作者位次 #4/6ECCV 2026Poster
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
Yijia Lei · Jinzhao Li · Yichi Zhang · Jiacheng Hua · Yin Li · Miao Liu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yijia Lei · Jinzhao Li · Yichi Zhang · Jiacheng Hua · Yin Li · Miao Liu
Jiacheng Hua · Yishu Yin · Yuhang Wu · Tai Wang · Yifei Huang · Miao Liu
Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive theories of allocentric spatial reasoning, we investigate...