Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918039562223616 |
|---|---|
| author | Fu, Chaoyou Dai, Yuhan Luo, Yongdong Li, Lei Ren, Shuhuai Zhang, Renrui Wang, Zihan Zhou, Chenyu Shen, Yunhang Zhang, Mengdan Chen, Peixian Li, Yanwei Lin, Shaohui Zhao, Sirui Li, Ke Xu, Tong Zheng, Xiawu Chen, Enhong Shan, Caifeng He, Ran Sun, Xing |
| author_facet | Fu, Chaoyou Dai, Yuhan Luo, Yongdong Li, Lei Ren, Shuhuai Zhang, Renrui Wang, Zihan Zhou, Chenyu Shen, Yunhang Zhang, Mengdan Chen, Peixian Li, Yanwei Lin, Shaohui Zhao, Sirui Li, Ke Xu, Tong Zheng, Xiawu Chen, Enhong Shan, Caifeng He, Ran Sun, Xing |
| contents | In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs in processing sequential visual data is still insufficiently explored, highlighting the absence of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including subtitles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. 900 videos with a total of 254 hours are manually selected and annotated by repeatedly viewing all the video content, resulting in 2,700 question-answer pairs. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1.5 Pro, as well as open-source image models like InternVL-Chat-V1.5 and video models like LLaVA-NeXT-Video. Our experiments reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data. Project Page: https://video-mme.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_21075 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis Fu, Chaoyou Dai, Yuhan Luo, Yongdong Li, Lei Ren, Shuhuai Zhang, Renrui Wang, Zihan Zhou, Chenyu Shen, Yunhang Zhang, Mengdan Chen, Peixian Li, Yanwei Lin, Shaohui Zhao, Sirui Li, Ke Xu, Tong Zheng, Xiawu Chen, Enhong Shan, Caifeng He, Ran Sun, Xing Computer Vision and Pattern Recognition Computation and Language In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs in processing sequential visual data is still insufficiently explored, highlighting the absence of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including subtitles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. 900 videos with a total of 254 hours are manually selected and annotated by repeatedly viewing all the video content, resulting in 2,700 question-answer pairs. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, including GPT-4 series and Gemini 1.5 Pro, as well as open-source image models like InternVL-Chat-V1.5 and video models like LLaVA-NeXT-Video. Our experiments reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data. Project Page: https://video-mme.github.io |
| title | Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2405.21075 |