A review on the attention mechanism of deep learning

Deep multi-view learning methods: a review

Evolutionary deep learning: A survey

Discriminative subspace matrix factorization for multiview data clustering

A comprehensive survey on robust image watermarking

Crowd counting has produced considerable concern in recent years. However, crowd counting in highly congested scenes is a challenging problem owing to scale variation. To remedy this issue, we propose a novel deep scale purifier network (DSPNet) that can encode multiscale features and reduce the loss of contextual information for dense crowd counting. Our proposed method has two strong points. First, the DSPNet model consists of a frontend and a backend. The frontend is a conventional deep convolutional neural network, while the unified deep neural network backend adopts a “maximal ratio combining” strategy to learn complementary scale information at different levels. The scale purifier module, which improves scale representations, can effectively fuse multiscale features. Second, DSPNet performs the whole RGB image-based inference to facilitate model learning and decrease contextual information loss. Our customized network is end-to-end and has a fully convolutional architecture. We demonstrate the generalization ability of our approach by cross-scene evaluation. Extensive experiments on three publicly available crowd counting benchmarks (i.e., UCF-QNRF, ShanghaiTech, and UCF_CC_50 datasets) show that our DSPNet delivers superior performance against state-of-the-art methods.

DSPNet: Deep scale purifier network for dense crowd counting

Sharing information between multiple tasks can enhance the accuracy of human action recognition systems. However, using shared information to improve multi-task human action clustering has never been considered before, and cannot be achieved using existing clustering methods. In this work, we present a novel and effective Multi-Task Information Bottleneck (MTIB) clustering method, which is capable of exploring the shared information between multiple action clustering tasks to improve the performance of individual task. Our motivation is that, different action collections always share many similar action patterns, and exploiting the shared information can lead to improved performance. Specifically, MTIB generally formulates this problem as an information loss minimization function. In this function, the shared information can be quantified by the distributional correlation of clusters in different tasks, which is based on a high-level common vocabulary constructed through a novel agglomerative information maximization method. Extensive experiments on two kinds of challenging data sets, including realistic action data sets (HMDB & UCF50, Olympic & YouTube), and cross-view data sets (IXMAS, WVU), show that the proposed approach compares favorably to the state-of-the-art methods.

/pdf/multi-task-clustering-of-human-actions-by-sharing-4sdhve5ebq.pdf

Multi-task Clustering of Human Actions by Sharing Information

Multiview clustering (MVC) has recently been the focus of much attention due to its ability to partition data from multiple views via view correlations. However, most MVC methods only learn either interfeature correlations or intercluster correlations, which may lead to unsatisfactory clustering performance. To address this issue, we propose a novel dual-correlated multivariate information bottleneck (DMIB) method for MVC. DMIB is able to explore both interfeature correlations (the relationship among multiple distinct feature representations from different views) and intercluster correlations (the close agreement among clustering results obtained from individual views). For the former, we integrate both view-shared feature correlations discovered by learning a shared discriminative feature subspace and view-specific feature information to fully explore the interfeature correlation. This allows us to attain multiple reliable local clustering results of different views. Following this, we explore the intercluster correlations by learning the shared mutual information over different local clusterings for an improved global partition. By integrating both correlations, we formulate the problem as a unified information maximization function and further design a two-step method for optimization. Moreover, we theoretically prove the convergence of the proposed algorithm, and discuss the relationships between our method and several existing clustering paradigms. The experimental results on multiple datasets demonstrate the superiority of DMIB compared to several state-of-the-art clustering methods.

Shizhe Hu

Papers

Deep multi-view learning methods: a review

DSPNet: Deep scale purifier network for dense crowd counting

Multi-task Clustering of Human Actions by Sharing Information

DMIB: Dual-Correlated Multivariate Information Bottleneck for Multiview Clustering.

Joint specific and correlated information exploration for multi-view action clustering