1.2k citations
- Chinese University of Hong KongHK59 papers
- Sun Yat-sen UniversityCN14 papers
- Tsinghua UniversityCN12 papers
- Chinese Academy of SciencesCN11 papers
- The University of SydneyAU9 papers
- University of Hong KongHK9 papers
- Beihang UniversityCN8 papers
- Nanyang Technological UniversitySG8 papers
- Shanghai Jiao Tong UniversityCN7 papers
- Shenzhen Institutes of Advanced TechnologyCN7 papers
- Tencent (China)CN7 papers
- Group Sense (China)CN6 papers
11 papers · 2 filters
LSTM Pose Machines
Yue Luo, Jimmy Ren, Zhouxia Wang +5
We observed that recent state-of-the-art results on single image human pose estimation were achieved by multi-stage Convolution Neural Networks (CNN). Notwithstanding the superior…
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Shuyang Sun, Zhanghui Kuang, Wanli Ouyang +2
Motion representation plays a vital role in human action recognition in videos. In this study, we introduce a novel compact motion representation for video action recognition, name…
End-to-end Flow Correlation Tracking with Spatial-temporal Attention
Zheng Zhu, Wei Wu, Wei Zou +1
Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers…
Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
Jiahao Pang, Wenxiu Sun, Jimmy SJ. Ren +2
Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performanc…
Practical Block-wise Neural Network Architecture Generation
Zhao Zhong, Junjie Yan, Wei Wu +2
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and ela…
Recurrent Scale Approximation for Object Detection in CNN
Yu Liu, Hongyang Li, Junjie Yan +3
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object…