LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
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_ | 1866912662326083584 |
|---|---|
| author | Han, ZhaoYang Lin, Qihan Liang, Hao Chen, Bowen Liu, Zhou Zhang, Wentao |
| author_facet | Han, ZhaoYang Lin, Qihan Liang, Hao Chen, Bowen Liu, Zhou Zhang, Wentao |
| contents | We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models' ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in three key areas: \textbf{a) Long-Duration, Information-Dense Videos:} We carefully select approximately 1,000 videos from open-source datasets FineVideo based on duration limit and the information density of both visual and audio modalities, focusing on content like lectures, interviews, and vlogs, which contain rich language elements. \textbf{b) Diverse and Challenging Task Scenarios:} We have designed six challenging task scenarios, including both Intra-Event and Inter-Event Tasks. \textbf{c) Rigorous and Comprehensive Quality Assurance Pipelines:} We have developed a three-step, semi-automated data quality assurance pipeline to ensure the difficulty and validity of the synthesized questions and answer options. Based on LongInsightBench, we designed a series of experiments. Experimental results shows that Omni-modal models(OLMs) still face challenge in tasks requiring precise temporal localization (T-Loc) and long-range causal inference (CE-Caus). Extended experiments reveal the information loss and processing bias in multi-modal fusion of OLMs. Our dataset and code is available at https://anonymous.4open.science/r/LongInsightBench-910F/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17305 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding Han, ZhaoYang Lin, Qihan Liang, Hao Chen, Bowen Liu, Zhou Zhang, Wentao Computer Vision and Pattern Recognition Multimedia We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models' ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in three key areas: \textbf{a) Long-Duration, Information-Dense Videos:} We carefully select approximately 1,000 videos from open-source datasets FineVideo based on duration limit and the information density of both visual and audio modalities, focusing on content like lectures, interviews, and vlogs, which contain rich language elements. \textbf{b) Diverse and Challenging Task Scenarios:} We have designed six challenging task scenarios, including both Intra-Event and Inter-Event Tasks. \textbf{c) Rigorous and Comprehensive Quality Assurance Pipelines:} We have developed a three-step, semi-automated data quality assurance pipeline to ensure the difficulty and validity of the synthesized questions and answer options. Based on LongInsightBench, we designed a series of experiments. Experimental results shows that Omni-modal models(OLMs) still face challenge in tasks requiring precise temporal localization (T-Loc) and long-range causal inference (CE-Caus). Extended experiments reveal the information loss and processing bias in multi-modal fusion of OLMs. Our dataset and code is available at https://anonymous.4open.science/r/LongInsightBench-910F/. |
| title | LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2510.17305 |