File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3291124
- Scopus: eid_2-s2.0-85062460059
- WOS: WOS:000460376800007
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective
Title | Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective |
---|---|
Authors | |
Keywords | Cross-dataset recognition Domain adaptation |
Issue Date | 2019 |
Citation | ACM Computing Surveys, 2019, v. 52, n. 1, article no. 7 How to Cite? |
Abstract | This article takes a problem-oriented perspective and presents a comprehensive review of transfer-learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into 17 problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer-learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition but also the problems (e.g., 8 of the 17 problems) that have been scarcely studied. This survey not only presents an up-to-date technical review for researchers but also a systematic approach and a reference for a machine-learning practitioner to categorise a real problem and to look up for a possible solution accordingly. |
Persistent Identifier | http://hdl.handle.net/10722/321213 |
ISSN | 2023 Impact Factor: 23.8 2023 SCImago Journal Rankings: 6.280 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Jing | - |
dc.contributor.author | Li, Wanqing | - |
dc.contributor.author | Ogunbona, Philip | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:17:24Z | - |
dc.date.available | 2022-11-03T02:17:24Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | ACM Computing Surveys, 2019, v. 52, n. 1, article no. 7 | - |
dc.identifier.issn | 0360-0300 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321213 | - |
dc.description.abstract | This article takes a problem-oriented perspective and presents a comprehensive review of transfer-learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into 17 problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer-learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition but also the problems (e.g., 8 of the 17 problems) that have been scarcely studied. This survey not only presents an up-to-date technical review for researchers but also a systematic approach and a reference for a machine-learning practitioner to categorise a real problem and to look up for a possible solution accordingly. | - |
dc.language | eng | - |
dc.relation.ispartof | ACM Computing Surveys | - |
dc.subject | Cross-dataset recognition | - |
dc.subject | Domain adaptation | - |
dc.title | Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3291124 | - |
dc.identifier.scopus | eid_2-s2.0-85062460059 | - |
dc.identifier.volume | 52 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | article no. 7 | - |
dc.identifier.epage | article no. 7 | - |
dc.identifier.eissn | 1557-7341 | - |
dc.identifier.isi | WOS:000460376800007 | - |