Hallucinated Humans as the Hidden Context for Labeling 3D Scenes
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2993-3000
- https://doi.org/10.1109/cvpr.2013.385
Abstract
For scene understanding, one popular approach has been to model the object-object relationships. In this paper, we hypothesize that such relationships are only an artifact of certain hidden factors, such as humans. For example, the objects, monitor and keyboard, are strongly spatially correlated only because a human types on the keyboard while watching the monitor. Our goal is to learn this hidden human context (i.e., the human-object relationships), and also use it as a cue for labeling the scenes. We present Infinite Factored Topic Model (IFTM), where we consider a scene as being generated from two types of topics: human configurations and human-object relationships. This enables our algorithm to hallucinate the possible configurations of the humans in the scene parsimoniously. Given only a dataset of scenes containing objects but not humans, we show that our algorithm can recover the human object relationships. We then test our algorithm on the task of attribute and object labeling in 3D scenes and show consistent improvements over the state-of-the-art.Keywords
This publication has 14 references indexed in Scilit:
- Learning human activities and object affordances from RGB-D videosThe International Journal of Robotics Research, 2013
- 3D-Based Reasoning with Blocks, Support, and StabilityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Detecting activities of daily living in first-person camera viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Learning to place new objects in a sceneThe International Journal of Robotics Research, 2012
- Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- From 3D scene geometry to human workspacePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Modeling mutual context of object and human pose in human-object interaction activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Categorizing object-action relations from semantic scene graphsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Make3D: Learning 3D Scene Structure from a Single Still ImageIeee Transactions On Pattern Analysis and Machine Intelligence, 2008
- Markov Chain Sampling Methods for Dirichlet Process Mixture ModelsJournal of Computational and Graphical Statistics, 2000