681 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Chinese Academy of SciencesCN70 papers
- University of Chinese Academy of SciencesCN24 papers
- National Astronomical ObservatoriesCN8 papers
- University of RochesterUS8 papers
- Peking UniversityCN7 papers
- University of Science and Technology of ChinaCN7 papers
- University of TorontoCA7 papers
- Changchun University of Science and TechnologyCN6 papers
- Purple Mountain ObservatoryCN6 papers
- Fudan UniversityCN5 papers
- State Key Laboratory of Applied Optics5 papers
- State Key Laboratory of Surface Physics5 papers
9 papers · 1 filter
Transformer-based stereo-aware 3D object detection from binocular images
Hanqing Sun, Yanwei Pang, Jiale Cao +2
Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the atten…
Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search
Jiabei Wang, Yanwei Pang, Jiale Cao +3
Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastiv…
Identity-aware Facial Expression Recognition in Compressed Video
Xiaofeng Liu, Linghao Jin, Xu Han +3
This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB…
Energy-constrained Self-training for Unsupervised Domain Adaptation
Xiaofeng Liu, Bo Hu, Xiongchang Liu +3
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-t…
Select Good Regions for Deblurring based on Convolutional Neural Networks
Hang Yang, Xiaotian Wu, Xinglong Sun
The goal of blind image deblurring is to recover sharp image from one input blurred image with an unknown blur kernel. Most of image deblurring approaches focus on developing image…
Accelerating temporal action proposal generation via high performance computing
Tian Wang, Shiye Lei, Youyou Jiang +3
Temporal action recognition always depends on temporal action proposal generation to hypothesize actions and algorithms usually need to process very long video sequences and output…
Background Subtraction with Real-time Semantic Segmentation
Dongdong Zeng, Xiang Chen, Ming Zhu +2
Accurate and fast foreground object extraction is very important for object tracking and recognition in video surveillance. Although many background subtraction (BGS) methods have…
Depth Image Upsampling based on Guided Filter with Low Gradient Minimization
Hang Yang, Zhongbo Zhang
In this paper, we present a novel upsampling framework to enhance the spatial resolution of the depth image. In our framework, the upscaling of a low-resolution depth image is guid…
Combining Background Subtraction Algorithms with Convolutional Neural Network
Dongdong Zeng, Ming Zhu, Arjan Kuijper
Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition. Thus, enormous bac…