File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2014.184
- Scopus: eid_2-s2.0-84906493570
- WOS: WOS:000361555601059
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Recognizing RGB images by learning from RGB-D data
Title | Recognizing RGB images by learning from RGB-D data |
---|---|
Authors | |
Keywords | domain adaptation gender recognition object recognition RGB-D transfer learning |
Issue Date | 2014 |
Citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 1418-1425 How to Cite? |
Abstract | In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images. We formulate this task as a new unsupervised domain adaptation (UDA) problem, in which we aim to take advantage of the additional depth features in the source domain and also cope with the data distribution mismatch between the source and target domains. To effectively utilize the additional depth features, we seek two optimal projection matrices to map the samples from both domains into a common space by preserving as much as possible the correlations between the visual features and depth features. To effectively employ the training samples from the source domain for learning the target classifier, we reduce the data distribution mismatch by minimizing the Maximum Mean Discrepancy (MMD) criterion, which compares the data distributions for each type of feature in the common space. Based on the above two motivations, we propose a new SVM based objective function to simultaneously learn the two projection matrices and the optimal target classifier in order to well separate the source samples from different classes when using each type of feature in the common space. An efficient alternating optimization algorithm is developed to solve our new objective function. Comprehensive experiments for object recognition and gender recognition demonstrate the effectiveness of our proposed approach for recognizing RGB images by learning from RGB-D data. |
Persistent Identifier | http://hdl.handle.net/10722/321611 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Lin | - |
dc.contributor.author | Li, Wen | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:20:13Z | - |
dc.date.available | 2022-11-03T02:20:13Z | - |
dc.date.issued | 2014 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, p. 1418-1425 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321611 | - |
dc.description.abstract | In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images. We formulate this task as a new unsupervised domain adaptation (UDA) problem, in which we aim to take advantage of the additional depth features in the source domain and also cope with the data distribution mismatch between the source and target domains. To effectively utilize the additional depth features, we seek two optimal projection matrices to map the samples from both domains into a common space by preserving as much as possible the correlations between the visual features and depth features. To effectively employ the training samples from the source domain for learning the target classifier, we reduce the data distribution mismatch by minimizing the Maximum Mean Discrepancy (MMD) criterion, which compares the data distributions for each type of feature in the common space. Based on the above two motivations, we propose a new SVM based objective function to simultaneously learn the two projection matrices and the optimal target classifier in order to well separate the source samples from different classes when using each type of feature in the common space. An efficient alternating optimization algorithm is developed to solve our new objective function. Comprehensive experiments for object recognition and gender recognition demonstrate the effectiveness of our proposed approach for recognizing RGB images by learning from RGB-D data. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.subject | domain adaptation | - |
dc.subject | gender recognition | - |
dc.subject | object recognition | - |
dc.subject | RGB-D | - |
dc.subject | transfer learning | - |
dc.title | Recognizing RGB images by learning from RGB-D data | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2014.184 | - |
dc.identifier.scopus | eid_2-s2.0-84906493570 | - |
dc.identifier.spage | 1418 | - |
dc.identifier.epage | 1425 | - |
dc.identifier.isi | WOS:000361555601059 | - |