LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos

Tiantian Geng; Jinrui Zhang; Qingni Wang; Teng Wang; Jinming Duan; Feng Zheng

doi:10.1109/cvpr52734.2025.01766

CVPR2025顶会

LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos

Tiantian Geng, Jinrui Zhang, Qingni Wang, Teng Wang, Jinming Duan, Feng Zheng

arXiv DOI 出版方

2025年份

16顶会引用

摘要

Figure 1. We introduce LongVALE, the first-ever omni-modality long video benchmark, offering precise temporal boundaries and captions for omni-modal events integrating visual, audio, and speech information. The captions feature audio-visual correlations to enhance crossmodal learning. Besides, we extend three fine-grained video tasks to the omni-modality domain, enabling omni-perception of long videos.