CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification
Published in European Conference on Computer Vision (ECCV), 2022
Recommended citation: Jinlin Wu, Lingxiao He, Wu Liu, Yang Yang, Zhen Lei, Tao Mei, Stan Z. Li. "CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification." ECCV 2022. pp. 549-566.
Download Paper