Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset
Zhengqian Wu, Zhixian Liu, Aodong Chen +6
Video question answering (VideoQA) aims to answer questions about given videos. While existing approaches excel on factoid VideoQA, they struggle with deep video understanding (DVU…
cs.CV2024
Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
Yueru Jia, Jiaming Liu, Sixiang Chen +8
3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial…