Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing

Uložené v:

Podrobná bibliografia
Vydané v:	International Journal of Computer Vision Ročník 131; s. 1122 - 1140
Hlavní autori:	Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda
Médium:	Journal Article
Jazyk:	Japanese
Vydavateľské údaje:	Springer Science and Business Media LLC 12.01.2023
Predmet:	[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD] Audio and Speech Processing (eess.AS) Audio-visual speech enhancement Bayesian filtering Computer Science - Computer Vision and Pattern Recognition Computer Science - Sound Computer Vision and Pattern Recognition (cs.CV) Electrical Engineering and Systems Science - Audio and Speech Processing Face frontalization FOS: Computer and information sciences FOS: Electrical engineering, electronic engineering, information engineering Lip reading Robust point registration Sound (cs.SD) Student’s t-distribution Variational auto-encoders
ISSN:	0920-5691, 1573-1405
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
ISSN:	0920-5691 1573-1405
DOI:	10.48550/arxiv.2204.02810