lmms-lab/Video-MME dataset hosted on Hugging Face and contributed by the HF Datasets community

vid-modeling/videomme dataset hosted on Hugging Face and contributed by the HF Datasets community

VLM2Vec/videomme-rawvideo dataset hosted on Hugging Face and contributed by the HF Datasets community

yanlaiy/VideoMME dataset hosted on Hugging Face and contributed by the HF Datasets community

topyun/Video-MME-Long dataset hosted on Hugging Face and contributed by the HF Datasets community

VLM2Vec/Video-MME dataset hosted on Hugging Face and contributed by the HF Datasets community

js-hyun/preprocess-videomme-data dataset hosted on Hugging Face and contributed by the HF Datasets community

ejhwang/Video-MME-Res-Text-Only dataset hosted on Hugging Face and contributed by the HF Datasets community

Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models

  📜 License

Video-LevelGauge is under the CC-BY-NC-SA-4.0 license. It is derived from several previously published datasets (VideoMME, MLVU, VisDrone, UCF-Crime, and Ego4D). Please note that the original datasets may have their own licenses. Users must comply with the licenses of the original datasets when using this derived… See the full description on the dataset page: https://huggingface.co/datasets/Cola-any/Video-LevelGauge.