Name
Abstract | ||
|---|---|---|
Entry level categories - the labels people will use to name an object - were originally defined and studied by psychologists in the 1980s. In this paper we study entry-level categories at a large scale and learn the first models for predicting entry-level categories for images. Our models combine visual recognition predictions with proxies for word "naturalness" mined from the enormous amounts of text on the web. We demonstrate the usefulness of our models for predicting nouns (entry-level words) associated with images by people. We also learn mappings between concepts predicted by existing visual recognition systems and entry-level concepts that could be useful for improving human-focused applications such as natural language image description or retrieval. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICCV.2013.344 | ICCV |
Keywords | Field | DocType |
entry-level concept,entry-level categories,visual recognition prediction,large scale image categorization,entry-level word,human-focused application,enormous amount,visual recognition system,entry level category,labels people,large scale,entry-level category,image retrieval,image recognition | Computer science,Naturalness,Noun,Image retrieval,Artificial intelligence,Natural language processing,Categorization,Computer vision,Automatic image annotation,Pattern recognition,Natural language,Entry Level,Visual Word | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
47 | 5.93 | 16 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vicente Ordonez | 1 | 1418 | 69.65 |
| Jia Deng | 2 | 10850 | 539.69 |
| Yejin Choi | 3 | 2239 | 153.18 |
| Alexander C. Berg | 4 | 10554 | 630.24 |
| Tamara L. Berg | 5 | 3221 | 225.32 |