File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-01240-3_28
- Scopus: eid_2-s2.0-85055091260
- WOS: WOS:000594233000028
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Dividing and aggregating network for multi-view action recognition
Title | Dividing and aggregating network for multi-view action recognition |
---|---|
Authors | |
Keywords | Dividing and Aggregating Network Large-scale action recognition Multi-view action recognition |
Issue Date | 2018 |
Publisher | Springer |
Citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, et al. (Eds.), Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, p. 457-473. Cham, Switzerland: Springer, 2018 How to Cite? |
Abstract | In this paper, we propose a new Dividing and Aggregating Network (DA-Net) for multi-view action recognition. In our DA-Net, we learn view-independent representations shared by all views at lower layers, while we learn one view-specific representation for each view at higher layers. We then train view-specific action classifiers based on the view-specific representation for each view and a view classifier based on the shared representation at lower layers. The view classifier is used to predict how likely each video belongs to each view. Finally, the predicted view probabilities from multiple views are used as the weights when fusing the prediction scores of view-specific action classifiers. We also propose a new approach based on the conditional random field (CRF) formulation to pass message among view-specific representations from different branches to help each other. Comprehensive experiments on two benchmark datasets clearly demonstrate the effectiveness of our proposed DA-Net for multi-view action recognition. |
Persistent Identifier | http://hdl.handle.net/10722/321811 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science ; 11213 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Dongang | - |
dc.contributor.author | Ouyang, Wanli | - |
dc.contributor.author | Li, Wen | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:21:36Z | - |
dc.date.available | 2022-11-03T02:21:36Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, et al. (Eds.), Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, p. 457-473. Cham, Switzerland: Springer, 2018 | - |
dc.identifier.isbn | 9783030012397 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321811 | - |
dc.description.abstract | In this paper, we propose a new Dividing and Aggregating Network (DA-Net) for multi-view action recognition. In our DA-Net, we learn view-independent representations shared by all views at lower layers, while we learn one view-specific representation for each view at higher layers. We then train view-specific action classifiers based on the view-specific representation for each view and a view classifier based on the shared representation at lower layers. The view classifier is used to predict how likely each video belongs to each view. Finally, the predicted view probabilities from multiple views are used as the weights when fusing the prediction scores of view-specific action classifiers. We also propose a new approach based on the conditional random field (CRF) formulation to pass message among view-specific representations from different branches to help each other. Comprehensive experiments on two benchmark datasets clearly demonstrate the effectiveness of our proposed DA-Net for multi-view action recognition. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 11213 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | Dividing and Aggregating Network | - |
dc.subject | Large-scale action recognition | - |
dc.subject | Multi-view action recognition | - |
dc.title | Dividing and aggregating network for multi-view action recognition | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-030-01240-3_28 | - |
dc.identifier.scopus | eid_2-s2.0-85055091260 | - |
dc.identifier.spage | 457 | - |
dc.identifier.epage | 473 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000594233000028 | - |
dc.publisher.place | Cham, Switzerland | - |