Search

Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness., Comment: Journal version of arXiv:2102.02051. Accepted by IEEE TPAMI

Temporal sentence grounding in videos (TSGV), \aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial style: from feature extraction from raw video and language query, to answer prediction of the target moment. Then we review the techniques for multimodal understanding and interaction, which is the key focus of TSGV for effective alignment between the two modalities. We construct a taxonomy of TSGV techniques and elaborate the methods in different categories with their strengths and weaknesses. Lastly, we discuss issues with the current TSGV research and share our insights about promising research directions., Comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Image annotation aims to jointly predict multiple tags for an image. Although significant progress has been achieved, existing approaches usually overlook aligning specific labels and their corresponding regions due to the weak supervised information (i.e., ``bag of labels'' for regions), thus failing to explicitly exploit the discrimination from different classes. In this article, we propose the deep label-specific feature (Deep-LIFT) learning model to build the explicit and exact correspondence between the label and the local visual region, which improves the effectiveness of feature learning and enhances the interpretability of the model itself. Deep-LIFT extracts features for each label by aligning each label and its region. Specifically, Deep-LIFTs are achieved through learning multiple correlation maps between image convolutional features and label embeddings. Moreover, we construct two variant graph convolutional networks (GCNs) to further capture the interdependency among labels. Empirical studies on benchmark datasets validate that the proposed model achieves superior performance on multilabel classification over other existing state-of-the-art methods.

Achieving high performance in many multi-server systems requires finding a good assignment of worker threads to servers and also effectively allocating each server's resources to its assigned threads. The assignment and allocation components of this problem have been studied extensively but largely separately in the literature. In this paper, we introduce the assign and allocate (AA) problem, which seeks to simultaneously find an assignment and allocation that maximizes the total utility of the threads. Assigning and allocating the threads together can result in substantially better overall utility than performing the steps separately, as is traditionally done. We model each thread by a utility function giving its performance as a function of its assigned resources. We first prove that the AA problem is NP-hard. We then present a $2 (\sqrt{2}-1) > 0.828$ factor approximation algorithm for concave utility functions, which runs in $O(mn^2 + n (\log mC)^2)$ time for $n$ threads and $m$ servers with $C$ amount of resources each. We also give a faster algorithm with the same approximation ratio and $O(n (\log mC)^2)$ time complexity. We then extend the problem to two more general settings. First, we consider threads with nonconcave utility functions, and give a 1/2 factor approximation algorithm. Next, we give an algorithm for threads using multiple types of resources, and show the algorithm achieves good empirical performance. We conduct extensive experiments to test the performance of our algorithms on threads with both synthetic and realistic utility functions, and find that they achieve over 92\% of the optimal utility on average. We also compare our algorithms with a number of practical heuristics, and find that our algorithms achieve up to 9 times higher total utility., 17 pages

Face verification can be regarded as a two-class fine-grained visual-recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric-learning technology is often applied to address this need while achieving a good tradeoff between underfitting, and overfitting plays a vital role in metric learning. Hence, we propose a novel ensemble cascade metric-learning (ECML) mechanism. In particular, hierarchical metric learning is executed in a cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split into nonoverlapping groups. Then, metric learning is executed among the feature groups in the ensemble manner to resist overfitting. Considering the feature distribution characteristics of faces, a robust Mahalanobis metric-learning method (RMML) with a closed-form solution is additionally proposed. It can avoid the computation failure issue on an inverse matrix faced by some well-known metric-learning approaches (e.g., KISSME). Embedding RMML into the proposed ECML mechanism, our metric-learning paradigm (EC-RMML) can run in the one-pass learning manner. The experimental results demonstrate that EC-RMML is superior to state-of-the-art metric-learning methods for face verification. The proposed ECML mechanism is also applicable to other metric-learning approaches.

The core component of most anomaly detectors is a self-supervised model, tasked with modeling patterns included in training samples and detecting unexpected patterns as the anomalies in testing samples. To cope with normal patterns, this model is typically trained with reconstruction constraints. However, the model has the risk of overfitting to training samples and being sensitive to hard normal patterns in the inference phase, which results in irregular responses at normal frames. To address this problem, we formulate anomaly detection as a mutual supervision problem. Due to collaborative training, the complementary information of mutual learning can alleviate the aforementioned problem. Based on this motivation, a SIamese generative network (SIGnet), including two subnetworks with the same architecture, is proposed to simultaneously model the patterns of the forward and backward frames. During training, in addition to traditional constraints on improving the reconstruction performance, a bidirectional consistency loss based on the forward and backward views is designed as the regularization term to improve the generalization ability of the model. Moreover, we introduce a consistency-based evaluation criterion to achieve stable scores at the normal frames, which will benefit detecting anomalies with fluctuant scores in the inference phase. The results on several challenging benchmark data sets demonstrate the effectiveness of our proposed method.

