MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
This addresses a gap in evaluation for multi-modal video understanding, but it is incremental as it builds on existing benchmarks by extending to multi-video scenarios.
The authors tackled the lack of benchmarks for evaluating multi-modal LLMs on complex interactions across multiple videos by introducing MVPBench, a benchmark with 14 subtasks and 5K question-answering tests, and found that current models struggle with multi-video inputs.
The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual and comprehension abilities. Existing benchmarks, however, are limited to static images or single videos, overlooking the complex interactions across multiple videos. To address this gap, we introduce the Multi-Video Perception Evaluation Benchmark (MVPBench), a new benchmark featuring 14 subtasks across diverse visual domains designed to evaluate models on extracting relevant information from video sequences to make informed decisions. MVPBench includes 5K question-answering tests involving 2.7K video clips sourced from existing datasets and manually annotated clips. Extensive evaluations reveal that current models struggle to process multi-video inputs effectively, underscoring substantial limitations in their multi-video comprehension. We anticipate MVPBench will drive advancements in multi-video perception.