中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组


News / Events

VIPL's paper on person re-identification is accepted by the journal IEEE TPAMI

Date of publication:2021-05-07      Number of clicks: 0

Recently, one paper on person re-identification is accepted by the journal IEEE TPAMI. The full name of TPAMI is Transactions on Pattern Analysis and Machine Intelligence, which is a

CCF-ranked-A top-tier Artificial Intelligence journal with a high IF score as 17.86. Below is a brief introduction of this work.

 

Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan and Xilin Chen, “Feature Completion for Occluded Person Re-Identification”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. (Accepted)

 

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 propose an occlusion-robust block, Region Feature Completion (RFC), for occluded reID. Different from most previous works that discard the occluded regions, RFC block can recover the semantics of occluded regions in feature space. Firstly, a Spatial RFC (SRFC) module is developed. SRFC exploits the long-range spatial contexts from non-occluded regions to predict the features of occluded regions.  Secondly, we introduce Temporal RFC (TRFC) module which captures the long-term temporal contexts to refine the prediction of SRFC. RFC block is lightweight, end-to-end trainable and can be

easily plugged into existing CNNs to form RFCnet. The framework of RFCnet is below.





In summary, the main contributions of our work lie in four aspects: (1) proposing to use feature completion to address the occluded person reID problem; (2) designing a SRFC and TRFC module that respectively captures spatial and temporal contexts to recover the features of occluded regions; (3) constructing a large-scale video occluded reID dataset Occluded-DukeMTMCVideoReID to facilitate the research on occluded reID; (4) achieving superior performance on both occluded and holistic reID compared with state-of-the-art methods.




中科院计算所视觉信息处理与学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号-1 京公网安备1101080060