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are designed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are trivial for powerful servers, but critical for edge devices. To mitigate these issues, We propose Resource Constrained Training (RCT). RCT only keeps a quantised model throughout the training, so that the memory requirements for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically in order to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image application and natural language processing. Experiments show that RCT saves more than 86\% energy for General Matrix Multiply (GEMM) and saves more than 46\% memory for model parameters, with limited accuracy loss. Comparing with QAT-based method, RCT saves about half of energy on moving model parameters., Comment: 14 pages

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual features for target localization. Such a formulation provides insufficient ability to model query at the word level, and therefore is prone to neglect words that may not be the most important ones for a sentence but are critical for the referred object. In this article, we propose Word2Pix: a one-stage visual grounding network based on the encoder-decoder transformer architecture that enables learning for textual to visual feature correspondence via word to pixel attention. Each word from the query sentence is given an equal opportunity when attending to visual pixels through multiple stacks of transformer decoder layers. In this way, the decoder can learn to model the language query and fuse language with the visual features for target prediction simultaneously. We conduct the experiments on RefCOCO, RefCOCO + , and RefCOCOg datasets, and the proposed Word2Pix outperforms the existing one-stage methods by a notable margin. The results obtained also show that Word2Pix surpasses the two-stage visual grounding models, while at the same time keeping the merits of the one-stage paradigm, namely, end-to-end training and fast inference speed. Code is available at https://github.com/azurerain7/Word2Pix.

Deep neural networks have achieved great success in both computer vision and natural language processing tasks. How to improve the gradient flows is crucial in training very deep neural networks. To address this challenge, a gradient enhancement approach is proposed through constructing the short circuit neural connections. The proposed short circuit is a unidirectional neural connection that back propagates the sensitivities rather than gradients in neural networks from the deep layers to the shallow layers. Moreover, the short circuit is further formulated as a gradient truncation operation in its connecting layers, which can be plugged into the backbone models without introducing extra training parameters. Extensive experiments demonstrate that the deep neural networks, with the help of short circuit connection, gain a large margin of improvement over the baselines on both computer vision and natural language processing tasks. The work provides the promising solution to the low‐resource scenarios, such as, intelligence transport systems of computer vision, question answering of natural language processing.

Is recurrent network really necessary for learning a good visual representation for video based person re-identification (VPRe-id)? In this paper, we first show that the common practice of employing recurrent neural networks (RNNs) to aggregate temporal spatial features may not be optimal. Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective to learn temporal dependencies than what we expected and implicitly yields an orderless representation. Based on this observation, we then present a simple yet surprisingly powerful approach for VPRe-id, where we treat VPRe-id as an efficient orderless ensemble of image based person re-identification problem. More specifically, we divide videos into individual images and re-identify person with ensemble of image based rankers. Under the i.i.d. assumption, we provide an error bound that sheds light upon how could we improve VPRe-id. Our work also presents a promising way to bridge the gap between video and image based person re-identification. Comprehensive experimental evaluations demonstrate that the proposed solution achieves state-of-the-art performances on multiple widely used datasets (iLIDS-VID, PRID 2011, and MARS)., Comment: Under Minor Revision in IEEE TPAMI

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and an image collection (untrained). An unsupervised model will avoid the intensive labor of collecting hazy-clean image pairs, and an untrained model is a “real” single image dehazing approach which could remove haze based on the observed hazy image only and no extra images are used. Motivated by the layer disentanglement, we propose a novel method, called you only look yourself (YOLY) which could be one of the first unsupervised and untrained neural networks for image dehazing. In brief, YOLY employs three joint subnetworks to separate the observed hazy image into several latent layers, i.e., scene radiance layer, transmission map layer, and atmospheric light layer. After that, three layers are further composed to the hazy image in a self-supervised manner. Thanks to the unsupervised and untrained characteristics of YOLY, our method bypasses the conventional training paradigm of deep models on hazy-clean pairs or a large scale dataset, thus avoids the labor-intensive data collection and the domain shift issue. Besides, our method also provides an effective learning-based haze transfer solution thanks to its layer disentanglement mechanism. Extensive experiments show the promising performance of our method in image dehazing compared with 14 methods on six databases. The code could be accessed at www.pengxi.me .

