: (1) It hurts the accuracy of the representation by directly exploiting the bottom-up attention based region-level features where each region is equally treated. (2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism. To address these limitations, we propose a Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR. Specifically, we delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules. One learns the global representation via the self-attention algorithm, noted as Self-Guided Enhancement (SGE) module. The other module benefits from the pre-trained CLIP module, which provides a novel scheme to exploit and transfer the knowledge from an off-the-shelf model, noted as CLIP-Guided Enhancement (CGE) module. Moreover, we incorporate the training mechanism of MoCo into ITR, in which two dynamic queues are employed to enrich and enlarge the scale of negative sample pairs. Meanwhile, a Unified Training Objective (UTO) is developed to learn from mini-batch based and dynamic queue based samples. Extensive experiments on the benchmark MSCOCO and Flickr30K datasets demonstrate the superiority of both retrieval accuracy and inference efficiency. For instance, compared with the existing best method NAAF, the metric R@1 of our USER on the MSCOCO 5K Testing set is improved by 5% and 2.4% on caption retrieval and image retrieval without any external knowledge or pre-trained model while enjoying over 60 times faster inference speed. Our source code will be released at https://github.com/zhangy0822/USER. [ABSTRACT FROM AUTHOR]

Few-shot learning (FSL) for human–object interaction (HOI) aims at recognizing various relationships between human actions and surrounding objects only from a few samples. It is a challenging vision task, in which the diversity and interactivity of human actions result in great difficulty to learn an adaptive classifier to catch ambiguous interclass information. Therefore, traditional FSL methods usually perform unsatisfactorily in complex HOI scenes. To this end, we propose dynamic graph-in-graph networks (DGIG-Net), a novel graph prototypes framework to learn a dynamic metric space by embedding a visual subgraph to a task-oriented cross-modal graph for few-shot HOI. Specifically, we first build a knowledge reconstruction graph to learn latent representations for HOI categories by reconstructing the relationship among visual features, which generates visual representations under the category distribution of every task. Then, a dynamic relation graph integrates both reconstructible visual nodes and dynamic task-oriented semantic information to explore a graph metric space for HOI class prototypes, which applies the discriminative information from the similarities among actions or objects. We validate DGIG-Net on multiple benchmark datasets, on which it largely outperforms existing FSL approaches and achieves state-of-the-art results. [ABSTRACT FROM AUTHOR]

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior knowledge, the performance of SGG is significantly improved. Inspired by this observation, in this article, we propose a relation regularized network (R2-Net), which can predict whether there is a relationship between two objects and encode this relation into object feature refinement and better SGG. Specifically, we first construct an affinity matrix among detected objects to represent the probability of a relationship between two objects. Graph convolution networks (GCNs) over this relation affinity matrix are then used as object encoders, producing relation-regularized representations of objects. With these relation-regularized features, our R2-Net can effectively refine object labels and generate scene graphs. Extensive experiments are conducted on the visual genome dataset for three SGG tasks (i.e., predicate classification, scene graph classification, and scene graph detection), demonstrating the effectiveness of our proposed method. Ablation studies also verify the key roles of our proposed components in performance improvement. [ABSTRACT FROM AUTHOR]

Visual tracking is a very critical issue in computer vision and video processing. For Discriminative Correlation Filter (DCF)-based tracking methods, it is very essential and meaningful to adaptively incorporate reliable target and surrounding information from video frames. However, most existing DCF-based trackers solely rely on pre-defined and fixed constraints such as a binary mask or quadratic function-based regularization to improve the discrimination. Unfortunately, such attempts fail to adjust the constraints according to the change of tracking circumstance in the video sequence, and thus lead to the lack of reliability of learned filters. To mitigate these problems, we present a novel DCF-based tracking method that introduces an adaptive target-and-surrounding soft mask (ATSM) into the learning formula. The adaptive soft mask that is represented by float numbers contains the detail information for both target region and its surrounding information: first, for the background area, it introduces meaningful background information and suppressing uninformative one; second, for the target area inside the bounding box, it helps to focus on the reliable area and repress the rapidly changing area; third, the target-and-surrounding soft mask is adaptively adjusted based on the variations of the target and its surrounding during the tracking process. By jointly modeling the filter and the adaptive soft mask, our ATSM tracker achieves an efficient integration of meaningful information of both foreground and background and performs favorably against state-of-the-art algorithms on seven well-known benchmarks. [ABSTRACT FROM AUTHOR]

