dc.citation.conferencePlace |
US |
- |
dc.citation.conferencePlace |
Providence |
- |
dc.citation.endPage |
1768 |
- |
dc.citation.startPage |
1761 |
- |
dc.citation.title |
IEEE Conference on Computer Vision and Pattern Recognition |
- |
dc.contributor.author |
Hwang, Sung Ju |
- |
dc.contributor.author |
Sha, Fei |
- |
dc.contributor.author |
Grauman, Kristen |
- |
dc.date.accessioned |
2023-12-20T03:06:17Z |
- |
dc.date.available |
2023-12-20T03:06:17Z |
- |
dc.date.created |
2015-08-13 |
- |
dc.date.issued |
2011-06-22 |
- |
dc.description.abstract |
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training. Rather than treat attributes as intermediate features, we consider how learning visual properties in concert with object categories can regularize the models for both. Given a low-level visual feature space together with attribute-and object-labeled image data, we learn a shared lower-dimensional representation by optimizing a joint loss function that favors common sparsity patterns across both types of prediction tasks. We adopt a recent kernelized formulation of convex multi-task feature learning, in which one alternates between learning the common features and learning task-specific classifier parameters on top of those features. In this way, our approach discovers any structure among the image descriptors that is relevant to both tasks, and allows the top-down semantics to restrict the hypothesis space of the ultimate object classifiers. We validate the approach on datasets of animals and outdoor scenes, and show significant improvements over traditional multi-class object classifiers and direct attribute prediction models. |
- |
dc.identifier.bibliographicCitation |
IEEE Conference on Computer Vision and Pattern Recognition, pp.1761 - 1768 |
- |
dc.identifier.doi |
10.1109/CVPR.2011.5995543 |
- |
dc.identifier.issn |
1063-6919 |
- |
dc.identifier.scopusid |
2-s2.0-80052908079 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/35737 |
- |
dc.identifier.url |
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5995543&tag=1 |
- |
dc.language |
영어 |
- |
dc.publisher |
IEEE, Computer Vision Society |
- |
dc.title |
Sharing Features between Objects and Their Attributes |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2011-06-20 |
- |