File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-319-10602-1_29
- Scopus: eid_2-s2.0-84906486177
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Exploiting privileged information from web data for image categorization
Title | Exploiting privileged information from web data for image categorization |
---|---|
Authors | |
Keywords | domain adaptation learning using privileged information multi-instance learning |
Issue Date | 2014 |
Publisher | Springer |
Citation | 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 6-12 September 2014. In Fleet, D, Pajdla, T, Schiele, B, et al. (Eds.), Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, p. 437-452. Cham: Springer, 2014 How to Cite? |
Abstract | Relevant and irrelevant web images collected by tag-based image retrieval have been employed as loosely labeled training data for learning SVM classifiers for image categorization by only using the visual features. In this work, we propose a new image categorization method by incorporating the textual features extracted from the surrounding textual descriptions (tags, captions, categories, etc.) as privileged information and simultaneously coping with noise in the loose labels of training web images. When the training and test samples come from different datasets, our proposed method can be further extended to reduce the data distribution mismatch by adding a regularizer based on the Maximum Mean Discrepancy (MMD) criterion. Our comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed methods for image categorization and image retrieval by exploiting privileged information from web data. © 2014 Springer International Publishing. |
Persistent Identifier | http://hdl.handle.net/10722/321609 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
Series/Report no. | Lecture Notes in Computer Science ; 8693 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Wen | - |
dc.contributor.author | Niu, Li | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:20:12Z | - |
dc.date.available | 2022-11-03T02:20:12Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 6-12 September 2014. In Fleet, D, Pajdla, T, Schiele, B, et al. (Eds.), Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, p. 437-452. Cham: Springer, 2014 | - |
dc.identifier.isbn | 9783319106014 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321609 | - |
dc.description.abstract | Relevant and irrelevant web images collected by tag-based image retrieval have been employed as loosely labeled training data for learning SVM classifiers for image categorization by only using the visual features. In this work, we propose a new image categorization method by incorporating the textual features extracted from the surrounding textual descriptions (tags, captions, categories, etc.) as privileged information and simultaneously coping with noise in the loose labels of training web images. When the training and test samples come from different datasets, our proposed method can be further extended to reduce the data distribution mismatch by adding a regularizer based on the Maximum Mean Discrepancy (MMD) criterion. Our comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed methods for image categorization and image retrieval by exploiting privileged information from web data. © 2014 Springer International Publishing. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 8693 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | domain adaptation | - |
dc.subject | learning using privileged information | - |
dc.subject | multi-instance learning | - |
dc.title | Exploiting privileged information from web data for image categorization | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-319-10602-1_29 | - |
dc.identifier.scopus | eid_2-s2.0-84906486177 | - |
dc.identifier.spage | 437 | - |
dc.identifier.epage | 452 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.publisher.place | Cham | - |