Do We Still Need Text Features for Video Retrieval in the Era of Vision-Language Models?

@inproceedings{langs-2026-still, author = {Georg Langs and Jiaqi Samantha Zhan and Crystina Zhang and Antonio Foncubierta-Rodr\'{i}guez and Shengyao Zhuang and Xueguang Ma and Georg Langs and Jiaqi Samantha Zhan and Jimmy Lin and Antonio Foncubierta-Rodr\'{i}guez and Crystina Zhang}, editor = {Ricardo Campos and Adam Jatowt and Yanyan Lan and Mohammad Aliannejadi and Christine Bauer and Sean MacAvaney and Avishek Anand and Zhaochun Ren and Suzan Verberne and Nan Bai and Masoud Mansoury}, title = {{Do We Still Need Text Features for Video Retrieval in the Era of Vision-Language Models?}}, booktitle = {{Advances in Information Retrieval - 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 - April 2, 2026, Proceedings, Part II}}, series = {Lecture Notes in Computer Science}, volume = {16484}, pages = {380--387}, publisher = {Springer}, year = {2026}, url = {https://doi.org/10.1007/978-3-032-21300-6_28}, doi = {https://doi.org/10.1007/978-3-032-21300-6_28} }