V2 Dial: Unification of Video and Visual Dialog via Multimodal Experts
Adnen Abdessaied, Anna Rohrbach, Marcus Rohrbach, Andreas Bulling
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8637-8647, 2025.
Abstract
Links
BibTeX
@inproceedings{11094556,
author = {Abdessaied, Adnen and Rohrbach, Anna and Rohrbach, Marcus and Bulling, Andreas},
booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
title = {V2 Dial: Unification of Video and Visual Dialog via Multimodal Experts},
year = {2025},
volume = {},
number = {},
pages = {8637-8647},
keywords = {Visualization;Computer vision;Limiting;Computational modeling;Training data;Contrastive learning;Routing;Data models;Pattern recognition;Videos},
doi = {10.1109/CVPR52734.2025.00807}
}