Effective texture categorization plays an important role in effective visual recognition. Despite noticeable progress in this area, blurred-texture recognition remains a challenge. As a key reason for this, existing well-established visual descriptors (e.g., local binary patterns and deep convolutional feature) generally cannot ensure an insensitivity to blur, exhibiting a considerable decrease in performance under clear to blurring conditions. To alleviate this, we propose a discriminative blur-insensitive textural descriptor, referred to as local phase quantization plus plus (LPQ++). The main idea is to establish spatial-channel interactions between the normalized blur-insensitive feature maps yielded by a short-term Fourier transform (STFT) to enhance the descriptive power while maintaining the insensitivity to blur. In particular, spatial interactions executed within the specific STFT feature map capture the spatial correlations between neighboring points. Meanwhile, the column-wise channel interactions among the STFT feature maps help differentiate the edge and flat areas in the images; this is crucial for effective texture characterization under blurring conditions. To enable blurred texture description under dense sampling conditions, LPQ++ is extracted by calculating the spatial-channel gradient orientation histogram and embedding it into the Fisher vector. Experiments conducted on three difficult texture datasets demonstrate the effectiveness of LPQ++ for blurred-texture categorization. Our code is open-source and available at https://github.com/hustzhzhu/LPQplusplus.

We propose a new architecture for addressing sequence labeling, termed Dual Adversarial Transfer Network (DATNet). Specifically, the proposed DATNet includes two variants, i.e., DATNet-F and DATNet-P, which are proposed to explore effective feature fusion between high and low resource. To address the noisy and imbalanced training data, we propose a novel Generalized Resource-Adversarial Discriminator (GRAD) and adopt adversarial training to boost model generalization. We investigate the effects of different components of DATNet across different domains and languages, and show that significant improvement can be obtained especially for low-resource data. Without augmenting any additional hand-crafted features, we achieve state-of-the-art performances on CoNLL, Twitter, PTB-WSJ, OntoNotes and Universal Dependencies with three popular sequence labeling tasks, i.e., Named entity recognition (NER), Part-of-Speech (POS) Tagging and Chunking.

Transformer model architectures have recently received great interest in natural language, machine translation, and computer vision, where attention mechanisms are their building blocks. However, the attention mechanism is expensive because of its intensive matrix computations and complicated data flow. The existing hardware architecture has some disadvantages for the computing structure of attention, such as inflexibility and low efficiency. Most of the existing papers accelerate attention by reducing the amount of computation through various pruning algorithms, which will affect the results in a certain extent with different sparsity. This paper proposes the hardware accelerator for the multi-head attention (MHA) on field-programmable gate arrays (FPGAs) with reconfigurable architecture, efficient systolic array, and hardware-friendly radix-2 softmax. We propose a novel method called Four inputs Processing Element(FPE) to double the computation rate of the data-aware systolic array (SA) and make it efficient and load balance. Especially, the computation framework is well designed to ensure the utilization of SA efficiently. Our design is evaluated on a Xilinx Alveo U250 card, and the proposed architecture achieves 51.3×, 17.3× improvement in latency, and 54.4×, 17.9× energy savings compared to CPU and GPU.

Multi-view representation learning (MvRL) aims to learn a consensus representation from diverse sources or domains to facilitate downstream tasks such as clustering, retrieval, and classification. Due to the limited representative capacity of the adopted shallow models, most existing MvRL methods may yield unsatisfactory results, especially when the labels of data are unavailable. To enjoy the representative capacity of deep learning, this paper proposes a novel multi-view unsupervised representation learning method, termed as Multi-view Laplacian Network (MvLNet), which could be the first deep version of the multi-view spectral representation learning method. Note that, such an attempt is nontrivial because simply combining Laplacian embedding (i.e., spectral representation) with neural networks will lead to trivial solutions. To solve this problem, MvLNet enforces an orthogonal constraint and reformulates it as a layer with the help of Cholesky decomposition. The orthogonal layer is stacked on the embedding network so that a common space could be learned for consensus representation. Compared with numerous recent-proposed approaches, extensive experiments on seven challenging datasets demonstrate the effectiveness of our method in three multi-view tasks including clustering, recognition, and retrieval. The source code could be found at www.pengxi.me .

