1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/45CQUPS |
Repository | sid.inpe.br/sibgrapi/2021/09.06.00.58 |
Last Update | 2021:09.06.00.58.09 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.06.00.58.09 |
Metadata Last Update | 2022:06.14.00.00.27 (UTC) administrator |
DOI | 10.1109/SIBGRAPI54419.2021.00063 |
Citation Key | AlmeidaPerValAlmPed:2021:ReLeIm |
Title | Representation Learning for Image Retrieval through 3D CNN and Manifold Ranking |
Format | On-line |
Year | 2021 |
Access Date | 2024, May 06 |
Number of Files | 1 |
Size | 4754 KiB |
|
2. Context | |
Author | 1 Almeida, Lucas Barbosa de 2 Pereira-Ferrero, Vanessa Helena 3 Valem, Lucas Pascotti 4 Almeida, Jurandy 5 Pedronette, Daniel Carlos Guimarães |
Affiliation | 1 UNESP 2 UNESP 3 UNESP 4 UNIFESP 5 UNESP |
Editor | Paiva, Afonso Menotti, David Baranoski, Gladimir V. G. Proença, Hugo Pedro Junior, Antonio Lopes Apolinario Papa, João Paulo Pagliosa, Paulo dos Santos, Thiago Oliveira e Sá, Asla Medeiros da Silveira, Thiago Lopes Trugillo Brazil, Emilio Vital Ponti, Moacir A. Fernandes, Leandro A. F. Avila, Sandra |
e-Mail Address | barbosa.almeida@unesp.br |
Conference Name | Conference on Graphics, Patterns and Images, 34 (SIBGRAPI) |
Conference Location | Gramado, RS, Brazil (virtual) |
Date | 18-22 Oct. 2021 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2021-09-06 00:58:09 :: barbosa.almeida@unesp.br -> administrator :: 2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021 2022-03-02 13:19:18 :: menottid@gmail.com -> administrator :: 2021 2022-06-14 00:00:27 :: administrator -> :: 2021 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | image retrieval representation learning manifold learning |
Abstract | Despite of the substantial success of Convolutional Neural Networks (CNNs) on many recognition and representation tasks, such models are very reliant on huge amount of data to allow effective training. In order to improve the generalization ability of CNNs, several approaches have been proposed, including variations of data augmentation strategies. With the goal of achieving more effective retrieval results on unsupervised learning scenarios, we propose a representation learning approach which exploits a rank-based formulation to build a more comprehensive data representation. The proposed model uses 2D and 3D CNNs trained by transfer learning and fuse both representations through a rank-based formulation based on manifold learning algorithms. Our approach was evaluated on an unsupervised image retrieval scenario applied to action recognition datasets. The experimental results indicated that significant effectiveness gains can be obtained on various datasets, reaching +56.93% of relative gains on MAP scores. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Representation Learning for... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Representation Learning for... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPEW34M/45CQUPS |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45CQUPS |
Language | en |
Target File | SIBGRAPI_2021_Camera_Ready.pdf |
User Group | barbosa.almeida@unesp.br |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/45PQ3RS 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2021/11.12.11.46 4 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume |
|