← Back to papers
2013 ICCV ICCV 2013

Discovering Object Functionality

Abstract

Object functionality refers to the quality of an object that allows humans to perform some specific actions. It has been shown in psychology that functionality (affordance) is at least as essential as appearance in object recognition by humans. In computer vision, most previous work on functionality either assumes exactly one functionality for each object, or requires detailed annotation of human poses and objects. In this paper, we propose a weakly supervised approach to discover all possible object functionalities. Each object functionality is represented by a specific type of human-object interaction. Our method takes any possible human-object interaction into consideration, and evaluates image similarity in 3D rather than 2D in order to cluster human-object interactions more coherently. Experimental results on a dataset of people interacting with musical instruments show the effectiveness of our approach.

🚀 Conference Pioneer — ICCV 2013
🌉 Interdisciplinary Bridge — Computer Vision and Machine Learning
📈 Trend Setter — Few-Shot Learning
🧭 Keyword Pioneer — affordance detection
🐣 Hot Topic Early Bird — human-object interaction
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Bangpeng Yao , Jiayuan Ma , Li Fei-fei

Topics

Machine Learning > Learning Types > Weakly Supervised Learning Computer Vision > Analysis > Object Detection Computer Vision > Analysis > Scene Understanding Machine Learning > Learning Paradigms > Few-Shot Learning

Keywords

object recognition weakly supervised learning human-object interaction affordance detection 3d analysis object functionality affordance recognition 3d image similarity
Download PDF

Related papers

Large-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences 2013
Cascaded Shape Space Pruning for Robust Facial Landmark Detection 2013
Unsupervised Intrinsic Calibration from a Single Frame Using a "Plumb-Line" Approach 2013
Accurate and Robust 3D Facial Capture Using a Single RGBD Camera 2013
From Where and How to What We See 2013