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

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.