VideoMME

The 'VideoMME' dataset/benchmark contains long-form videos and is used to evaluate the performance of multi-modal large language models in video understanding tasks.

Papers using VideoMME (3)

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding2025 · 3 citesThink-Clip-Sample: Slow-Fast Frame Selection for Video Understanding2026Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders2025