{
 "id": "SEACrowd/openvivqa",
 "owner": "SEACrowd",
 "name": "openvivqa",
 "downloads": 79,
 "likes": 0,
 "last_modified": "2026-06-29T21:37:43.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering"
 ],
 "citation": "@article{NGUYEN2023101868,\ntitle = {OpenViVQA: Task, dataset, and multimodal fusion models for visual question answering in Vietnamese},\njournal = {Information Fusion},\nvolume = {100},\npages = {101868},\nyear = {2023},\nissn = {1566-2535},\ndoi = {https://doi.org/10.1016/j.inffus.2023.101868},\nurl = {https://www.sciencedirect.com/science/article/pii/S1566253523001847},\nauthor = {Nghia Hieu Nguyen and Duong T.D. Vo and Kiet {Van Nguyen} and Ngan Luu-Thuy Nguyen},\nkeywords = {Visual question answering, Vision-language understanding, Low-resource languages, Information fusion, Multimodal representation},\nabstract = {In recent years, visual question answering (VQA) has attracted attention from the research community because of its highly potential applications (such as virtual assistance on intelligent cars, assistant devices for blind people, or information retrieval from document images using natural language as queries) and challenge. The VQA task requires methods that have the ability to fuse the information from questions and images to produce appropriate answers. Neural visual question answering models have achieved tremendous growth on large-scale datasets which are mostly for resource-rich languages such as English. However, available datasets narrow the VQA task as the answers selection task or answer classification task. We argue that this form of VQA is far from human ability and eliminates the challenge of the answering aspect in the VQA task by just selecting answers ra",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "f410585619a191d121779148b68437388147da10",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/openvivqa/blob/f410585619a191d121779148b68437388147da10/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/openvivqa/blob/f410585619a191d121779148b68437388147da10/LICENSE",
 "card_nc": false
}