{
 "id": "DAMO-NLP-SG/Multi-Source-Video-Captioning",
 "owner": "DAMO-NLP-SG",
 "name": "Multi-Source-Video-Captioning",
 "downloads": 52,
 "likes": 7,
 "last_modified": "2024-06-17T09:15:05.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering",
  "question-answering"
 ],
 "citation": "@article{damonlpsg2024videollama2,\n  title={VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs},\n  author={Cheng, Zesen and Leng, Sicong and Zhang, Hang and Xin, Yifei and Li, Xin and Chen, Guanzheng and Zhu, Yongxin and Zhang, Wenqi and Luo, Ziyang and Zhao, Deli and Bing, Lidong},\n  journal={arXiv preprint arXiv:2406.07476},\n  year={2024},\n  url = {https://arxiv.org/abs/2406.07476}\n}\n\n@article{damonlpsg2023videollama,\n  title = {Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding},\n  author = {Zhang, Hang and Li, Xin and Bing, Lidong},\n  journal = {arXiv preprint arXiv:2306.02858},\n  year = {2023},\n  url = {https://arxiv.org/abs/2306.02858}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "4b62116393bc100dd75680c960c2b5f1d8e6b5f8",
 "stated_evidence": "https://huggingface.co/datasets/DAMO-NLP-SG/Multi-Source-Video-Captioning/blob/4b62116393bc100dd75680c960c2b5f1d8e6b5f8/README.md",
 "file_evidence": "https://huggingface.co/datasets/DAMO-NLP-SG/Multi-Source-Video-Captioning/tree/4b62116393bc100dd75680c960c2b5f1d8e6b5f8",
 "card_nc": false
}