dc.citation.conferencePlace |
US |
- |
dc.citation.conferencePlace |
Montreal |
- |
dc.citation.endPage |
279 |
- |
dc.citation.startPage |
271 |
- |
dc.citation.title |
28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 |
- |
dc.contributor.author |
Hwang, Sung Ju |
- |
dc.contributor.author |
Sigal, Leonid |
- |
dc.date.accessioned |
2023-12-19T23:06:47Z |
- |
dc.date.available |
2023-12-19T23:06:47Z |
- |
dc.date.created |
2015-08-04 |
- |
dc.date.issued |
2014-12-08 |
- |
dc.description.abstract |
We propose a method that learns a discriminative yet semantic space for object categorization, where we also embed auxiliary semantic entities such as supercat-egories and attributes. Contrary to prior work, which only utilized them as side information, we explicitly embed these semantic entities into the same space where we embed categories, which enables us to represent a category as their linear combination. By exploiting such a unified model for semantics, we enforce each category to be generated as a supercategory + a sparse combination of attributes, with an additional exclusive regularization to learn discriminative composition. The proposed reconstructive regularization guides the discriminative learning process to learn a model with better generalization. This model also generates compact semantic description of each category, which enhances interoperability and enables humans to analyze what has been learned. |
- |
dc.identifier.bibliographicCitation |
28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, pp.271 - 279 |
- |
dc.identifier.issn |
1049-5258 |
- |
dc.identifier.scopusid |
2-s2.0-84937837455 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/46677 |
- |
dc.identifier.url |
http://www.scopus.com/record/display.url?eid=2-s2.0-84937837455&origin=resultslist&sort=plf-f&src=s&st1=A+Unified+Semantic+Embedding%3a+Relating+Taxonomies+and+Attributes&st2=&sid=0E564388E569D971376D666F2CB629AE.euC1gMODexYlPkQec4u1Q%3a1630&sot=b&sdt=b&sl=79&s=TITLE-ABS-KEY%28A+Unified+Semantic+Embedding%3a+Relating+Taxonomies+and+Attributes%29&relpos=0&relpos=0&citeCnt=0&searchTerm=TITLE-ABS-KEY%28A+Unified+Semantic+Embedding%3A+Relating+Taxonomies+and+Attributes%29 |
- |
dc.language |
영어 |
- |
dc.publisher |
Neural Information Processing Systems |
- |
dc.title |
A Unified Semantic Embedding: Relating Taxonomies and Attributes |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2014-12-08 |
- |