@article{learningclipguidedvisualtextfusion,
  title = {Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition},
  author = {Jun Zhu and Jiandong Jin and Zihan Yang and Xiaohao Wu and Xiao Wang},
  year = {2023},
  eprint = {2304.10091},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2304.10091v1},
}