arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

ACM International Conference on Multimedia · 会议 · Multimedia

2025-10-29 至 2025-10-29 共收录 2
2509.20077 2025-10-29 cs.RO cs.CV cs.HC

Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning

Xun Li, Rodrigo Santa Cruz, Mingze Xi, Hu Zhang, Madhawa Perera, Ziwei Wang, Ahalya Ravendran, Brandon J. Matthews, Feng Xu, Matt Adcock, Dadong Wang, Jiajun Liu

机构 * CSIRO(澳大利亚联邦科学与工业研究组织)

Journal ref MM '25: Proceedings of the 33rd ACM International Conference on Multimedia (2025) Pages 12492 - 12500

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17939 2025-10-29 cs.CV cs.AI

GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning

Bo Liu, Xiangyu Zhao, Along He, Yidi Chen, Huazhu Fu, Xiao-Ming Wu

机构 * The Hong Kong Polytechnic University(香港理工大学) Shenzhen University(深圳大学) West China Hospital of Sichuan University(四川大学华西医院) IHPC, Agency for Science, Technology and Research(科技研究局IHPC)

Comments Accepted at ACM MM 2025 (also known as GEMeX-ThinkVG)

详情

展开后加载摘要…

URL PDF HTML 收藏