Video-MME is the first comprehensive benchmark for multi-modal LLMs in video analysis, covering diverse video types, durations from seconds to an hour, and multi-modal inputs.
Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Video-MME is the first comprehensive benchmark for multi-modal LLMs in video analysis, covering diverse video types, durations from seconds to an hour, and multi-modal inputs.