In this article, we propose a deep extension of sparse subspace clustering, termed deep subspace clustering with L1-norm (DSC-L1). Regularized by the unit sphere distribution assumption for the learned deep features, DSC-L1 can infer a new data affinity matrix by simultaneously satisfying the sparsity principle of SSC and the nonlinearity given by neural networks. One of the appealing advantages brought by DSC-L1 is that when original real-world data do not meet the class-specific linear subspace distribution assumption, DSC-L1 can employ neural networks to make the assumption valid with its nonlinear transformations. Moreover, we prove that our neural network could sufficiently approximate the minimizer under mild conditions. To the best of our knowledge, this could be one of the first deep-learning-based subspace clustering methods. Extensive experiments are conducted on four real-world data sets to show that the proposed method is significantly superior to 17 existing methods for subspace clustering on handcrafted features and raw data.

Most popular clustering methods map raw image data into a projection space in which the clustering assignment is obtained with the vanilla k-means approach. In this article, we discovered a novel prior, namely, there exists a common invariance when assigning an image sample to clusters using different metrics. In short, different distance metrics will lead to similar soft clustering assignments on the manifold. Based on such a novel prior, we propose a novel clustering method by minimizing the discrepancy between pairwise sample assignments for each data point. To the best of our knowledge, this could be the first work to reveal the sample-assignment invariance prior based on the idea of treating labels as ideal representations. Furthermore, the proposed method is one of the first end-to-end clustering approaches, which jointly learns clustering assignment and representation. Extensive experimental results show that the proposed method is remarkably superior to 16 state-of-the-art clustering methods on five image data sets in terms of four evaluation metrics.

The thirteen papers in this special section focus on social media data analytics with deep intelligence. Big cross-model social media data analytics with deep intelligence aims to handle data sampling from multimodal deep spaces, so as to well characterize the big data. The addressed topic span from the range of human action recognition to affective computing, disaster detection, classification, retrieval, clustering, vehicle reidentification, and data security.

The automatic identification system (AIS) plays a vital role in maritime traffic surveillance. AIS is designed for remotely tracking vessels but nowadays also becomes a useful data source to enable vessels’ trajectory prediction so as to facilitate early alert of potential collision risks. Recent studies focus on improving prediction accuracy through the machine learning and knowledge-based technologies but the computational cost also greatly increases due to the model complexity of these methodologies. It becomes a practical challenge to realize near real-time (NRT) trajectory prediction of a large volume of ships. For risk alert application, forecasting timeliness is one of the key design considerations. In this paper, we propose a concurrent processing cluster solution to empower advanced trajectory forecasting for hundreds of vessels in NRT. The proposed solution relies on the properly determined frameworks by customizing the desired features for an integrated solution. Meanwhile, a novel task-based load balancing strategy with newly defined metrics are proposed, which aims to reduce the makespan of jobs and outperforms the existing load balancing algorithms. A practicable cluster system has been successfully implemented, serving as a step toward unlocking the power of advanced maritime traffic forecasting technologies and enabling the benefit from the latest progress on the methodological innovation.

A common way of solving a multi-class classification problem is to decompose it into a collection of simpler two-class problems. One major disadvantage is that with such a binary decomposition scheme it may be difficult to represent subtle between-class differences in many-class classification problems due to limited choices of binary-value partitions. To overcome this challenge, we propose a new decomposition method called N-ary decomposition that decomposes the original multi-class problem into a set of simpler multi-class subproblems. We theoretically show that the proposed N-ary decomposition could be unified into the framework of error correcting output codes and give the generalization error bound of an N-ary decomposition for multi-class classification. Extensive experimental results demonstrate the state-of-the-art performance of our approach.

Recent works that utilized deep models have achieved superior results in various image restoration (IR) applications. Such approach is typically supervised, which requires a corpus of training images with distributions similar to the images to be recovered. On the other hand, the shallow methods, which are usually unsupervised remain promising performance in many inverse problems, e.g. , image deblurring and image compressive sensing (CS), as they can effectively leverage nonlocal self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various artifacts due to naive patch aggregation in addition to the slow speed. Using either approach alone usually limits performance and generalizability in IR tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely, internal and external , shallow and deep , and non-local and local priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for IR. Following this, a simple yet effective algorithm is developed to solve the proposed H-PnP based IR problems. Extensive experimental results on several representative IR tasks, including image deblurring, image CS and image deblocking, demonstrate that the proposed H-PnP algorithm achieves favorable performance compared to many popular or state-of-the-art IR methods in terms of both objective and visual perception.