Stego-images are often contaminated by interchannel noise or active noise attack when communicating on the Web. And it is challenging to restore embedded image from corrupted stego-image. This paper studies a kNN-bit approximation algorithm to remove noises in embedded image. The proposed algorithm distinguishes reliable bits from extracted bits, and estimates pixel values by keeping reliable bits unchanged and correcting unreliable bits. Specifically, the 8th (highest) unreliable bit of a pixel can be approximated with its nearest neighbor pixels. And then, if an unreliable bit locates at any one of the $5^{th}\sim 7^{th}$ 5 t h ∼ 7 t h bits of a pixel, it is adjusted with two nearest neighbors of the pixel, where the pixel is in-between these two nearest neighbors. Finally, for other unreliable bits, each one is approximated by the maximum and minimum possible values of nearest neighbors of its pixel. We conduct experiments for illustrating the efficiency, and demonstrate that the proposed algorithm can recover the embedded images with good visual quality from corrupted stego-images. [ABSTRACT FROM AUTHOR]

Multimodal emotion recognition in conversational videos (ERC) develops rapidly in recent years. To fully extract the relative context from video clips, most studies build their models on the entire dialogues which make them lack of real-time ERC ability. Different from related researches, a novel multimodal emotion recognition model for conversational videos based on reinforcement learning and domain knowledge (ERLDK) is proposed in this paper. In ERLDK, the reinforcement learning algorithm is introduced to conduct real-time ERC with the occurrence of conversations. The collection of history utterances is composed as an emotion-pair which represents the multimodal context of the following utterance to be recognized. Dueling deep-Q-network (DDQN) based on gated recurrent unit (GRU) layers is designed to learn the correct action from the alternative emotion categories. Domain knowledge is extracted from public dataset based on the former information of emotion-pairs. The extracted domain knowledge is used to revise the results from the RL module and is transformed into other dataset to examine the rationality. The experimental results on datasets show that ERLDK achieves the state-of-the-art results on weighted average and most of the specific emotion categories. [ABSTRACT FROM AUTHOR]

Remote sensing image captioning (RSIC), which aims at generating a well-formed sentence for a remote sensing image, has attracted more attention in recent years. The general framework for RSIC is the encoder–decoder architecture containing two submodels of encoder and decoder. Although the significant performance is obtained, the encoder–decoder architecture is a black-box model with a lack of explainability. To overcome this drawback, in this article, we propose a new explainable word–sentence framework for RSIC. The proposed word–sentence framework consists of two parts: word extractor and sentence generator, where the former extracts the valuable words in the given remote sensing image, while the latter organizes these words into a well-formed sentence. The proposed framework decomposes RSIC into a word classification task and a word sorting task, which is more in line with human intuitive understanding. On the basis of the word–sentence framework, some ablation experiments are conducted on the three public RSIC data sets of Sydney-captions, UCM-captions, and RSICD to explore the specific and effective network structures. In order to evaluate the proposed word–sentence framework objectively, we further conduct some comparative experiments on these three data sets and achieve comparable results in comparison with the encoder–decoder-based methods. [ABSTRACT FROM AUTHOR]

Fusion of multimodal features is a momentous problem for video emotion recognition. As the development of deep learning, directly fusing feature matrixes of each mode through neural networks at feature level becomes mainstream method. However, unlike unimodal issues, for multimodal analysis, finding the correlations between different modal is as important as discovering effective unimodal features. To make up the deficiency in unearthing the intrinsic relationships between multimodal, a novel modularized multimodal emotion recognition model based on deep canonical correlation analysis (MERDCCA) is proposed in this letter. In MERDCCA, four utterances are gathered as a new group and each utterance contains text, audio and visual information as multimodal input. Gated recurrent unit layers are used to extract the unimodal features. Deep canonical correlation analysis based on encoder-decoder network is designed to extract cross-modal correlations by maximizing the relevance between multimodal. The experiments on two public datasets show that MERDCCA achieves the better results. [ABSTRACT FROM AUTHOR]

