v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914622415568896 |
|---|---|
| author | Shi, Zhengpeng Zhao, Yanpeng Zhou, Jianqun Wang, Yuxuan Cui, Qinrong Bi, Wei Zhu, Songchun Zhao, Bo Zheng, Zilong |
| author_facet | Shi, Zhengpeng Zhao, Yanpeng Zhou, Jianqun Wang, Yuxuan Cui, Qinrong Bi, Wei Zhu, Songchun Zhao, Bo Zheng, Zilong |
| contents | AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models (MLLMs) for humor understanding, we introduce v-HUB, a novel video humor understanding benchmark. v-HUB comprises a curated collection of non-verbal short videos, reflecting real-world scenarios where humor can be appreciated purely through visual cues. We pair each video clip with rich annotations to support a variety of evaluation tasks and analyses, including a novel study of environmental sound that can enhance humor. To broaden its applicability, we construct an open-ended QA task, making v-HUB readily integrable into existing video understanding task suites. We evaluate a diverse set of MLLMs, from specialized Video-LLMs to versatile OmniLLMs that can natively process audio, covering both open-source and proprietary domains. The experimental results expose the difficulties MLLMs face in comprehending humor from visual cues alone. Our findings also demonstrate that incorporating audio helps with video humor understanding, highlighting the promise of integrating richer modalities for complex video understanding tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound Shi, Zhengpeng Zhao, Yanpeng Zhou, Jianqun Wang, Yuxuan Cui, Qinrong Bi, Wei Zhu, Songchun Zhao, Bo Zheng, Zilong Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language AI models capable of comprehending humor hold real-world promise -- for example, enhancing engagement in human-machine interactions. To gauge and diagnose the capacity of multimodal large language models (MLLMs) for humor understanding, we introduce v-HUB, a novel video humor understanding benchmark. v-HUB comprises a curated collection of non-verbal short videos, reflecting real-world scenarios where humor can be appreciated purely through visual cues. We pair each video clip with rich annotations to support a variety of evaluation tasks and analyses, including a novel study of environmental sound that can enhance humor. To broaden its applicability, we construct an open-ended QA task, making v-HUB readily integrable into existing video understanding task suites. We evaluate a diverse set of MLLMs, from specialized Video-LLMs to versatile OmniLLMs that can natively process audio, covering both open-source and proprietary domains. The experimental results expose the difficulties MLLMs face in comprehending humor from visual cues alone. Our findings also demonstrate that incorporating audio helps with video humor understanding, highlighting the promise of integrating richer modalities for complex video understanding tasks. |
| title | v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.25773 |