Dramatic imaging viewpoint variation is the critical challenge toward action recognition for depth video. To address this, one feasible way is to enhance view-tolerance of visual feature, while still maintaining strong discriminative capacity. Multi-view dynamic image (MVDI) is the most recently proposed 3-D action representation manner that is able to compactly encode human motion information and 3-D visual clue well. However, it is still view-sensitive. To leverage its performance, a discriminative MVDI fusion method is proposed by us via multi-instance learning (MIL). Specifically, the dynamic images (DIs) from different observation viewpoints are regarded as the instances for 3-D action characterization. After being encoded using Fisher vector (FV), they are then aggregated by sum-pooling to yield the representative 3-D action signature. Our insight is that viewpoint aggregation helps to enhance view-tolerance. And, FV can map the raw DI feature to the higher dimensional feature space to promote the discriminative power. Meanwhile, a discriminative viewpoint instance discovery method is also proposed to discard the viewpoint instances unfavorable for action characterization. The wide-range experiments on five data sets demonstrate that our proposition can significantly enhance the performance of cross-view 3-D action recognition. And, it is also applicable to cross-view 3-D object recognition. The source code is available at https://github.com/3huo/ActionView.

Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to their event-driven computation mechanism and the replacement of energy-consuming weight multiplication with addition. However, to achieve high accuracy, it usually requires long spike trains to ensure accuracy, usually more than 1000 time steps. This offsets the computation efficiency brought by SNNs because a longer spike train means a larger number of operations and larger latency. In this article, we propose a radix-encoded SNN, which has ultrashort spike trains. Specifically, it is able to use less than six time steps to achieve even higher accuracy than its traditional counterpart. We also develop a method to fit our radix encoding technique into the ANN-to-SNN conversion approach so that we can train radix-encoded SNNs more efficiently on mature platforms and hardware. Experiments show that our radix encoding can achieve 25 × improvement in latency and 1.7% improvement in accuracy compared to the state-of-the-art method using the VGG-16 network on the CIFAR-10 dataset.

Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To address the challenge, we propose a novel framework termed Cross Partial Multi-View Networks (CPM-Nets), which aims to fully and flflexibly take advantage of multiple partial views. We fifirst provide a formal defifinition of completeness and versatility for multi-view representation and then theoretically prove the versatility of the learned latent representations. For completeness, the task of learning latent multi-view representation is specififically translated to a degradation process by mimicking data transmission, such that the optimal tradeoff between consistency and complementarity across different views can be implicitly achieved. Equipped with adversarial strategy, our model stably imputes missing views, encoding information from all views for each sample to be encoded into latent representation to further enhance the completeness. Furthermore, a nonparametric classifification loss is introduced to produce structured representations and prevent overfifitting, which endows the algorithm with promising generalization under view-missing cases. Extensive experimental results validate the effectiveness of our algorithm over existing state of the arts for classifification, representation learning and data imputation.

Cross-modal retrieval (CMR) enables flexible retrieval experience across different modalities (e.g., texts versus images), which maximally benefits us from the abundance of multimedia data. Existing deep CMR approaches commonly require a large amount of labeled data for training to achieve high performance. However, it is time-consuming and expensive to annotate the multimedia data manually. Thus, how to transfer valuable knowledge from existing annotated data to new data, especially from the known categories to new categories, becomes attractive for real-world applications. To achieve this end, we propose a deep multimodal transfer learning (DMTL) approach to transfer the knowledge from the previously labeled categories (source domain) to improve the retrieval performance on the unlabeled new categories (target domain). Specifically, we employ a joint learning paradigm to transfer knowledge by assigning a pseudolabel to each target sample. During training, the pseudolabel is iteratively updated and passed through our model in a self-supervised manner. At the same time, to reduce the domain discrepancy of different modalities, we construct multiple modality-specific neural networks to learn a shared semantic space for different modalities by enforcing the compactness of homoinstance samples and the scatters of heteroinstance samples. Our method is remarkably different from most of the existing transfer learning approaches. To be specific, previous works usually assume that the source domain and the target domain have the same label set. In contrast, our method considers a more challenging multimodal learning situation where the label sets of the two domains are different or even disjoint. Experimental studies on four widely used benchmarks validate the effectiveness of the proposed method in multimodal transfer learning and demonstrate its superior performance in CMR compared with 11 state-of-the-art methods.

