Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912264175484928 |
|---|---|
| author | Zhao, Zijia Lu, Haoyu Huo, Yuqi Du, Yifan Yue, Tongtian Guo, Longteng Wang, Bingning Chen, Weipeng Liu, Jing |
| author_facet | Zhao, Zijia Lu, Haoyu Huo, Yuqi Du, Yifan Yue, Tongtian Guo, Longteng Wang, Bingning Chen, Weipeng Liu, Jing |
| contents | Video understanding is a crucial next step for multimodal large language models (MLLMs). Various benchmarks are introduced for better evaluating the MLLMs. Nevertheless, current video benchmarks are still inefficient for evaluating video models during iterative development due to the high cost of constructing datasets and the difficulty in isolating specific skills. In this paper, we propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation. VideoNIAH decouples video content from their query-responses by inserting unrelated visual 'needles' into original videos. The framework automates the generation of query-response pairs using predefined rules, minimizing manual labor. The queries focus on specific aspects of video understanding, enabling more skill-specific evaluations. The separation between video content and the queries also allow for increased video variety and evaluations across different lengths. Utilizing VideoNIAH, we compile a video benchmark VNBench, which includes tasks such as retrieval, ordering, and counting to evaluate three key aspects of video understanding: temporal perception, chronological ordering, and spatio-temporal coherence. We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities across various tasks. Additionally, we perform an in-depth analysis of the test results and model configurations. Based on these findings, we provide some advice for improving video MLLM training, offering valuable insights to guide future research and model development. The code and data are available at https://github.com/joez17/VideoNIAH. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09367 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs Zhao, Zijia Lu, Haoyu Huo, Yuqi Du, Yifan Yue, Tongtian Guo, Longteng Wang, Bingning Chen, Weipeng Liu, Jing Computer Vision and Pattern Recognition Video understanding is a crucial next step for multimodal large language models (MLLMs). Various benchmarks are introduced for better evaluating the MLLMs. Nevertheless, current video benchmarks are still inefficient for evaluating video models during iterative development due to the high cost of constructing datasets and the difficulty in isolating specific skills. In this paper, we propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation. VideoNIAH decouples video content from their query-responses by inserting unrelated visual 'needles' into original videos. The framework automates the generation of query-response pairs using predefined rules, minimizing manual labor. The queries focus on specific aspects of video understanding, enabling more skill-specific evaluations. The separation between video content and the queries also allow for increased video variety and evaluations across different lengths. Utilizing VideoNIAH, we compile a video benchmark VNBench, which includes tasks such as retrieval, ordering, and counting to evaluate three key aspects of video understanding: temporal perception, chronological ordering, and spatio-temporal coherence. We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities across various tasks. Additionally, we perform an in-depth analysis of the test results and model configurations. Based on these findings, we provide some advice for improving video MLLM training, offering valuable insights to guide future research and model development. The code and data are available at https://github.com/joez17/VideoNIAH. |
| title | Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.09367 |