Learning Object Permanence from Video
Authors:
Preprint
Abstract
Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since objects in natural visual scenes dynamically occlude and contain each-other. Intensive studies in developmental psychology suggest that object permanence is a challenging task that is learned through extensive experience. Here we introduce the setup of learning Object Permanence from data. We explain why this learning problem should be dissected into four components, where objects are (1) visible, (2) occluded, (3) contained by another object and (4) carried by a containing object. The fourth subtask, where a target object is carried by a containing object, is particularly challenging because it requires a system to reason about a moving location of an invisible object. We then present a unified deep architecture that learns to predict object location under these four scenarios. We evaluate the architecture and system on a new dataset based on CATER, and find that it outperforms previous localization methods and various baselines.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Video Captioning With Attention-Based LSTM and Semantic ConsistencyIEEE Transactions on Multimedia, 2017
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Visual Relationship Detection with Language Priors2016
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- The significance of event information for 6- to 16-month-old infants' perception of containment.Developmental Psychology, 2009
- 2.5-Month-Old Infants' Reasoning about When Objects Should and Should Not Be OccludedCognitive Psychology, 1999