File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3242969.3264978
- Scopus: eid_2-s2.0-85056662620
- WOS: WOS:000457913100089
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Video-based emotion recognition using deeply-supervised neural networks
Title | Video-based emotion recognition using deeply-supervised neural networks |
---|---|
Authors | |
Keywords | Convolutional Neural Network Deeply-Supervised Emotion Recognition EmotiW 2018 Challenge Side-output Layers |
Issue Date | 2018 |
Publisher | Association for Computing Machinery. |
Citation | Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI '18), Boulder, Colorado, USA, 16-20 October 2018, p. 584-588 How to Cite? |
Abstract | Emotion recognition (ER) based on natural facial images/videos has been studied for some years and considered a comparatively hot topic in the field of affective computing. However, it remains a challenge to perform ER in the wild, given the noises generated from head pose, face deformation, and illumination variation. To address this challenge, motivated by recent progress in Convolutional Neural Network (CNN), we develop a novel deeply supervised CNN (DSN) architecture, taking the multi-level and multi-scale features extracted from different convolutional layers to provide a more advanced representation of ER. By embedding a series of side-output layers, our DSN model provides class-wise supervision and integrates predictions from multiple layers. Finally, our team ranked 3rd at the EmotiW 2018 challenge with our model achieving an accuracy of 61.1%. |
Persistent Identifier | http://hdl.handle.net/10722/263544 |
ISBN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fan, Y | - |
dc.contributor.author | Lam, JCK | - |
dc.contributor.author | Li, VOK | - |
dc.date.accessioned | 2018-10-22T07:40:39Z | - |
dc.date.available | 2018-10-22T07:40:39Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI '18), Boulder, Colorado, USA, 16-20 October 2018, p. 584-588 | - |
dc.identifier.isbn | 978-1-4503-5692-3 | - |
dc.identifier.uri | http://hdl.handle.net/10722/263544 | - |
dc.description.abstract | Emotion recognition (ER) based on natural facial images/videos has been studied for some years and considered a comparatively hot topic in the field of affective computing. However, it remains a challenge to perform ER in the wild, given the noises generated from head pose, face deformation, and illumination variation. To address this challenge, motivated by recent progress in Convolutional Neural Network (CNN), we develop a novel deeply supervised CNN (DSN) architecture, taking the multi-level and multi-scale features extracted from different convolutional layers to provide a more advanced representation of ER. By embedding a series of side-output layers, our DSN model provides class-wise supervision and integrates predictions from multiple layers. Finally, our team ranked 3rd at the EmotiW 2018 challenge with our model achieving an accuracy of 61.1%. | - |
dc.language | eng | - |
dc.publisher | Association for Computing Machinery. | - |
dc.relation.ispartof | Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI 2018) | - |
dc.rights | Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI 2018). Copyright © Association for Computing Machinery. | - |
dc.subject | Convolutional Neural Network | - |
dc.subject | Deeply-Supervised | - |
dc.subject | Emotion Recognition | - |
dc.subject | EmotiW 2018 Challenge | - |
dc.subject | Side-output Layers | - |
dc.title | Video-based emotion recognition using deeply-supervised neural networks | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Fan, Y: yrfan@HKUCC-COM.hku.hk | - |
dc.identifier.email | Lam, JCK: h9992013@hkucc.hku.hk | - |
dc.identifier.email | Li, VOK: vli@eee.hku.hk | - |
dc.identifier.authority | Lam, JCK=rp00864 | - |
dc.identifier.authority | Li, VOK=rp00150 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3242969.3264978 | - |
dc.identifier.scopus | eid_2-s2.0-85056662620 | - |
dc.identifier.hkuros | 294322 | - |
dc.identifier.hkuros | 306539 | - |
dc.identifier.spage | 584 | - |
dc.identifier.epage | 588 | - |
dc.identifier.isi | WOS:000457913100089 | - |
dc.publisher.place | New York, NY | - |