File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2015.2469286
- Scopus: eid_2-s2.0-84963829815
- WOS: WOS:000374164700007
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Learning Deep Representation for Face Alignment with Auxiliary Attributes
Title | Learning Deep Representation for Face Alignment with Auxiliary Attributes |
---|---|
Authors | |
Keywords | convolutional network deep learning Face Alignment face landmark detection |
Issue Date | 2016 |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, v. 38, n. 5, p. 918-930 How to Cite? |
Abstract | © 2015 IEEE. In this study, we show that landmark detection or face alignment task is not a single and independent problem. Instead, its robustness can be greatly improved with auxiliary information. Specifically, we jointly optimize landmark detection together with the recognition of heterogeneous but subtly correlated facial attributes, such as gender, expression, and appearance attributes. This is non-trivial since different attribute inference tasks have different learning difficulties and convergence rates. To address this problem, we formulate a novel tasks-constrained deep model, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Extensive evaluations show that the proposed task-constrained learning (i) outperforms existing face alignment methods, especially in dealing with faces with severe occlusion and pose variation, and (ii) reduces model complexity drastically compared to the state-of-the-art methods based on cascaded deep model. |
Persistent Identifier | http://hdl.handle.net/10722/273556 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Zhanpeng | - |
dc.contributor.author | Luo, Ping | - |
dc.contributor.author | Loy, Chen Change | - |
dc.contributor.author | Tang, Xiaoou | - |
dc.date.accessioned | 2019-08-12T09:55:56Z | - |
dc.date.available | 2019-08-12T09:55:56Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, v. 38, n. 5, p. 918-930 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/273556 | - |
dc.description.abstract | © 2015 IEEE. In this study, we show that landmark detection or face alignment task is not a single and independent problem. Instead, its robustness can be greatly improved with auxiliary information. Specifically, we jointly optimize landmark detection together with the recognition of heterogeneous but subtly correlated facial attributes, such as gender, expression, and appearance attributes. This is non-trivial since different attribute inference tasks have different learning difficulties and convergence rates. To address this problem, we formulate a novel tasks-constrained deep model, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Extensive evaluations show that the proposed task-constrained learning (i) outperforms existing face alignment methods, especially in dealing with faces with severe occlusion and pose variation, and (ii) reduces model complexity drastically compared to the state-of-the-art methods based on cascaded deep model. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.subject | convolutional network | - |
dc.subject | deep learning | - |
dc.subject | Face Alignment | - |
dc.subject | face landmark detection | - |
dc.title | Learning Deep Representation for Face Alignment with Auxiliary Attributes | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPAMI.2015.2469286 | - |
dc.identifier.scopus | eid_2-s2.0-84963829815 | - |
dc.identifier.volume | 38 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 918 | - |
dc.identifier.epage | 930 | - |
dc.identifier.isi | WOS:000374164700007 | - |
dc.identifier.issnl | 0162-8828 | - |