AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
This work addresses the problem of generating temporally aligned captions for videos with audio, benefiting video understanding and generation, but it is incremental as it builds on existing methods with new training techniques.
The paper tackles audiovisual video captioning by introducing AVoCaDO, a model that uses a two-stage post-training pipeline with fine-tuning and reward-based optimization, resulting in significant outperformance over existing open-source models on four benchmarks and competitive performance in visual-only settings.
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.