MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918406161170432 |
|---|---|
| author | Bai, Purui Wu, Tao Sun, Jiayang Liu, Xinyue Huang, Huaibo He, Ran |
| author_facet | Bai, Purui Wu, Tao Sun, Jiayang Liu, Xinyue Huang, Huaibo He, Ran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22756 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding Bai, Purui Wu, Tao Sun, Jiayang Liu, Xinyue Huang, Huaibo He, Ran Computer Vision and Pattern Recognition 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. |
| title | MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.22756 |