3 papers
cs.CV2025
Multi-Modal Graph Convolutional Network with Sinusoidal Encoding for Robust Human Action Segmentation
Hao Xing, Kai Zhe Boey, Yuankai Wu +2
Accurate temporal segmentation of human actions is critical for intelligent robots in collaborative settings, where a precise understanding of sub-activity labels and their tempora…
cs.CV2025
Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge
Constantin Patsch, Marsil Zakour, Yuankai Wu +1
In this report, we address the task of online mistake detection, which is vital in domains like industrial automation and education, where real-time video analysis allows human ope…
cs.CV2024
ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living
Marsil Zakour, Partha Pratim Nath, Ludwig Lohmer +6
Hand-Object Interactions (HOIs) are conditioned on spatial and temporal contexts like surrounding objects, previous actions, and future intents (for example, grasping and handover…