1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/45CU66B |
Repository | sid.inpe.br/sibgrapi/2021/09.06.18.15 |
Last Update | 2021:09.06.18.15.01 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.06.18.15.01 |
Metadata Last Update | 2022:09.10.00.16.17 (UTC) administrator |
Citation Key | MaiaVieiPedr:2021:ViRhCo |
Title | Visual rhythm-based convolutional neural networks and adaptive fusion for a multi-stream architecture applied to human action recognition |
Format | On-line |
Year | 2021 |
Access Date | 2024, Apr. 29 |
Number of Files | 1 |
Size | 939 KiB |
|
2. Context | |
Author | 1 Maia, Helena de Almeida 2 Vieira, Marcelo Bernardes 3 Pedrini, Helio |
Affiliation | 1 UNICAMP 2 UFJF 3 UNICAMP |
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 | helena.maia@ic.unicamp.br |
Conference Name | Conference on Graphics, Patterns and Images, 34 (SIBGRAPI) |
Conference Location | Gramado, RS, Brazil (virtual) |
Date | 18-22 Oct. 2021 |
Publisher | Sociedade Brasileira de Computação |
Publisher City | Porto Alegre |
Book Title | Proceedings |
Tertiary Type | Master's or Doctoral Work |
History (UTC) | 2021-09-06 18:28:31 :: helena.maia@ic.unicamp.br -> administrator :: 2021 2022-09-10 00:16:17 :: administrator -> :: 2021 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | action recognition visual rhythm multi-stream architecture |
Abstract | In this work, we address the problem of human action recognition in videos. We propose and analyze a multi-stream architecture containing image-based networks pre-trained on the large ImageNet. Different image representations are extracted from the videos to feed the streams, in order to provide complementary information for the system. Here, we propose new streams based on visual rhythm that encodes longer-term information when compared to still frames and optical flow. Our main contribution is a stream based on a new variant of the visual rhythm called Learnable Visual Rhythm (LVR) formed by the outputs of a deep network. The features are collected at multiple depths to enable the analysis of different abstraction levels. This strategy significantly outperforms the handcrafted version on the UCF101 and HMDB51 datasets. We also investigate many combinations of the streams to identify the modalities that better complement each other. Experiments conducted on the two datasets show that our multi-stream network achieved competitive results compared to state-of-the-art approaches. |
Arrangement | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Visual rhythm-based convolutional... |
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/45CU66B |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45CU66B |
Language | en |
Target File | camera_ready.pdf |
User Group | helena.maia@ic.unicamp.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/45PQ3RS |
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 documentstage doi 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 versiontype volume |
|