3 papers
cs.CV2026
PhysInOne: Visual Physics Learning and Reasoning in One Suite
Siyuan Zhou, Hejun Wang, Hu Cheng +36
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to mere…
cs.CV2026
SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
Xinyi Zheng, Yunze Liu, Chi-Hao Wu +5
We present SpatialMem, a memory-centric system for long-horizon, language-grounded retrieval and QA from egocentric video, where metric 3D serves as an interpretable indexing scaff…
cs.CV2025
X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding
Wenqi Zhou, Kai Cao, Hao Zheng +8
Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in…