activity
20172021
most citedCross Attention Network for Few-shot Classification

142 citations · 314 across the 11 of their papers we have counts for

collaborators

14 papers

cs.CV2021

Feature Completion for Occluded Person Re-Identification

Ruibing Hou, Bingpeng Ma, Hong Chang +3

Person re-identification (reID) plays an important role in computer vision. However, existing methods suffer from performance degradation in occluded scenes. In this work, we propo…

cs.CV2021

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

Ruibing Hou, Hong Chang, Bingpeng Ma +2

In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for…

cs.CV2021

Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking

Shen Li, Bingpeng Ma, Hong Chang +2

This paper proposes a novel model, named Continuity-Discrimination Convolutional Neural Network (CD-CNN), for visual object tracking. Existing state-of-the-art tracking methods do…

cs.CV20203 cited

IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

Ruibing Hou, Bingpeng Ma, Hong Chang +3

Person re-identification (reID) by CNNs based networks has achieved favorable performance in recent years. However, most of existing CNNs based methods do not take full advantage o…

cs.CV202012 cited

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Xinqian Gu, Hong Chang, Bingpeng Ma +2

Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID). In this case, 3D…

cs.CV202015 cited

Temporal Complementary Learning for Video Person Re-Identification

Ruibing Hou, Hong Chang, Bingpeng Ma +2

This paper proposes a Temporal Complementary Learning Network that extracts complementary features of consecutive video frames for video person re-identification. Firstly, we intro…