Global-Local Temporal Representations for Video Person Re-Identification

Jianing Li, Jingdong Wang, Qi Tian, Wen Gao, Shiliang Zhang; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 3958-3967


This paper proposes the Global-Local Temporal Representation (GLTR) to exploit the multi-scale temporal cues in video sequences for video person Re-Identification (ReID). GLTR is constructed by first modeling the short-term temporal cues among adjacent frames, then capturing the long-term relations among inconsecutive frames. Specifically, the short-term temporal cues are modeled by parallel dilated convolutions with different temporal dilation rates to represent the motion and appearance of pedestrian. The long-term relations are captured by a temporal self-attention model to alleviate the occlusions and noises in video sequences. The short and long-term temporal cues are aggregated as the final GLTR by a simple single-stream CNN. GLTR shows substantial superiority to existing features learned with body part cues or metric learning on four widely-used video ReID datasets. For instance, it achieves Rank-1 Accuracy of 87.02% on MARS dataset without re-ranking, better than current state-of-the art.

Related Material

author = {Li, Jianing and Wang, Jingdong and Tian, Qi and Gao, Wen and Zhang, Shiliang},
title = {Global-Local Temporal Representations for Video Person Re-Identification},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}