Extreme instance imbalance among categories and combinatorial explosion make the recognition of Human-Object Interaction (HOI) a challenging task. Few studies have addressed both challenges directly. Motivated by the success of few-shot learning that learns a robust model from a few instances, we formulate HOI as a few-shot task in a meta-learning framework to alleviate the above challenges. Due to the fact that the intrinsical characteristic of HOI is diverse and interactive, we propose a Semantic-guided Attentive Prototypes Network (SAPNet) framework to learn a semantic-guided metric space where HOI recognition can be performed by computing distances to attentive prototypes of each class. Specifically, the model generates attentive prototypes guided by the category names of actions and objects, which highlight the commonalities of images from the same class in HOI. In addition, we design two alternative prototypes calculation methods, i.e., Prototypes Shift (PS) approach and Hallucinatory Graph Prototypes (HGP) approach, which explore to learn a suitable category prototypes representations in HOI. Finally, in order to realize the task of few-shot HOI, we reorganize 2 HOI benchmark datasets with 2 split strategies, i.e., HICO-NN, TUHOI-NN, HICO-NF, and TUHOI-NF. Extensive experimental results on these datasets have demonstrated the effectiveness of our proposed SAPNet approach. [ABSTRACT FROM AUTHOR]

Recently, remote sensing image captioning (RSIC) has drawn an increasing attention. In this field, the encoder–decoder-based methods have become the mainstream due to their excellent performance. In the encoder–decoder framework, the convolutional neural network (CNN) is used to encode a remote sensing image into a semantic feature vector, and a sequence model such as long short-term memory (LSTM) is subsequently adopted to generate a content-related caption based on the feature vector. During the traditional training stage, the probability of the target word at each time step is forcibly optimized to 1 by the cross entropy (CE) loss. However, because of the variability and ambiguity of possible image captions, the target word could be replaced by other words like its synonyms, and therefore, such an optimization strategy would result in the overfitting of the network. In this article, we explore the overfitting phenomenon in the RSIC caused by CE loss and correspondingly propose a new truncation cross entropy (TCE) loss, aiming to alleviate the overfitting problem. In order to verify the effectiveness of the proposed approach, extensive comparison experiments are performed on three public RSIC data sets, including UCM-captions, Sydney-captions, and RSICD. The state-of-the-art result of Sydney-captions and RSICD and the competitive results of UCM-captions achieved by TCE loss demonstrate that the proposed method is beneficial to RSIC. [ABSTRACT FROM AUTHOR]

With the benefits from deep learning technology, generating captions for remote sensing images has become achievable, and great progress has been made in this field in the recent years. However, a large-scale variation of remote sensing images, which would lead to errors or omissions in feature extraction, still limits the further improvement of caption quality. To address this problem, we propose a denoising-based multi-scale feature fusion (DMSFF) mechanism for remote sensing image captioning in this letter. The proposed DMSFF mechanism aggregates multiscale features with the denoising operation at the stage of visual feature extraction. It can help the encoder–decoder framework, which is widely used in image captioning, to obtain the denoising multiscale feature representation. In experiments, we apply the proposed DMSFF in the encoder–decoder framework and perform the comparative experiments on two public remote sensing image captioning data sets including UC Merced (UCM)-captions and Sydney-captions. The experimental results demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Vision-to-language tasks aim to integrate computer vision and natural language processing together, which has attracted the attention of many researchers. For typical approaches, they encode image into feature representations and decode it into natural language sentences. While they neglect high-level semantic concepts and subtle relationships between image regions and natural language elements. To make full use of these information, this paper attempt to exploit the text-guided attention and semantic-guided attention (SA) to find the more correlated spatial information and reduce the semantic gap between vision and language. Our method includes two-level attention networks. One is the text-guided attention network which is used to select the text-related regions. The other is SA network which is used to highlight the concept-related regions and the region-related concepts. At last, all these information are incorporated to generate captions or answers. Practically, image captioning and visual question answering experiments have been carried out, and the experimental results have shown the excellent performance of the proposed approach. [ABSTRACT FROM AUTHOR]

