Multi-modal visual tracking based on textual generation

Jiahao Wang, Fang Liu, Licheng Jiao, Hao Wang, Shuo Li, Lingling Li, Puhua Chen, Xu Liu

Abstract

Highlights•Visual-Language Interaction Prompt Manager is proposed.•Multi-modal Image Description Co-Generation Module is introduced.•Multi-modal Visual Tracking Based on Textual Generation method is designed.
BibTeX
@article{wang2024multi,
  author = {Jiahao Wang and Fang Liu and Licheng Jiao and Hao Wang and Shuo Li and Lingling Li and Puhua Chen and Xu Liu},
  title = {{Multi-modal visual tracking based on textual generation}},
  journal = {Information Fusion},
  year = {2024},
  doi = {10.1016/j.inffus.2024.102531},
}

Loading related content...

Figure