NEIL: Extracting Visual Knowledge from Web Data
- 1 December 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1409-1416
- https://doi.org/10.1109/iccv.2013.178
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.Keywords
This publication has 25 references indexed in Scilit:
- What makes Paris look like Paris?ACM Transactions on Graphics, 2012
- Augmented Attribute RepresentationsLecture Notes in Computer Science, 2012
- Relative attributesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Large-scale live active learning: Training object detectors with crawled data and crowdsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Clustering by Passing Messages Between Data PointsScience, 2007
- Animals on the WebPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIeee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Combining labeled and unlabeled data with co-trainingPublished by Association for Computing Machinery (ACM) ,1998