Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Fu Jie Huang"'
Publikováno v:
ICDAR
The machine learning and pattern recognition communities are facing two challenges: solving the normalization problem, and solving the deep learning problem. The normalization problem is related to the difficulty of training probabilistic models over
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4b96deea250efe49b059da0ce4ea469
https://doi.org/10.1109/icdar.2007.4378728
https://doi.org/10.1109/icdar.2007.4378728
Publikováno v:
CVPR
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a feature-pooling layer t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c88ad8103281a90fe1e67672d0dbe75
https://doi.org/10.1109/cvpr.2007.383157
https://doi.org/10.1109/cvpr.2007.383157
Autor:
Yann LeCun, Fu Jie Huang
Publikováno v:
CVPR (1)
The detection and recognition of generic object categories with invariance to viewpoint, illumination, and clutter requires the combination of a feature extractor and a classifier. We show that architectures such as convolutional networks are good at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2ac15fdd58f1cf99baee3d00f3cc43bf
https://doi.org/10.1109/cvpr.2006.164
https://doi.org/10.1109/cvpr.2006.164
Publikováno v:
CVPR (2)
We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1beaf591111553d2d4679e5b7f64658b
https://doi.org/10.1109/cvpr.2004.1315150
https://doi.org/10.1109/cvpr.2004.1315150
Autor:
Fu Jie Huang, Tsuhan Chen
Publikováno v:
MMSP
In this demo, we present a technique for synthesizing the mouth movement from acoustic speech information. The algorithm maps the audio parameter set to the visual parameter set using the Gaussian mixture model and the hidden Markov model. With this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d17fff5934717689881e1fbb808d13b
https://doi.org/10.1109/mmsp.1998.738959
https://doi.org/10.1109/mmsp.1998.738959
Autor:
Tsuhan Chen, Fu Jie Huang
Publikováno v:
MMSP
We propose a method for integrating audio and visual information to enhance speech recognition in adverse environments. We train the audio hidden Markov model and the visual hidden Markov model separately, and then use a Viterbi algorithm to decode b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff2ccd3d8642ded033f5d37687980f0b
https://doi.org/10.1109/mmsp.2001.962800
https://doi.org/10.1109/mmsp.2001.962800
Autor:
Tsuhan Chen, Fu Jie Huang
Publikováno v:
IEEE International Conference on Multimedia and Expo (III)
Describes a real-time face-tracking algorithm. We start with single face tracking based on statistical color modeling and a deformable template. We then expand the algorithm to track multiple faces, possibly with occlusion, by constraining the speed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::784bcfa51f461a094e86223a83302a66
https://doi.org/10.1109/icme.2000.871067
https://doi.org/10.1109/icme.2000.871067
Publikováno v:
FG
We describe a novel neural network architecture, which can recognize human faces with any view in a certain viewing angle range (from left 30 degrees to right 30 degrees out of plane rotation). View-specific eigenface analysis is used as the front-en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4fb8e3e663d92fc79729bfd892ce11eb
https://doi.org/10.1109/afgr.2000.840642
https://doi.org/10.1109/afgr.2000.840642
Publikováno v:
ICASSP
Concatenative visual speech synthesis selects frames from a large recorded video database of mouth shapes to generate photo-realistic talking head sequences. The synthesized sequence must exhibit precise lip-sound synchronization and smooth articulat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7cab4b84af90d1669e1435a72088ee4
https://doi.org/10.1109/icassp.2002.5745033
https://doi.org/10.1109/icassp.2002.5745033
Publikováno v:
IEEE International Conference on Acoustics Speech and Signal Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70ce7b72c85ea420959510cabd24517a
https://doi.org/10.1109/icassp.2002.1006173
https://doi.org/10.1109/icassp.2002.1006173