M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval.

@inproceedings{yu-2024-m2raap, author = {Xuzheng Yu and Sicong Zhang and Xingning Dong and Zipeng Feng and Chunluan Zhou and Xuzheng Yu and Sicong Zhang and Ming Yang and Qingpei Guo}, editor = {Grace Hui Yang and Hongning Wang and Sam Han and Claudia Hauff and Guido Zuccon and Yi Zhang}, title = {{M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval}}, booktitle = {{Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington DC, USA, July 14-18, 2024}}, pages = {2156--2166}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3626772.3657833}, doi = {https://doi.org/10.1145/3626772.3657833} }