4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation Paper • 2512.17012 • Published 9 days ago • 42
Depth Anything 3: Recovering the Visual Space from Any Views Paper • 2511.10647 • Published Nov 13 • 95
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics Paper • 2408.17443 • Published Aug 30, 2024 • 2
Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection Paper • 2304.04688 • Published Apr 10, 2023 • 1
Holistic Interaction Transformer Network for Action Detection Paper • 2210.12686 • Published Oct 23, 2022
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics Paper • 2408.17443 • Published Aug 30, 2024 • 2