Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions

Links to Files

https://www.ijcai.org/proceedings/2019/907

Permanent Link

https://doi.org/10.24963/ijcai.2019/907
 http://hdl.handle.net/11603/38686

Collections

UMBC Computer Science and Electrical Engineering Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-5593-2804

Date

2019

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Gokhale, Tejas. “Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions,” IJCAI, 2019, 6436–37. https://www.ijcai.org/proceedings/2019/907

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

Deep neural networks trained in an end-to-end fashion have brought about exceptional advances in computer vision, especially in computational perception. We go beyond perception and seek to enable vision modules to reason about perceived visual entities such as scenes, objects and actions. We introduce a challenging visual reasoning task, Image-Based Event Sequencing (IES) and compile the first IES dataset, Blocksworld Image Reasoning Dataset (BIRD). Motivated by the blocksworld concept, we propose a modular approach supported by literature in cognitive psychology and children’s development. We decompose the problem into two stages - visual perception and event sequencing, and show that our approach can be extended to natural images without re-training