StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval
Harbin Institute of Technology · Shenzhen Institute of Information Technology · Xi'an Jiaotong University · Shandong University
- Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval
- 2026-07-15
- 0
@inproceedings{wang2026structalign,
title = {StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval},
author = {Shaokun Wang and Weili Guan and Jizhou Han and Jianlong Wu and Yupeng Hu and Liqiang Nie},
year = {2026},
booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval},
eprint = {2601.20597},
archivePrefix = {arXiv},
doi = {10.1145/3805712.3809704},
url = {https://arxiv.org/abs/2601.20597},
}