NEIL: Extracting Visual Knowledge from Web Data


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… (More)
DOI: 10.1109/ICCV.2013.178
View Slides


7 Figures and Tables


Citations per Year

234 Citations

Semantic Scholar estimates that this publication has 234 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Chen2013NEILEV, title={NEIL: Extracting Visual Knowledge from Web Data}, author={Xinlei Chen and Abhinav Shrivastava and Abhinav Gupta}, journal={2013 IEEE International Conference on Computer Vision}, year={2013}, pages={1409-1416} }