Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Akshay Asthana"'
Publikováno v:
2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a589a9748ebf82147c39ff3498d5bab7
https://doi.org/10.1109/fg52635.2021.9667072
https://doi.org/10.1109/fg52635.2021.9667072
Publikováno v:
International Journal of Computer Vision
Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94490b0d89ead9a1e2505bc700954e7a
https://doi.org/10.1007/s11263-017-0999-5
https://doi.org/10.1007/s11263-017-0999-5
Publikováno v:
FG
In this paper, a bi-directional long-short term memory (LSTM) based approach is proposed for the estimation of missing body parts in a human pose estimation context. Accurate human pose estimation is often a key component for accurate human action an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::016834817831f32f21ad5cd99a32c0f6
https://doi.org/10.1109/fg.2019.8756597
https://doi.org/10.1109/fg.2019.8756597
Publikováno v:
WACV
Facial fiducial detection is a challenging problem for several reasons like varying pose, appearance, expression, partial occlusion and others. In the past, several approaches like mixture of trees [32], regression based methods [8], exemplar based m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7847d8df5199f31cafcd42f3ac85a29b
https://doi.org/10.1109/wacv.2016.7477592
https://doi.org/10.1109/wacv.2016.7477592
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. 18:1511-1519
The issue of transferring facial performance from one person's face to another's has been an area of interest for the movie industry and the computer graphics community for quite some time. In recent years, deformable face models, such as the Active
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fb8e3e2b1c73d202d468d04962ee854
https://doi.org/10.1109/tvcg.2011.157
https://doi.org/10.1109/tvcg.2011.157
Publikováno v:
Pattern Recognition. 44:2598-2613
A major drawback of statistical models of non-rigid, deformable objects, such as the active appearance model (AAM), is the required pseudo-dense annotation of landmark points for every training image. We propose a regression-based approach for automa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8237dd3a7f3a8ea24360a1b096bb9f2
https://doi.org/10.1016/j.patcog.2011.03.014
https://doi.org/10.1016/j.patcog.2011.03.014
Publikováno v:
ICPR
We propose a fully automatic learning-based multi-atlas approach to segment the prostate using multi-channel (T1 and T2) MR images. After affine transformation to the template space, multi-scale features are extracted and separate random forest class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::511708c2356ed460b3da74b830f7b72f
https://doi.org/10.1109/icpr.2014.568
https://doi.org/10.1109/icpr.2014.568
Publikováno v:
Medical Imaging: Image Processing
We propose a learning-based approach to segment the seminal vesicles (SV) via random forest classifiers. The proposed discriminative approach relies on the decision forest using high-dimensional multi-scale context-aware spatial, textual and descript
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dc9c426d91930d177c599bc43366da8
https://doi.org/10.1117/12.2043893
https://doi.org/10.1117/12.2043893
Publikováno v:
ICCV
An ideal approach to the problem of pose-invariant face recognition would handle continuous pose variations, would not be database specific, and would achieve high accuracy without any manual intervention. Most of the existing approaches fail to matc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f552e837e488dc093d2bc10a8b4d032
https://doi.org/10.1109/iccv.2011.6126336
https://doi.org/10.1109/iccv.2011.6126336
Publikováno v:
FG
There are various scenarios where finding the most similar expression is the requirement rather than classifying one into discrete, pre-defined classes, for example, for facial expression transfer and facial expression based automatic album generatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04818872f8509678845fb26081a00875
https://doi.org/10.1109/fg.2011.5771354
https://doi.org/10.1109/fg.2011.5771354