Video-Based Person Re-Identification With Unregulated Sequences

Video-based person re-identification (re-id) has recently attracted widespread attentions because extra space-time information and more appearance cues in videos can be used to improve the performance of image-based person re-id. Most existing approaches equally treat person video images, ignoring their individual discrepancy. However, in real scenarios, captured images are usually contaminated by various noises, especially occlusions, resulting in a series of unregulated sequences. Through investigating the impact of unregulated sequences to feature representation of video-based person re-id, the authors find a remarkable promotion by eliminating noisy sub sequences. Based on this interesting finding, an adaptive unregulated sub sequence detection and refinement method is proposed to purify original video sequence and obtain a more effective and discriminative feature representation for video-based person re-id. Experimental results on two public datasets demonstrate that the proposed method outperforms the state-of-the-art work.