Multimodal Graph Conditioned Diffusion Model for Video Captioning.

@inproceedings{zhang-2026-multimodal, author = {Benhui Zhang and Junyu Gao and Yuan Yuan}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Multimodal Graph Conditioned Diffusion Model for Video Captioning}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {3566--3575}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792087}, doi = {https://doi.org/10.1145/3774904.3792087} }