In many real-world applications, we are often confronted with high dimensional data which are represented by various heterogeneous views. How to cluster this kind of data is still a challenging problem due to the curse of dimensionality and effectively integration of different views. To address this problem, we propose two parameter-free weighted multi-view projected clustering methods which perform structured graph learning and dimensionality reduction simultaneously. We can use the obtained structured graph directly to extract the clustering indicators, without performing other discretization procedures as previous graph-based clustering methods have to do. Moreover, two parameter-free strategies are adopted to learn an optimal weight for each view automatically, without introducing a regularization parameter as previous methods do. Extensive experiments on several public datasets demonstrate that the proposed methods outperform other state-of-the-art approaches and can be used more practically. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN) has shown their advantages in salient object detection. CNN can generate great saliency maps because it can obtain high-level semantic information. And the semantic information is usually achieved by stacking multiple convolutional layers and pooling layers. However, multiple pooling operations will reduce the size of the feature map and easily blur the boundary of the salient object. Therefore, such operations are not beneficial to generate great saliency results. To alleviate this issue, we propose a novel edge information-guided hierarchical feature fusion network (HFFNet). Our network fuses features hierarchically and retains accurate semantic information and clear edge information effectively. Specifically, we extract image features from different levels of VGG. Then, we fuse the features hierarchically to generate high-level semantic information and low-level edge information. In order to retain better information at different levels, we adopt a one-to-one hierarchical supervision strategy to supervise the generation of low-level information and high-level information respectively. Finally, we use low-level edge information to guide the saliency map generation, and the edge guidance fusion is able to identify saliency regions effectively. The proposed HFFNet has been extensively evaluated on five traditional benchmark datasets. The experimental results demonstrate that the proposed model is fairly effective in salient object detection compared with 10 state-of-the-art models under different evaluation indicators, and it is superior to most of the comparison models. [ABSTRACT FROM AUTHOR]

Smoke density estimation from a single image is a totally new but highly ill-posed problem. To solve the problem, we stack several convolutional encoder-decoder structures together to propose a wave-shaped neural network, termed W-Net. Stacking encoder-decoders directly increases the network depth, leading to the enlargement of receptive fields for encoding more semantic information. To maximize the degrees of feature re-usage, we copy and resize the outputs of encoding layers to corresponding decoding layers, and then concatenate them to implement short-cut connections for improving spatial accuracy. The crests and troughs of W-Net are special structures containing abundant localization and semantic information, so we also use short-cut connections between these structures and decoding layers. Estimated smoke density is useful in many applications, such as smoke segmentation, smoke detection, disaster simulation. Experimental results show that our method outperforms existing methods on both smoke density estimation and segmentation. It also achieves satisfying results in visual detection of auto exhausts. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, and the output is a keyshot sequence. Our key idea is to learn a deep summarization network with attention mechanism to mimic the way of selecting the keyshots of human. To this end, we propose a novel video summarization framework named attentive encoder–decoder networks for video summarization (AVS), in which the encoder uses a bidirectional long short-term memory (BiLSTM) to encode the contextual information among the input video frames. As for the decoder, two attention-based LSTM networks are explored by using additive and multiplicative objective functions, respectively. Extensive experiments are conducted on two video summarization benchmark datasets, i.e., SumMe and TVSum. The results demonstrate the superiority of the proposed AVS-based approaches against the state-of-the-art approaches, with remarkable improvements on both datasets. [ABSTRACT FROM AUTHOR]

Existence of haze significantly degrades visual quality and hence negatively affects the performance of visual surveillance, video analysis, and human–machine interaction. To remove haze from a visual signal, in this paper, we propose a generative adversarial network for visual haze removal called HRGAN. HRGAN consists of a generator network and a discriminator network. A unified network jointly estimating transmission maps, atmospheric light, and haze-free images (called UNTA) is proposed as the generator network of HRGAN. Instead of being optimized by minimizing the pixel-wise loss, HRGAN is optimized by minimizing a novel loss function consisting of pixel-wise loss, perceptual loss, and adversarial loss produced by a discriminator network. Classical model-based image dehazing algorithms consist of three separate stages: 1) estimating transmission map; 2) estimating atmospheric light; and 3) restoring haze-free image by using an atmospheric scattering model to process the transmission map and atmospheric light. Such a separate scheme is not guaranteed to achieve optimal results. On the contrary, UNTA performs transmission map estimation and atmospheric light estimation simultaneously to obtain joint optimal solutions. The experimental results on both synthetic and real-world image databases demonstrate that HRGAN outperforms the state-of-the-art algorithms in terms of both effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Video captioning has been attracting broad research attention in the multimedia community. However, most existing approaches heavily rely on static visual information or partially capture the local temporal knowledge (e.g., within 16 frames), thus hardly describing motions accurately from a global view. In this paper, we propose a novel video captioning framework, which integrates bidirectional long-short term memory (BiLSTM) and a soft attention mechanism to generate better global representations for videos as well as enhance the recognition of lasting motions in videos. To generate video captions, we exploit another long-short term memory as a decoder to fully explore global contextual information. The benefits of our proposed method are two fold: 1) the BiLSTM structure comprehensively preserves global temporal and visual information and 2) the soft attention mechanism enables a language decoder to recognize and focus on principle targets from the complex content. We verify the effectiveness of our proposed video captioning framework on two widely used benchmarks, that is, microsoft video description corpus and MSR-video to text, and the experimental results demonstrate the superiority of the proposed approach compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

