DOAJ Open Access 2023

Dynamic deformable transformer for end‐to‐end face alignment

Liming Han Chi Yang Qing Li Bin Yao Zixian Jiao +1 lainnya

Abstrak

Abstract Heatmap‐based regression (HBR) methods have dominated for a long time in the face alignment field while these methods need complex design and post‐processing. In this study, the authors propose an end‐to‐end and simple enough coordinate‐based regression (CBR) method called Dynamic Deformable Transformer (DDT) for face alignment. Unlike general pre‐defined landmark queries, DDT uses Dynamic Landmark Queries (DLQs) to query landmarks' classes and coordinates together. Besides, DDT adopts a deformable attention mechanism rather than a regular attention mechanism which has a faster convergence speed and lower computational complexity. Experiment results on three mainstream datasets 300W, WFLW, and COFW demonstrate DDT exceeds the state‐of‐the‐art CBR methods by a large margin and is comparable to the current state‐of‐the‐art HBR methods with much less computational complexity.

Topik & Kata Kunci

Computer applications to medicine. Medical informatics Computer software

Penulis (6)

Liming Han

Chi Yang

Qing Li

Bin Yao

Zixian Jiao

Qianyang Xie

Format Sitasi

APA MLA BibTeX

Han, L., Yang, C., Li, Q., Yao, B., Jiao, Z., Xie, Q. (2023). Dynamic deformable transformer for end‐to‐end face alignment. https://doi.org/10.1049/cvi2.12208

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1049/cvi2.12208

Informasi Jurnal

Tahun Terbit: 2023
Sumber Database: DOAJ
DOI: 10.1049/cvi2.12208
Akses: Open Access ✓