• Publications
  • Influence
Pruning Filters for Efficient ConvNets
The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning andExpand
  • 1,172
  • 255
  • PDF
Parallel Support Vector Machines: The Cascade SVM
We describe an algorithm for support vector machines (SVM) that can be parallelized efficiently and scales to very large problems with hundreds of thousands of training vectors. Instead of analyzingExpand
  • 432
  • 55
  • PDF
An image transform approach for HMM based automatic lipreading
This paper concentrates on the visual front end for hidden Markov model based automatic lipreading. Two approaches for extracting features relevant to lipreading, given image sequences of theExpand
  • 206
  • 22
  • PDF
Neural Network Recognizer for Hand-Written Zip Code Digits
This paper describes the construction of a system that recognizes handprinted digits, using a combination of classical techniques and neural-net methods. The system has been trained and tested onExpand
  • 118
  • 18
  • PDF
Photo-Realistic Talking-Heads from Image Samples
This paper describes a system for creating a photo-realistic model of the human head that can be animated and lip-synched from phonetic transcripts of text. Combined with a state-of-the-artExpand
  • 129
  • 13
  • PDF
Visual prosody: facial movements accompanying speech
As we articulate speech, we usually move the head and exhibit various facial expressions. This visual aspect of speech aids understanding and helps communicating additional information, such as theExpand
  • 189
  • 11
  • PDF
A Massively Parallel Coprocessor for Convolutional Neural Networks
We present a massively parallel coprocessor for accelerating Convolutional Neural Networks (CNNs), a class of important machine learning algorithms. The coprocessor functional units, consisting ofExpand
  • 171
  • 10
Discriminative training of HMM stream exponents for audio-visual speech recognition
  • G. Potamianos, H. Graf
  • Computer Science
  • Proceedings of the IEEE International Conference…
  • 12 May 1998
We propose the use of discriminative training by means of the generalized probabilistic descent (GPB) algorithm to estimate hidden Markov model (HMM) stream exponents for audio-visual speechExpand
  • 143
  • 9
A programmable parallel accelerator for learning and classification
For learning and classification workloads that operate on large amounts of unstructured data with stringent performance constraints, general purpose processor performance scales poorly with dataExpand
  • 79
  • 9
  • PDF
A Massively Parallel FPGA-Based Coprocessor for Support Vector Machines
We present a massively parallel FPGA-based coprocessor for Support Vector Machines (SVMs), a machine learning algorithm whose applications include recognition tasks such as learning scenes,Expand
  • 71
  • 8
  • PDF