To benefit the skin care, this paper aims to design an automatic and effective visual analysis framework, with the expectation of recognizing the skin disease from a given image conveying the disease affected surface. This task is nontrivial, since it is hard to collect sufficient well-labeled samples. To address such problem, we present a novel transfer learning model, which is able to incorporate external knowledge obtained from the rich and relevant Web images contributed by grassroots. In particular, we first construct a target domain by crawling a small set of images from vertical and professional dermatological websites. We then construct a source domain by collecting a large set of skin disease related images from commercial search engines. To reinforce the learning performance in the target domain, we initially build a learning model in the target domain, and then seamlessly leverage the training samples in the source domain to enhance this learning model. The distribution gap between these two domains are bridged by a linear combination of Gaussian kernels. Instead of training models with low-level features, we resort to deep models to learn the succinct, invariant, and high-level image representations. Different from previous efforts that focus on a few types of skin diseases with a small and confidential set of images generated from hospitals, this paper targets at thousands of commonly seen skin diseases with publicly accessible Web images. Hence the proposed model is easily repeatable by other researchers and extendable to other disease types. Extensive experiments on a real-world dataset have demonstrated the superiority of our proposed method over the state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. First, how to prevent the synthesised data from over-fitting to training classes? Second, how to guarantee the synthesised data is discriminative for ZSL tasks? Third, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm. (1) We introduce a latent embedding space which aims to reconcile the structural difference between the visual and semantic spaces, meanwhile preserve the local structure. (2) We propose a novel Diffusion Regularisation (DR) that explicitly forces the variances to diffuse over most dimensions of the synthesised data. By an orthogonal rotation (more precisely, an orthogonal transformation), DR can remove the redundant correlated attributes and further alleviate the over-fitting problem. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data for zero-shot learning. Extensive experimental results suggest that our proposed approach significantly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Fast and accurately categorizing the millions of aerial images on Google Maps is a useful technique in pattern recognition. Existing methods cannot handle this task successfully due to two reasons: 1) the aerial images’ topologies are the key feature to distinguish their categories, but they cannot be effectively encoded by a conventional visual codebook and 2) it is challenging to build a realtime image categorization system, as some geo-aware Apps update over 20 aerial images per second. To solve these problems, we propose an efficient aerial image categorization algorithm. It focuses on learning a discriminative topological codebook of aerial images under a multitask learning framework. The pipeline can be summarized as follows. We first construct a region adjacency graph (RAG) that describes the topology of each aerial image. Naturally, aerial image categorization can be formulated as RAG-to-RAG matching. According to graph theory, RAG-to-RAG matching is conducted by enumeratively comparing all their respective graphlets (i.e., small subgraphs). To alleviate the high time consumption, we propose to learn a codebook containing topologies jointly discriminative to multiple categories. The learned topological codebook guides the extraction of the discriminative graphlets. Finally, these graphlets are integrated into an AdaBoost model for predicting aerial image categories. Experimental results show that our approach is competitive to several existing recognition models. Furthermore, over 24 aerial images are processed per second, demonstrating that our approach is ready for real-world applications. [ABSTRACT FROM PUBLISHER]

Saliency detection models aiming to quantitatively predict human eye-attended locations in the visual field have been receiving increasing research interest in recent years. Unlike traditional methods that rely on hand-designed features and contrast inference mechanisms, this paper proposes a novel framework to learn saliency detection models from raw image data using deep networks. The proposed framework mainly consists of two learning stages. At the first learning stage, we develop a stacked denoising autoencoder (SDAE) model to learn robust, representative features from raw image data under an unsupervised manner. The second learning stage aims to jointly learn optimal mechanisms to capture the intrinsic mutual patterns as the feature contrast and to integrate them for final saliency prediction. Given the input of pairs of a center patch and its surrounding patches represented by the features learned at the first stage, a SDAE network is trained under the supervision of eye fixation labels, which achieves both contrast inference and contrast integration simultaneously. Experiments on three publically available eye tracking benchmarks and the comparisons with 16 state-of-the-art approaches demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM PUBLISHER]

