1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPAW/3PF6LMS |
Repository | sid.inpe.br/sibgrapi/2017/08.17.15.31 |
Last Update | 2017:08.17.15.31.46 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2017/08.17.15.31.46 |
Metadata Last Update | 2022:06.14.00.08.44 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2017.13 |
Citation Key | CaetanoMeloSantSchw:2017:AcReBa |
Title | Activity Recognition based on a Magnitude-Orientation Stream Network |
Format | On-line |
Year | 2017 |
Access Date | 2024, Oct. 08 |
Number of Files | 1 |
Size | 1018 KiB |
|
2. Context | |
Author | 1 Caetano, Carlos 2 Melo, Victor H. C. de 3 Santos, Jefersson A. dos 4 Schwartz, William Robson |
Affiliation | 1 Universidade Federal de Minas Gerais 2 Universidade Federal de Minas Gerais 3 Universidade Federal de Minas Gerais 4 Universidade Federal de Minas Gerais |
Editor | Torchelsen, Rafael Piccin Nascimento, Erickson Rangel do Panozzo, Daniele Liu, Zicheng Farias, Mylène Viera, Thales Sacht, Leonardo Ferreira, Nivan Comba, João Luiz Dihl Hirata, Nina Schiavon Porto, Marcelo Vital, Creto Pagot, Christian Azambuja Petronetto, Fabiano Clua, Esteban Cardeal, Flávio |
e-Mail Address | carlos.caetano@dcc.ufmg.br |
Conference Name | Conference on Graphics, Patterns and Images, 30 (SIBGRAPI) |
Conference Location | Niterói, RJ, Brazil |
Date | 17-20 Oct. 2017 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2017-08-17 15:31:46 :: carlos.caetano@dcc.ufmg.br -> administrator :: 2022-06-14 00:08:44 :: administrator -> :: 2017 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | Magnitude Orientation Stream Network Convolutional Neural Networks |
Abstract | The temporal component of videos provides an important clue for activity recognition, as a number of activities can be reliably recognized based on the motion information. In view of that, this work proposes a novel temporal stream for two-stream convolutional networks based on images computed from the optical flow magnitude and orientation, named Magnitude-Orientation Stream (MOS), to learn the motion in a better and richer manner. Our method applies simple nonlinear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Experimental results, carried on two well-known datasets (HMDB51 and UCF101), demonstrate that using our proposed temporal stream as input to existing neural network architectures can improve their performance for activity recognition. Results demonstrate that our temporal stream provides complementary information able to improve the classical two-stream methods, indicating the suitability of our approach to be used as a temporal video representation. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2017 > Activity Recognition based... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Activity Recognition based... |
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/8JMKD3MGPAW/3PF6LMS |
zipped data URL | http://urlib.net/zip/8JMKD3MGPAW/3PF6LMS |
Language | en |
Target File | main Certified by IEEE PDF eXpress.pdf |
User Group | carlos.caetano@dcc.ufmg.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 | 8JMKD3MGPAW/3PKCC58 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2017/09.12.13.04 33 sid.inpe.br/sibgrapi/2022/06.10.21.49 3 sid.inpe.br/banon/2001/03.30.15.38.24 1 |
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 |
|