Year: 2025
Type: preprint
Abstract: Audiovisual video captioning aims to generate semantically rich descriptions with temporal alignment between visual and auditory events, thereby benefiting both video understanding and generation. In this paper, we present AVoCaDO, a powerful audiovisual video captioner driven by the temporal orchestration between audio and visual modalities. We propose a two-stage post-training pipeline: (1) AVoCaDO SFT, which fine-tunes the model on a newly curated dataset of 107K high-quality, temporally-aligned audiovisual captions; and (2) AVoCaDO GRPO, which leverages tailored reward functions to further enhance temporal coherence and dialogue accuracy while regularizing caption length and reducing collapse. Experimental results demonstrate that AVoCaDO significantly outperforms existing open-source models across four audiovisual video captioning benchmarks, and also achieves competitive performance on the VDC and DREAM-1K benchmark under visual-only settings.
Source: arXiv (Cornell University)
Authors: Chen, Xinlong, Ding, Yue, Lin, Weihong, Hua, Jingyun, Yao, Linli, Shi, Yang, Li, Bozhou, Zhang, Yuanxing, Liu, Qiang, Wan, Pengfei, Wang, Liang, Tan, Tieniu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7090714929
Cites:
Cited by:
Related to: