Jun, 2024
基于 CLIP 的服装无关特征学习与人物换衣再识别
CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification
Shuang Li, Jiaxu Leng, Guozhang Li, Ji Gan, Haosheng chen...
TL;DR提出了一种名为 CLIP-Driven Cloth-Agnostic Feature Learning (CCAF) 的新颖框架,用于解决 Cloth-Changing Person Re-Identification (CC-ReID) 中 Contrastive Language-Image Pre-Training (CLIP) 过度关注衣物线索的问题,在多个流行的 CC-ReID 基准测试上取得了新的最先进性能,而无需额外的推理时间。