cs.CVNov 10, 2026

Hand-Object Contact Transition Detection in Egocentric Video

Authors: Huy Anh Nguyen, Chang Dong, Feras Dayoub, Minh Hoai

Organizations: Australian Institute for Machine Learning, Adelaide University, Adelaide, Australia

Abstract

This paper tackles the task of hand-object contact transition detection in egocentric video, which aims to localize the two temporal boundaries of a contact episode: the moment a hand first establishes contact with an object (touch) and the moment contact is released (release). We propose a unified framework that jointly models the interacting hand and object to accurately localize both transition types. The proposed framework augments hand-centric spatiotemporal representations with object-aware features learned directly from the video and introduces a transition-aware event spotting formulation tailored to contact transitions, without relying on external object or hand-object interaction detectors during inference. To support this task, we present ContactTransition, a dataset comprising 4,021 egocentric videos with 8,498 touch and 8,077 release annotations, together with object-of-interest supervision. Experiments demonstrate that the proposed method consistently outperforms strong two-stage and end-to-end event-spotting baselines on both transition types. Finally, we show that detected contact transitions provide effective temporal anchors for downstream egocentric hand-object reasoning.

Figures & tables

Explore similar work

CardsList
  1. Detecting Precise Hand Touch Moments in Egocentric Video

    Apr 14, 2026Huy Anh Nguyen, Feras Dayoub, Minh HoaiHand-Object Contact EstimationHand-Object Interaction Detection

  2. TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video

    May 13, 2026Jianyi Zhou, Ziteng Gao, Feiyang Hong +11Vision-Based Tactile SensingVisual-to-Tactile Prediction

  3. EgoContact: Evaluating Physical Intelligence with Egocentric Video

    Oct 29, 2026Adam Deryło, Alexey Gavryushin, Daniel Cremers +2Robot Manipulation DatasetsRobot Manipulation Benchmarks