{
 "id": "nvidia/PhysicalAI-VANTAGE-Bench",
 "owner": "nvidia",
 "name": "PhysicalAI-VANTAGE-Bench",
 "downloads": 2875,
 "likes": 16,
 "last_modified": "2026-09-15T20:42:25.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "nvidia-evaluation-data-license",
 "licence_link": "LICENSE.md",
 "file_licence": null,
 "licence_files": [
  "LICENSE.md"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-text-to-text",
  "video-text-to-text"
 ],
 "citation": "@inproceedings{Fujita2020SODA,\n  author    = {Soichiro Fujita and Tsutomu Hirao and Hidetaka Kamigaito and Manabu Okumura and Masaaki Nagata},\n  title     = {{SODA}: Story Oriented Dense Video Captioning Evaluation Framework},\n  booktitle = {Proc. ECCV},\n  year      = {2020}\n}\n\n@inproceedings{Fu2024BLINK,\n  author    = {Xingyu Fu and Yushi Hu and Bangzheng Li and Yu Feng and Haoyu Wang and Xudong Lin and Dan Roth and Noah A. Smith and Wei-Chiu Ma and Ranjay Krishna},\n  title     = {{BLINK}: Multimodal Large Language Models Can See but Not Perceive},\n  booktitle = {Proc. ECCV},\n  year      = {2024}\n}\n\n@article{Sun2025RefDrone,\n  author    = {Zhichao Sun and Yuda Zou and Xian Sun and Yingchao Feng and Wenhui Diao and Menglong Yan and Kun Fu},\n  title     = {{RefDrone}: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes},\n  journal   = {arXiv preprint arXiv:2502.00392},\n  year      = {2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "ad5297f645ba90830478a4c6a72a3a7ab077a2f7",
 "stated_evidence": "https://huggingface.co/datasets/nvidia/PhysicalAI-VANTAGE-Bench/blob/ad5297f645ba90830478a4c6a72a3a7ab077a2f7/README.md",
 "file_evidence": "https://huggingface.co/datasets/nvidia/PhysicalAI-VANTAGE-Bench/blob/ad5297f645ba90830478a4c6a72a3a7ab077a2f7/LICENSE.md",
 "card_nc": false
}