In this article, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zero-shot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several “simpler” layers, i.e. , a hazy-free image layer, transmission map layer, and atmospheric light layer. The major advantages of the proposed ZID are two-fold. First, it is an unsupervised method that does not use any clean images including hazy-clean pairs as the ground-truth. Second, ZID is a “zero-shot” method, which just uses the observed single hazy image to perform learning and inference. In other words, it does not follow the conventional paradigm of training deep model on a large scale dataset. These two advantages enable our method to avoid the labor-intensive data collection and the domain shift issue of using the synthetic hazy images to address the real-world images. Extensive comparisons show the promising performance of our method compared with 15 approaches in the qualitative and quantitive evaluations. The source code could be found at http://www.pengxi.me .

Edge devices demand low energy consumption, cost, and small form factor. To efficiently deploy convolutional neural network (CNN) models on the edge device, energy-aware model compression becomes extremely important. However, existing work did not study this problem well because of the lack of considering the diversity of dataflow types in hardware architectures. In this article, we propose EDCompress (EDC), an energy-aware model compression method for various dataflows. It can effectively reduce the energy consumption of various edge devices, with different dataflow types. Considering the very nature of model compression procedures, we recast the optimization process to a multistep problem and solve it by reinforcement learning algorithms. We also propose a multidimensional multistep (MDMS) optimization method, which shows higher compressing capability than the traditional multistep method. Experiments show that EDC could improve 20x, 17x, and 26x energy efficiency in VGG-16, MobileNet, and LeNet-5 networks, respectively, with negligible loss of accuracy. EDC could also indicate the optimal dataflow type for specific neural networks in terms of energy consumption, which can guide the deployment of CNN on hardware.

One major assumption used in most existing hashing approaches is that the domain of interest (i.e., the target domain) could provide sufficient training data, either labeled or unlabeled. However, this assumption may be violated in practice. To address this so-called data sparsity issue in hashing, a new framework termed transfer hashing with privileged information (THPI) is proposed, which marriages hashing and transfer learning (TL). To show the efficacy of THPI, we propose three variants of the well-known iterative quantization (ITQ) [11] as a showcase. The proposed methods, ITQ+, LapITQ+, and deep transfer hashing (DTH), solve the aforementioned data sparsity issue from different aspects. Specifically, ITQ+ is a shallow model, which makes ITQ achieve hashing in a TL manner. ITQ+ learns a new slack function from the source domain to approximate the quantization error on the target domain given by ITQ. To further improve the performance of ITQ+, LapITQ+ is proposed by embedding the geometric relationship of the source domain into the target domain. Moreover, DTH is proposed to show the generality of our framework by utilizing the powerful representative capacity of deep learning. To the best of our knowledge, this could be one of the first DTH works. Extensive experiments on several popular data sets demonstrate the effectiveness of our shallow and DTH approaches comparing with several state-of-the-art hashing approaches.

Existing subspace clustering methods typically employ shallow models to estimate underlying subspaces of unlabeled data points and cluster them into corresponding groups. However, due to the limited representative capacity of the employed shallow models, those methods may fail in handling realistic data without the linear subspace structure. To address this issue, we propose a novel subspace clustering approach by introducing a new deep model-Structured AutoEncoder (StructAE). The StructAE learns a set of explicit transformations to progressively map input data points into nonlinear latent spaces while preserving the local and global subspace structure. In particular, to preserve local structure, the StructAE learns representations for each data point by minimizing reconstruction error w.r.t. itself. To preserve global structure, the StructAE incorporates a prior structured information by encouraging the learned representation to preserve specified reconstruction patterns over the entire data set. To the best of our knowledge, StructAE is one of first deep subspace clustering approaches. Extensive experiments show that the proposed StructAE significantly outperforms 15 state-of-the-art subspace clustering approaches in terms of five evaluation metrics.

We propose an automatic crowd control framework based on multi-objective optimisation of strategy space using genetic programming. In particular, based on the sensed local crowd densities at different segments, our framework is capable of generating control strategies that guide the individuals on when and where to slow down for optimal overall crowd flow in realtime, quantitatively measured by multiple objectives such as shorter travel time and less congestion along the path. The resulting Pareto-front allows selection of resilient and efficient crowd control strategies in different situations. We first chose a benchmark scenario as used in [1] to test the proposed method. Results show that our method is capable of finding control strategies that are not only quantitatively measured better, but also well aligned with domain experts’ recommendations on effective crowd control such as “slower is faster” and “asymmetric control”. We further applied the proposed framework in actual event planning with approximately 400 participants navigating through a multi-story building. In comparison with the baseline crowd models that do no employ control strategies or just use some hard-coded rules, the proposed framework achieves a shorter travel time and a significantly lower (20%) congestion along critical segments of the path. Accepted version

