Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electrical and Electronic Engineering | en_US |
| dc.contributor.advisor | Lam, Kin-man Kenneth (EEE) | en_US |
| dc.creator | Qian, Zhiya | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13744 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Facial expression recognition using attention mechanism | en_US |
| dcterms.abstract | Facial expression recognition (FER) is a long-standing and challenging problem in human face analysis, holding considerable potential across diverse domains such as human-machine interaction, medical monitoring, fatigue detection, etc. Current approaches addressing facial expression recognition often employ a cross-attention mechanism, either by directly learning facial features through Transformer architectures or by applying attention mechanisms solely within the context of loss functions. While these strategies yield reasonable results, attention-based FER methods still have room for enhancement in terms of face feature extraction and classification. To improve recognition accuracy, we propose an innovative method, incorporating an enhanced facial feature encoder, multi-scale modeling, and cross-attention-based feature fusion. Comparative evaluations against baseline methods on four benchmark datasets reveal the superiority of our method, both quantitatively and qualitatively, manifesting an absolute performance improvement exceeding 1.34%. Notably, our method exhibits robust training efficiency, necessitating fewer training epochs to achieve convergence. Extensive ablation studies demonstrate the efficacy of our architectural designs. | en_US |
| dcterms.extent | 44 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2023 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Human face recognition (Computer science) | en_US |
| dcterms.LCSH | Image analysis -- Data processing | en_US |
| dcterms.LCSH | Image processing -- Digital techniques | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8261.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 11.66 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/13744