← back
arXivQiaohui Chu, Haoyu Zhang, Yisen Feng, Meng Liu, Weili Guan, Dongmei Jiang, Liqiang NieWed, May 20, 2026, 1:42 AM PDT
score 12.9
2cites

System predicts what humans will touch next in video

Original: VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026

Source: arxiv.org

Writing ELI5 summary…