In image analysis, the images are often represented by multiple visual features (also known as multiview features), that aim to better interpret them for achieving remarkable performance of the learning. Since the processes of feature extraction on each view are separated, the multiple visual features of images may include overlap, noise, and redundancy. Thus, learning with all the derived views of the data could decrease the effectiveness. To address this, this paper simultaneously conducts a hierarchical feature selection and a multiview multilabel (MVML) learning for multiview image classification, via embedding a proposed a new block-row regularizer into the MVML framework. The block-row regularizer concatenating a Frobenius norm ( F -norm) regularizer and an \boldsymbol \ell \textbf {2,1} -norm regularizer is designed to conduct a hierarchical feature selection, in which the F -norm regularizer is used to conduct a high-level feature selection for selecting the informative views (i.e., discarding the uninformative views) and the \boldsymbol \ell \textbf {2,1} -norm regularizer is then used to conduct a low-level feature selection on the informative views. The rationale of the use of a block-row regularizer is to avoid the issue of the over-fitting (via the block-row regularizer), to remove redundant views and to preserve the natural group structures of data (via the F -norm regularizer), and to remove noisy features (the \boldsymbol \ell \textbf {2,1} -norm regularizer), respectively. We further devise a computationally efficient algorithm to optimize the derived objective function and also theoretically prove the convergence of the proposed optimization method. Finally, the results on real image datasets show that the proposed method outperforms two baseline algorithms and three state-of-the-art algorithms in terms of classification performance. [ABSTRACT FROM PUBLISHER]

Fine-grained image categorization is a challenging task aiming at distinguishing objects belonging to the same basic-level category, e.g., leaf or mushroom. It is a useful technique that can be applied for species recognition, face verification, and so on. Most of the existing methods either have difficulties to detect discriminative object components automatically, or suffer from the limited amount of training data in each sub-category. To solve these problems, this paper proposes a new fine-grained image categorization model. The key is a dense graph mining algorithm that hierarchically localizes discriminative object parts in each image. More specifically, to mimic the human hierarchical perception mechanism, a superpixel pyramid is generated for each image. Thereby, graphlets from each layer are constructed to seamlessly capture object components. Intuitively, graphlets representative to each super-/sub-category is densely distributed in their feature space. Thus, a dense graph mining algorithm is developed to discover graphlets representative to each super-/sub-category. Finally, the discovered graphlets from pairwise images are integrated into an image kernel for fine-grained recognition. Theoretically, the learned kernel can generalize several state-of-the-art image kernels. Experiments on nine image sets demonstrate the advantage of our method. Moreover, the discovered graphlets from each sub-category accurately capture those tiny discriminative object components, e.g., bird claws, heads, and bodies. [ABSTRACT FROM PUBLISHER]

Sparse representation-based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates, while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using \ell 1 -norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximized. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection (RP) and weighted least squares (WLS) techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a WLS method to obtain the representation coefficients. To further reduce the computational complexity, structurally RP is used to reduce the dimensionality of the feature space, while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods. [ABSTRACT FROM AUTHOR]

Nowadays, with the continual development of digital capture technologies and social media services, a vast number of media documents are captured and shared online to help attendees record their experience during events. In this paper, we present a method combining semantic inference and multimodal analysis for automatically finding media content to illustrate events using an adaptive probabilistic hypergraph model. In this model, media items are taken as vertices in the weighted hypergraph and the task of enriching media to illustrate events is formulated as a ranking problem. In our method, each hyperedge is constructed using the K-nearest neighbors of a given media document. We also employ a probabilistic representation, which assigns each vertex to a hyperedge in a probabilistic way, to further exploit the correlation among media data. Furthermore, we optimize the hypergraph weights in a regularization framework, which is solved as a second-order cone problem. The approach is initiated by seed media and then used to rank the media documents using a transductive inference process. The results obtained from validating the approach on an event dataset collected from EventMedia demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM PUBLISHER]

