@inproceedings{learningaudioguidedvideorepresentation, title = {Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval}, author = {Boseung Jeong and Jicheol Park and Sungyeon Kim and Suha Kwak}, year = {2025}, booktitle = {CVPR 2025 1}, eprint = {2504.02397}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.02397v1}, }