Fine-grained understanding of operating room (OR) activity could enable workflow-aware assistance, yet remains difficult due to clutter, occlusions, and limited sensing. The prevailing approach to model this environment is scene graphs as an interpretable representation of OR interactions.
arXiv:2607. 03595v1 Announce Type: cross Abstract: Affordance grounding aims to localize image regions that support a specific action, serving as a core capability for physical intelligence and embodied perception.
Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries.
Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming proposes PoseOFF, a representation that captures local motion around human joints by conditioning optical flow extraction on pose. This structured motion representation aligns with human kinematics and improves early action recognition accuracy across multiple datasets and backbones. PoseOFF achieves comparable or better performance while observing less of the action sequence, making it suitable for real‑time, resource‑constrained robotic systems.
Action Quality Assessment (AQA) aims to objectively evaluate performance quality from action videos. Most existing methods follow a ``one-by-one'' paradigm, training a separate model for each action type.
arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).
arXiv:2401. 10805v4 Announce Type: replace-cross Abstract: We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding.
Human-robot interaction (HRI) requires robots to interpret human actions early in their execution in order to respond safely, efficiently, and naturally. However, many existing approaches to human act...
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
arXiv:2605. 23045v2 Announce Type: replace-cross Abstract: Video representation learning has seen tremendous progress in recent years.
arXiv:2608.24093v1 Announce Type: cross Abstract: Self-supervised representation learning for 4D point cloud videos is challenging because annotations are costly and reconstruction-based pretraining...
arXiv:2603. 09731v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric viewpoint.