Results 1 - 10 of 320

Neural Network-Based Face Detection

by Henry A. Rowley, Shumeet Baluja, Takeo Kanade - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 1998
"... We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present ..."
Abstract - Cited by 1206 (22 self) - Add to MetaCart
We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present

Learning Long-Term Dependencies with Gradient Descent is Difficult

by Yoshua Bengio, Patrice Simard, Paolo Frasconi - TO APPEAR IN THE SPECIAL ISSUE ON RECURRENT NETWORKS OF THE IEEE TRANSACTIONS ON NEURAL NETWORKS
"... Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in th ..."
Abstract - Cited by 389 (37 self) - Add to MetaCart
Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present

Touring protein fold space with DALI/FSSP

by Liisa Holm, Chris S - Nucleic Acids Res , 1998
"... The FSSP database and its new supplement, the Dali Domain Dictionary, present a continuously updated classification of all known 3D protein structures. The classification is derived using an automatic structure alignment program (Dali) for the all-against-all comparison of structures in the Protein ..."
Abstract - Cited by 188 (0 self) - Add to MetaCart
are decomposed into structural domains based on the recurrence of structural motifs; (iii) folds are defined as tight clusters of domains in fold space. The fold classification, domain definitions and test sets for sequence-structure alignment (threading) are accessible on the web at www

Speech recognition with deep recurrent neural networks

by Alex Graves, Abdel-rahman Mohamed, Geoffrey Hinton , 2013
"... Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the L ..."
Abstract - Cited by 104 (8 self) - Add to MetaCart
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods

M (2003) Active wavelet networks for face alignment

by Changbo Hu, Rogerio Feris, Matthew Turk - In: Proceedings of British machine vision conference
"... The active appearance model (AAM) algorithm has proved to be a successful method for face alignment and synthesis. By elegantly combining both shape and texture models, AAM allows fast and robust deformable image matching. However, the method is sensitive to partial occlusions and illumination chang ..."
Abstract - Cited by 19 (3 self) - Add to MetaCart
changes. In such cases, the PCA-based texture model causes the reconstruction error to be globally spread over the image. In this paper, we propose a new method for face alignment called active wavelet networks (AWN), which replaces the AAM texture model by a wavelet network representation. Since we

Recurrent Neural Networks for Word Alignment Model

by Akihiro Tamura, Taro Watanabe, Eiichiro Sumita
"... This study proposes a word alignment model based on a recurrent neural net-work (RNN), in which an unlimited alignment history is represented by re-currently connected hidden layers. We perform unsupervised learning using noise-contrastive estimation (Gutmann and Hyvärinen, 2010; Mnih and Teh, 2012 ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
This study proposes a word alignment model based on a recurrent neural net-work (RNN), in which an unlimited alignment history is represented by re-currently connected hidden layers. We perform unsupervised learning using noise-contrastive estimation (Gutmann and Hyvärinen, 2010; Mnih and Teh

Robust Face Alignment Based On Hierarchical Classifier Network

by Li Zhang, Haizhou Ai, Shihong Lao - Proc. ECCV Workshop Human-Computer Interaction , 2006
"... Abstract. Robust face alignment is crucial for many face processing applications. As face detection only gives a rough estimation of face region, one important problem is how to align facial shapes starting from this rough estimation, especially on face images with expression and pose changes. We pr ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
propose a novel method of face alignment by building a hierarchical classifier network, connecting face detection and face alignment into a smooth coarse-to-fine procedure. Classifiers are trained to recognize feature textures in different scales from entire face to local patterns. A multi-layer structure

Exploiting the Past and the Future in Protein Secondary Structure Prediction

by Pierre Baldi, Søren Brunak, Paolo Frasconi, Giovanni Soda, Gianluca Pollastri , 1999
"... Motivation: Predicting the secondary structure of a protein (alpha-helix, beta-sheet, coil) is an important step towards elucidating its three dimensional structure, as well as its function. Presently, the best predictors are based on machine learning approaches, in particular neural network archite ..."
Abstract - Cited by 154 (30 self) - Add to MetaCart
to make predictions based on variable ranges of dependencies. These architectures extend recurrent neural networks, introducing non-causal bidirectional dynamics to capture both upstream and downstream information. The prediction algorithm is completed by the use of mixtures of estimators that leverage

L.: Deepface: Closing the gap to human-level performance in face verification

by Yaniv Taigman, Ming Yang, Lior Wolf - In: IEEE CVPR , 2014
"... In modern face recognition, the conventional pipeline consists of four stages: detect ⇒ align ⇒ represent ⇒ clas-sify. We revisit both the alignment step and the representa-tion step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face represe ..."
Abstract - Cited by 103 (4 self) - Add to MetaCart
In modern face recognition, the conventional pipeline consists of four stages: detect ⇒ align ⇒ represent ⇒ clas-sify. We revisit both the alignment step and the representa-tion step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face

Supervised sequence labelling with recurrent neural networks

by Alex Graves , 2008
"... Recurrent neural networks are powerful sequence learners. They are able to incorporate context information in a flexible way, and are robust to localised distortions of the input data. These properties make them well suited to sequence labelling, where input sequences are transcribed with streams ..."
Abstract - Cited by 59 (6 self) - Add to MetaCart
networks in general, and long short-term memory in particular. Its two main contributions are (1) a new type of output layer that allows recurrent networks to be trained directly for sequence labelling tasks where the alignment between the inputs and the labels is unknown, and (2) an extension of long
Results 1 - 10 of 320