1.6k citations · 3.7k across the 93 of their papers we have counts for
15 papers · 1 filter
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
Dacheng Yin, Chong Luo, Zhiwei Xiong +1
Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude pre…
Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments
Junsheng Zhou, Yuwang Wang, Kaihuai Qin +1
Recently unsupervised learning of depth from videos has made remarkable progress and the results are comparable to fully supervised methods in outdoor scenes like KITTI. However, t…
Unsupervised High-Resolution Depth Learning From Videos With Dual Networks
Junsheng Zhou, Yuwang Wang, Kaihuai Qin +1
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal…
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
Pengfei Zhang, Jianru Xue, Cuiling Lan +3
Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on c…
Cross View Fusion for 3D Human Pose Estimation
Haibo Qiu, Chunyu Wang, Jingdong Wang +2
We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) e…
Posterior-Guided Neural Architecture Search
Yizhou Zhou, Xiaoyan Sun, Chong Luo +2
The emergence of neural architecture search (NAS) has greatly advanced the research on network design. Recent proposals such as gradient-based methods or one-shot approaches signif…
Semantics-Aligned Representation Learning for Person Re-identification
Xin Jin, Cuiling Lan, Wenjun Zeng +2
Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally seman…
Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification
Zheng Wang, Zhixiang Wang, Yinqiang Zheng +3
An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis. Recently,…
Quality-Gated Convolutional LSTM for Enhancing Compressed Video
Ren Yang, Xiaoyan Sun, Mai Xu +1
The past decade has witnessed great success in applying deep learning to enhance the quality of compressed video. However, the existing approaches aim at quality enhancement on a s…
SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
Guangting Wang, Chong Luo, Zhiwei Xiong +1
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, name…
CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
Xin Jin, Cuiling Lan, Wenjun Zeng +2
Objects at different spatial positions in an image exhibit different scales. Adaptive receptive fields are expected to capture suitable ranges of context for accurate pixel level s…
Relation-Aware Global Attention for Person Re-identification
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng +2
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matche…
Target-Tailored Source-Transformation for Scene Graph Generation
Wentong Liao, Cuiling Lan, Wenjun Zeng +2
Scene graph generation aims to provide a semantic and structural description of an image, denoting the objects (with nodes) and their relationships (with edges). The best performin…
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Pengfei Zhang, Cuiling Lan, Wenjun Zeng +3
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feed…
View Invariant 3D Human Pose Estimation
Guoqiang Wei, Cuiling Lan, Wenjun Zeng +1
The recent success of deep networks has significantly advanced 3D human pose estimation from 2D images. The diversity of capturing viewpoints and the flexibility of the human poses…