Single-image dehazing has been an important topic given the commonly occurred image degradation caused by adverse atmosphere aerosols. The key to haze removal relies on an accurate estimation of global air-light and the transmission map. Most existing methods estimate these two parameters using separate pipelines which reduces the efficiency and accumulates errors, thus leading to a suboptimal approximation, hurting the model interpretability, and degrading the performance. To address these issues, this article introduces a novel generative adversarial network (GAN) for single-image dehazing. The network consists of a novel compositional generator and a novel deeply supervised discriminator. The compositional generator is a densely connected network, which combines fine-scale and coarse-scale information. Benefiting from the new generator, our method can directly learn the physical parameters from data and recover clean images from hazy ones in an end-to-end manner. The proposed discriminator is deeply supervised, which enforces that the output of the generator to look similar to the clean images from low-level details to high-level structures. To the best of our knowledge, this is the first end-to-end generative adversarial model for image dehazing, which simultaneously outputs clean images, transmission maps, and air-lights. Extensive experiments show that our method remarkably outperforms the state-of-the-art methods. Furthermore, to facilitate future research, we create the HazeCOCO dataset which is currently the largest dataset for single-image dehazing.

Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter may suffer from much larger computational complexity. To cope with those issues, we propose to regress via an efficient “divide and conquer” manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both “accurate” and “diversified.” Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines as well as the versatility of the proposed method. The source code and trained models are available on our project page: https://mmcheng.net/dncl/ .

In this paper, we mainly investigate two issues for sequence labeling, namely, label imbalance and noisy data that are commonly seen in the scenario of named entity recognition (NER) and are largely ignored in the existing works. To address these two issues, a new method termed robust sequence labeling (RoSeq) is proposed. Specifically, to handle the label imbalance issue, we first incorporate label statistics in a novel conditional random field (CRF) loss. In addition, we design an additional loss to reduce the weights of overwhelming easy tokens for augmenting the CRF loss. To address the noisy training data, we adopt an adversarial training strategy to improve model generalization. In experiments, the proposed RoSeq achieves the state-of-the-art performances on CoNLL and English Twitter NER—88.07% on CoNLL-2002 Dutch, 87.33% on CoNLL-2002 Spanish, 52.94% on WNUT-2016 Twitter, and 43.03% on WNUT-2017 Twitter without using the additional data.

© 1992-2012 IEEE. Automatically understanding and discriminating different users' liking for an image is a challenging problem. This is because the relationship between image features (even semantic ones extracted by existing tools, viz., faces, objects, and so on) and users' likes is non-linear, influenced by several subtle factors. This paper presents a deep bi-modal knowledge representation of images based on their visual content and associated tags (text). A mapping step between the different levels of visual and textual representations allows for the transfer of semantic knowledge between the two modalities. Feature selection is applied before learning deep representation to identify the important features for a user to like an image. The proposed representation is shown to be effective in discriminating users based on images they like and also in recommending images that a given user likes, outperforming the state-of-the-art feature representations by ∼ 15%-20%. Beyond this test-set performance, an attempt is made to qualitatively understand the representations learned by the deep architecture used to model user likes.

Imbalanced data distribution in crowd counting datasets leads to severe under-estimation and over-estimation problems, which has been less investigated in existing works. In this paper, we tackle this challenging problem by proposing a simple but effective locality-based learning paradigm to produce generalizable features by alleviating sample bias. Our proposed method is locality-aware in two aspects. First, we introduce a locality-aware data partition (LADP) approach to group the training data into different bins via locality-sensitive hashing. As a result, a more balanced data batch is then constructed by LADP. To further reduce the training bias and enhance the collaboration with LADP, a new data augmentation method called locality-aware data augmentation (LADA) is proposed where the image patches are adaptively augmented based on the loss. The proposed method is independent of the backbone network architectures, and thus could be smoothly integrated with most existing deep crowd counting approaches in an end-to-end paradigm to boost their performance. We also demonstrate the versatility of the proposed method by applying it for adversarial defense. Extensive experiments verify the superiority of the proposed method over the state of the arts.

