NEIL: Extracting Visual Knowledge from Web Data

Citations Over TimeTop 1% of 2013 papers

Abstract

We propose NEIL (Never Ending Image Learner), a computer program that runs 24 hours per day and 7 days per week to automatically extract visual knowledge from Internet data. NEIL uses a semi-supervised learning algorithm that jointly discovers common sense relationships (e.g., "Corolla is a kind of/looks similar to Car", "Wheel is a part of Car") and labels instances of the given visual categories. It is an attempt to develop the world's largest visual structured knowledge base with minimum human labeling effort. As of 10th October 2013, NEIL has been continuously running for 2.5 months on 200 core cluster (more than 350K CPU hours) and has an ontology of 1152 object categories, 1034 scene categories and 87 attributes. During this period, NEIL has discovered more than 1700 relationships and has labeled more than 400K visual instances.

Related Papers

• → Recognition by functional parts [function-based object recognition(1994)17 cited
• → Object recognition using appearance models accumulated into environment(2002)12 cited
• → A method to check knowledge base consistency(1988)1 cited
• On the Base of Educational Knowledge(2012)
• → Visual Recognition of Object Categories and Object Arrangements Using You Only Look Once Framework(2017)