Subspace clustering is an effective method that has been successfully applied to many applications. Here we propose a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC). Unlike most existing single-view subspace clustering methods, which directly reconstruct data points using original features, our method explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation. Using the complementarity of multiple views, the latent representation depicts data more comprehensively than each individual view, accordingly making subspace representation more accurate and robust. We proposed two LMSC formulations: linear LMSC (lLMSC), based on linear correlations between latent representation and each view, and generalized LMSC (gLMSC), based on neural networks to handle general relationships. The proposed method can be efficiently optimized under the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) framework. Extensive experiments on diverse datasets demonstrate the effectiveness of the proposed method.

Object detection, including objectness detection (OD), salient object detection (SOD), and category-specific object detection (COD), is one of the most fundamental yet challenging problems in the computer vision community. Over the last several decades, great efforts have been made by researchers to tackle this problem, due to its broad range of applications for other computer vision tasks such as activity or event recognition, content-based image retrieval and scene understanding, etc. While numerous methods have been presented in recent years, a comprehensive review for the proposed high-quality object detection techniques, especially for those based on advanced deep-learning techniques, is still lacking. To this end, this article delves into the recent progress in this research field, including 1) definitions, motivations, and tasks of each subdirection; 2) modern techniques and essential research trends; 3) benchmark data sets and evaluation metrics; and 4) comparisons and analysis of the experimental results. More importantly, we will reveal the underlying relationship among OD, SOD, and COD and discuss in detail some open questions as well as point out several unsolved challenges and promising future works.

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. Moreover, we introduce a novel multi-modal feature fusion strategy within the LSTM unit in this paper. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method.

Sparse-view computed tomography (CT) holds great promise for speeding up data acquisition and reducing radiation dose in CT scans. Recent advances in reconstruction algorithms for sparse-view CT, such as iterative reconstruction algorithms, obtained high-quality image while requiring advanced computing power. Lately, deep learning (DL) has been widely used in various applications and has obtained many remarkable outcomes. In this paper, we propose a new method for sparse-view CT reconstruction based on the DL approach. The method can be divided into two steps. First, filter backprojection (FBP) was used to reconstruct the CT image from sparsely sampled sinogram. Then, the FBP results were fed to a DL neural network, which is a DenseNet and deconvolution-based network (DD-Net). The DD-Net combines the advantages of DenseNet and deconvolution and applies shortcut connections to concatenate DenseNet and deconvolution to accelerate the training speed of the network; all of those operations can greatly increase the depth of network while enhancing the expression ability of the network. After the training, the proposed DD-Net achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation. Compared with the other state-of-the-art reconstruction methods, the DD-Net method can increase the structure similarity by up to 18% and reduce the root mean square error by up to 42%. These results indicate that DD-Net has great potential for sparse-view CT image reconstruction.

The performance of object detection has recently been significantly improved due to the powerful features learnt through convolutional neural networks (CNNs). Despite the remarkable success, there are still several major challenges in object detection, including object rotation, within-class diversity, and between-class similarity, which generally degenerate object detection performance. To address these issues, we build up the existing state-of-the-art object detection systems and propose a simple but effective method to train rotation-invariant and Fisher discriminative CNN models to further boost object detection performance. This is achieved by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features. Specifically, the first regularizer enforces the CNN feature representations of the training samples before and after rotation to be mapped closely to each other in order to achieve rotation-invariance. The second regularizer constrains the CNN features to have small within-class scatter but large between-class separation. We implement our proposed method under four popular object detection frameworks, including region-CNN (R-CNN), Fast R- CNN, Faster R- CNN, and R- FCN. In the experiments, we comprehensively evaluate the proposed method on the PASCAL VOC 2007 and 2012 data sets and a publicly available aerial image data set. Our proposed methods outperform the existing baseline methods and achieve the state-of-the-art results.

Traditional video compression approaches build upon the hybrid coding framework with motion-compensated prediction and residual transform coding. In this paper, taking advantage of both the classical compression architecture and the powerful non-linear representation ability of neural networks, we propose the first end-to-end deep video compression framework. Our framework employs pixel-wise motion information, which is learned from an optical flow network and further compressed by an auto-encoder network to save bits. The other compression components are also implemented by well-designed networks for high efficiency. All the modules are jointly optimized by using the rate-distortion trade-off and collaborate with each other. More importantly, the proposed deep video compression framework is very flexible and can be easily extended by using lightweight or advanced networks for higher speed or better efficiency. Experimental results show that the proposed approach can outperform the widely used video coding standard H.264 and be even on par with the latest standard H.265.