Sparse coding methods have achieved great success in visual tracking, and we present a strong classifier and structural local sparse descriptors for robust visual tracking. Since the summary features considering the sparse codes are sensitive to occlusion and other interfering factors, we extract local sparse descriptors from a fraction of all patches by performing a pooling operation. The collection of local sparse descriptors is combined into a boosting-based strong classifier for robust visual tracking using a discriminative appearance model. Furthermore, a structural reconstruction error based weight computation method is proposed to adjust the classification score of each candidate for more precise tracking results. To handle appearance changes during tracking, we present an occlusion-aware template update scheme. Comprehensive experimental comparisons with the state-of-the-art algorithms demonstrated the better performance of the proposed method. [ABSTRACT FROM PUBLISHER]

Hashing methods are effective in generating compact binary signatures for images and videos. This paper addresses an important open issue in the literature, i.e., how to learn compact hash codes by enhancing the complementarity among different hash functions. Most of prior studies solve this problem either by adopting time-consuming sequential learning algorithms or by generating the hash functions which are subject to some deliberately-designed constraints (e.g., enforcing hash functions orthogonal to one another). We analyze the drawbacks of past works and propose a new solution to this problem. Our idea is to decompose the feature space into a subspace shared by all hash functions and its complementary subspace. On one hand, the shared subspace, corresponding to the common structure across different hash functions, conveys most relevant information for the hashing task. Similar to data de-noising, irrelevant information is explicitly suppressed during hash function generation. On the other hand, in case that the complementary subspace also contains useful information for specific hash functions, the final form of our proposed hashing scheme is a compromise between these two kinds of subspaces. To make hash functions not only preserve the local neighborhood structure but also capture the global cluster distribution of the whole data, an objective function incorporating spectral embedding loss, binary quantization loss, and shared subspace contribution is introduced to guide the hash function learning. We propose an efficient alternating optimization method to simultaneously learn both the shared structure and the hash functions. Experimental results on three well-known benchmarks CIFAR-10, NUS-WIDE, and a-TRECVID demonstrate that our approach significantly outperforms state-of-the-art hashing methods. [ABSTRACT FROM PUBLISHER]

Scene recognition has been widely studied to understand visual information from the level of objects and their relationships. Toward scene recognition, many methods have been proposed. They, however, encounter difficulty to improve the accuracy, mainly due to two limitations: 1) lack of analysis of intrinsic relationships across different scales, say, the initial input and its down-sampled versions and 2) existence of redundant features. This paper develops a semi-supervised learning mechanism to reduce the above two limitations. To address the first limitation, we propose a multitask model to integrate scene images of different resolutions. For the second limitation, we build a model of sparse feature selection-based manifold regularization (SFSMR) to select the optimal information and preserve the underlying manifold structure of data. SFSMR coordinates the advantages of sparse feature selection and manifold regulation. Finally, we link the multitask model and SFSMR, and propose the semi-supervised learning method to reduce the two limitations. Experimental results report the improvements of the accuracy in scene recognition. [ABSTRACT FROM PUBLISHER]

The groundwater seepage in the fractured rock mass affects the stability of the surrounding rock of the roadway. To understand the fluid seepage characteristics and the change law of the microscopic pore structure of the fractured rock mass under different loading conditions, the low-field nuclear magnetic resonance technology (LF-NMR) was used to conduct a visual experimental study. The T 2 spectrum distribution curve tested by nuclear magnetic resonance indicated that the pore structure of the fractured sandstone sample had three peaks (namely micropores, mesopores, and macropores) with medium and large pores distributed from 0.63 μm to 100 μm. Quantitative analysis of nuclear magnetic resonance imaging signals during water flooding of fractured sandstones revealed the characteristics of fluid migration and distribution at different times and locations at different flow rates in the core. The height of the fractured core at 23 mm had small water content and low porosity. The water content at the position of 25–40 mm was higher, and the porosity was large. Under the effect of flow velocity, there were obvious differences in the state of fractured core displacement. That is, the greater the flow velocity, the shorter the water flooding time and the more concentrated the fluid sweep area. The dominant channel for seepage was formed quickly. The research results can provide a reference for preventing the erosion of roadway surrounding rock caused by groundwater fluid. • The low-field nuclear magnetic resonance technology (LF-NMR) was used to conduct a visual experimental study. • Quantitative analysis of nuclear magnetic resonance imaging signals during water flooding of fractured sandstones revealed the characteristics of fluid migration and distribution at different times and locations at different flow rates in the core. • The greater the flow velocity, the shorter the water flooding time, and the more concentrated the fluid sweep area. The dominant channel for seepage was formed quickly. [ABSTRACT FROM AUTHOR]

