TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing.

@inproceedings{chen-2025-temtg, author = {Yaru Chen and Peiliang Zhang and Fei Li and Faegheh Sardari and Ruohao Guo and Zhenbo Li and Wenwu Wang}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {1978--1982}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733495}, doi = {https://doi.org/10.1145/3731715.3733495} }