Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs.

@inproceedings{zeng-2026-learning, author = {Donghuo Zeng and Hao Niu and Yanan Wang and Masato Taya}, 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 = {{Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs}}, 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 = {254--270}, publisher = {Springer}, year = {2026}, url = {https://doi.org/10.1007/978-3-032-21300-6_16}, doi = {https://doi.org/10.1007/978-3-032-21300-6_16} }