We present a framework for image classification that extends beyond the window sampling of fixed spatial pyramids and is supported by a new learning algorithm. Based on the observation that fixed spatial pyramids sample a rather limited subset of the possible image windows, we propose a method that accounts for a comprehensive set of windows densely sampled over location, size, and aspect ratio. A concise high-level image feature is derived to effectively deal with this large set of windows, and this higher level of abstraction offers both efficient handling of the dense samples and reduced sensitivity to misalignment. In addition to dense window sampling, we introduce generalized adaptive \ell p -norm multiple kernel learning (GA-MKL) to learn a robust classifier based on multiple base kernels constructed from the new image features and multiple sets of prelearned classifiers from other classes. With GA-MKL, multiple levels of image features are effectively fused, and information is shared among different classifiers. Extensive evaluation on benchmark datasets for object recognition (Caltech256 and Caltech101) and scene recognition (15Scenes) demonstrate that the proposed method outperforms the state-of-the-art under a broad range of settings. [ABSTRACT FROM PUBLISHER]

To fill the semantic gap between the predictive power of computational saliency models and human behavior, this paper proposes to predict where people look at using spatial-aware object-level cues. While object-level saliency has been recently suggested by psychophysics experiments and shown effective with a few computational models, the spatial relationship between the objects has not yet been explored in this context. We in this work for the first time explicitly model such spatial relationship, as well as leveraging semantic information of an image to enhance object-level saliency modeling. The core computational module is a graphlet-based (i.e., graphlets are moderate-sized connected subgraphs) deep architecture, which hierarchically learns a saliency map from raw image pixels to object-level graphlets (oGLs) and further to spatial-level graphlets (sGLs). Eye tracking data are also used to leverage human experience in saliency prediction. Experimental results demonstrate that the proposed oGLs and sGLs well capture object-level and spatial-level cues relating to saliency, and the resulting saliency model performs competitively compared with the state-of-the-art. [ABSTRACT FROM PUBLISHER]

Visual reranking has been widely deployed to refine the traditional text-based image retrieval. Its current trend is to combine the retrieval results from various visual features to boost reranking precision and scalability. And its prominent challenge is how to effectively exploit the complementary property of different features. Another significant issue raises from the noisy instances, from manual or automatic labels, which makes the exploration of such complementary property difficult. This paper proposes a novel image reranking by introducing a new Co-Regularized Multi- Graph Learning (Co-RMGL) framework, in which intra-graph and inter-graph constraints are integrated to simultaneously encode the similarity in a single graph and the consistency across multiple graphs. To deal with the noisy instances, weakly supervised learning via co-occurred visual attribute is utilized to select a set of graph anchors to guide multiple graphs alignment and fusion, and to filter out those pseudo labeling instances to highlight the strength of individual features. After that, a learned edge weighting matrix from a fused graph is used to reorder the retrieval results. We evaluate our approach on four popular image retrieval datasets and demonstrate a significant improvement over state-of-the-art methods. [ABSTRACT FROM PUBLISHER]

Image seam carving algorithm should preserve important and salient objects as much as possible when changing the image size, while not removing the secondary objects in the scene. However, it is still difficult to determine the important and salient objects that avoid the distortion of these objects after resizing the input image. In this paper, we develop a novel depth-aware single image seam carving approach by taking advantage of the modern depth cameras such as the Kinect sensor, which captures the RGB color image and its corresponding depth map simultaneously. By considering both the depth information and the just noticeable difference (JND) model, we develop an efficient JND-based significant computation approach using the multiscale graph cut based energy optimization. Our method achieves the better seam carving performance by cutting the near objects less seams while removing distant objects more seams. To the best of our knowledge, our algorithm is the first work to use the true depth map captured by Kinect depth camera for single image seam carving. The experimental results demonstrate that the proposed approach produces better seam carving results than previous content-aware seam carving methods. [ABSTRACT FROM PUBLISHER]