arXiv Computer Vision
Gaze2HOI: Gaze-Aware Intention Disambiguation for Egocentric Hand-Object Interaction Forecasting
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Oct 1
Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation
arXiv:2609.38615v1 Announce Type: cross Abstract: Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Ex...
arXiv AI
Sep 10
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video
arXiv:2609.08636v1 Announce Type: cross Abstract: Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize...
Hugging Face Trending Papers
Jul 9
Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts by relying on spurious correlations among hands, objects, or environmental context, rather than reasoning from the appearance and dynamics of hands and objects themselves.
arXiv Computer Vision
Oct 22
UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
UniRAP is a unified model that infers part-level physical affordances and translates language instructions into actionable geometric representations. It treats the task as a conditional multimodal generation problem, integrating visual inputs, textual instructions, and optional prompts into a shared spatiotemporal representation via a unified interface token mechanism. The model employs a Unified Affordance Decoder to jointly perform object detection, part-level affordance segmentation, and 4‑DoF interaction pose estimation, and uses a curriculum-based transfer training strategy to improve data efficiency with limited textual annotations.
arXiv Computer Vision
Oct 21
Decoupling Action from Egocentric Observation for World Simulation
arXiv:2610.27946v1 Announce Type: new Abstract: Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalab...
arXiv Computer Vision
Oct 12
ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies
ForeAct3D is a framework that grounds future world modeling in Vision‑Language‑Action policies by decoding depth, semantic segmentation, and camera pose from policy representations into current and future 3D scene states. The future queries are conditioned on the policy‑generated action chunk, and a physical‑consistency closure enforces background staticity, instance‑level rigidity, and wrist‑camera pose alignment with end‑effector kinematics. This approach eliminates the need for future prediction at inference and achieves high success rates on LIBERO and CALVIN, outperforming the base policy across all suites.