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve the NLVL problem from the perspective of computer vision by formulating it as ranking, anchor, or regression tasks. These methods suffer from large performance degradation when localizing on long videos. In this work, we address the NLVL from a new perspective, i.e., span-based question answering (QA), by treating the input video as a text passage. We propose a video span localizing network (VSLNet), on top of the standard span-based QA framework (named VSLBase), to address NLVL. VSLNet tackles the differences between NLVL and span-based QA through a simple yet effective query-guided highlighting (QGH) strategy. QGH guides VSLNet to search for the matching video span within a highlighted region. To address the performance degradation on long videos, we further extend VSLNet to VSLNet-L by applying a multi-scale split-and-concatenation strategy. VSLNet-L first splits the untrimmed video into short clip segments; then, it predicts which clip segment contains the target moment and suppresses the importance of other segments. Finally, the clip segments are concatenated, with different confidences, to locate the target moment accurately. Extensive experiments on three benchmark datasets show that the proposed VSLNet and VSLNet-L outperform the state-of-the-art methods; VSLNet-L addresses the issue of performance degradation on long videos. Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem., 15 pages, 18 figures, and 10 tables. Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). arXiv admin note: substantial text overlap with arXiv:2004.13931

In this paper, we study a new problem in the scenario of sequences labeling. To be exact, we consider that the training data are with annotation of various degrees, namely, fully labeled, unlabeled, and partially labeled sequences. The learning with fully un/labeled sequence refers to the standard setting in traditional un/supervised learning, and the proposed partially labeling specifies the subject that the element does not belong to. The partially labeled data are cheaper to obtain compared with the fully labeled data though it is less informative, especially when the tasks require a lot of domain knowledge. To solve such a practical challenge, we propose a novel deep conditional random field (CRF) model which utilizes an end-to-end learning manner to smoothly handle fully/un/partially labeled sequences within a unified framework. To the best of our knowledge, this could be one of the first works to utilize the partially labeled instance for sequence labeling, and the proposed algorithm unifies the deep learning and CRF in an end-to-end framework. Extensive experiments show that our method achieves state-of-the-art performance in two sequence labeling tasks on some popular data sets.

A panoply of multi-view clustering algorithms has been developed to deal with prevalent multi-view data. Among them, spectral clustering-based methods have drawn much attention and demonstrated promising results recently. Despite progress, there are still two fundamental questions that stay unanswered to date. First, how to fuse different views into one graph. More often than not, the similarities between samples may be manifested differently by different views. Many existing algorithms either simply take the average of multiple views or just learn a common graph. These simple approaches fail to consider the flexible local manifold structures of all views. Hence, the rich heterogeneous information is not fully exploited. Second, how to learn the explicit cluster structure. Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately. Those unreliable graphs might lead to suboptimal clustering results. To fill these gaps, in this paper, we propose a novel multi-view spectral clustering model which performs graph fusion and spectral clustering simultaneously. The fusion graph approximates the original graph of each individual view but maintains an explicit cluster structure. Experiments on four widely used data sets confirm the superiority of the proposed method., Comment: submitted to Knowledge-based Systems

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow for motion characterization, dynamic imaging exhibits superior efficiency and compactness. Inspired by the success of dynamic imaging in RGB video, this study extends it to the depth domain. To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed. In particular, the raw depth video is densely projected with respect to different virtual imaging viewpoints by rotating the virtual camera within the 3D space. Subsequently, dynamic images are extracted from the obtained multi-view depth videos and multi-view dynamic images are thus constructed from these images. Accordingly, more view-tolerant visual cues can be involved. A novel CNN model is then proposed to perform feature learning on multi-view dynamic images. Particularly, the dynamic images from different views share the same convolutional layers but correspond to different fully connected layers. This is aimed at enhancing the tuning effectiveness on shallow convolutional layers by alleviating the gradient vanishing problem. Moreover, as the spatial occurrence variation of the actions may impair the CNN, an action proposal approach is also put forth. In experiments, the proposed approach can achieve state-of-the-art performance on three challenging datasets., Comment: accepted by Information Sciences

© 2010-2012 IEEE. The increased proliferation of data production technologies (e.g., cameras) and consumption avenues (e.g., social media) has led to images and videos being utilized by users to convey innate preferences and tastes. This has opened up the possibility of using multimedia as a source for user-modeling. This work attempts to model personality traits (based on the Five Factor Theory) of users using a collection of images they tag as 'favorite' (or like) on Flickr. First, a set of semantic features are proposed to be used for representing different concepts in images which influence users to like them. The addition of the proposed features led to improvement over state-of-the-art by 12 percent. Second, a novel machine learning approach is developed to model users' personality based on the image features (resulting in upto 15 percent improvement). Third, efficacy of the semantic features and the modeling approach is shown in recommending images based on personality modeling. Using the modeling approach, recommendations are made regarding the factors that might influence users with different personality traits to like an image.