71 citations
- Huazhong University of Science and TechnologyCN8 papers
- Chinese Academy of SciencesCN7 papers
- Institute of AutomationCN7 papers
- Nanjing UniversityCN7 papers
- Tsinghua UniversityCN7 papers
- University of Chinese Academy of SciencesCN6 papers
- Wuhan UniversityCN5 papers
- Institute of AcousticsCN4 papers
- Center for Excellence in Brain Science and Intelligence TechnologyCN3 papers
- Chinese University of Hong KongHK2 papers
- Google (United States)US2 papers
- Horizon Research (United States)US2 papers
7 papers · 1 filter
Monocular Road Planar Parallax Estimation
Haobo Yuan, Teng Chen, Wei Sui +4
Estimating the 3D structure of the drivable surface and surrounding environment is a crucial task for assisted and autonomous driving. It is commonly solved either by using 3D sens…
Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
Xinggang Wang, Zhaojin Huang, Bencheng Liao +3
Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for p…
Deep Online Correction for Monocular Visual Odometry
Jiaxin Zhang, Wei Sui, Xinggang Wang +3
In this work, we propose a novel deep online correction (DOC) framework for monocular visual odometry. The whole pipeline has two stages: First, depth maps and initial poses are ob…
Mutual Information State Intrinsic Control
Rui Zhao, Yang Gao, Pieter Abbeel +2
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts…
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
Helong Zhou, Liangchen Song, Jiajie Chen +4
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The out…
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
Mengting Chen, Xinggang Wang, Heng Luo +2
Deep networks can learn to accurately recognize objects of a category by training on a large number of annotated images. However, a meta-learning challenge known as a low-shot imag…