publications

2024

1. CVPR

   

   ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval

   Kaipeng Fang, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Zhi-Qi Cheng, Xiyao Li, and Heng Tao Shen

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   TL;DR arXiv Bib Code

   

   This paper proposes Prompting-to-Simulate (ProS), a novel prompt tuning framework for Universal Cross-Domain Retrieval (UCDR) that generates Content-aware Dynamic Prompts via a two-stage simulation process to effectively address domain and semantic shifts, achieving state-of-the-art performance with high parameter efficiency.

   @inproceedings{fang2024pros,
     title = {ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval},
     author = {Fang, Kaipeng and Song, Jingkuan and Gao, Lianli and Zeng, Pengpeng and Cheng, Zhi-Qi and Li, Xiyao and Shen, Heng Tao},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2024},
     tldr = {This paper proposes Prompting-to-Simulate (ProS), a novel prompt tuning framework for Universal Cross-Domain Retrieval (UCDR) that generates Content-aware Dynamic Prompts via a two-stage simulation process to effectively address domain and semantic shifts, achieving state-of-the-art performance with high parameter efficiency.},
   }