People : eric : publications

Articles and Conference Papers

Meyer, John and Cosatto, Eric and Graf, Hans Peter: Mitotic Index of Invasive Breast Carcinoma. Archives of Pathology and Laboratory Medicine (11) (2009)

Cadambi, Srihari and Durdanovic, Igor and Jakkula, Venkata and Sankaradass, Murugan and Cosatto, Eric and Chakradhar, Srimat and Graf, Hans Peter: A Massively Parallel FPGA Based Co-Processor for Support Vector Machines. Proc. Field Programmable Custom Computing Machines, FCCM (2009)

Meyer, John and Cosatto, Eric and Graf, Hans Peter: Mitotic Index of Breast Carcinoma: Understanding and Remedying Irreproducibility. US and Canadian Academy of Pathology, 2009 Annual Meeting (2009)

Sankaradass, Murugan and Jakkula, Venkata and Cadambi, Srihari and Durdanovic, Igor and Cosatto, Eric and Chakradhar, Srimat and Graf, Hans Peter: A Massively Parallel Coprocessor for Convolutional Neural Networks. Proc. Application-specific Systems, Architectures and Processors, ASAP 2009 (2009)

Cosatto, Eric and Miller, Matt and Graf, Hans Peter and Meyer, John: Grading Nuclear Pleomorphism on Histological Micrographs. Proc. Int. Conf. Pattern Recognition (2008)

Malon, Christopher and Miller, Matt and Burger, Christopher and Cosatto, Eric and Graf, Hans Peter: Identifying Histological Elements with Convolutional Neural Networks. Proc. ACM CSTST 2008 Workshop on Computational Intelligence in Medical Imaging (2008)

Graf, Hans Peter and Cadambi, Srihari and Durdanovic, Igor and Jakkula, Venkata and Sankardadass, Murugan and Cosatto, Eric and Chakradhar, Srimat: A Massively Parallel Digital Learning Processor. Advances in Neural Information Processing Systems (2008)

Durdanovic, I. and Cosatto, E. and Graf, H.P.: Large Scale Parallel SVM Implementation. Large Scale Kernel Machines (2007) (link)

LeCun, Y. and Muller, U. and Ben, J. and Cosatto, E. and Flepp, B.: Off-road obstacle avoidance through end-to-end learning. Advances in neural information processing systems (2006)

Graf, Hans Peter and Cosatto, Eric and Bottou, Léon and Durdanovic, Igor and Vapnik, Vladimir: Parallel Support Vector Machines: The Cascade SVM. Advances in Neural Information Processing Systems (2005) (link)

Cosatto, E. and Graf, H.P. and Ostermann, J.: From Audio-Only to Audio and Video Text-to-Speech. Acta Acustica united with Acustica (6) (2004)

Cosatto, E. and Ostermann, J. and Graf, H.P. and Schoeter, J.: Lifelike talking faces for interactive services. Proceedings of the IEEE (9) (2003)

Graf, HP and Cosatto, E. and Strom, V.: Visual prosody: facial movements accompanying speech. Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on (2002) (link)

Huang, F.J. and Cosatto, E. and Graf, HP: Triphone based unit selection for concatenative visual speechsynthesis. Acoustics, Speech, and Signal Processing, 2002. Proceedings.(ICASSP'02). IEEE International Conference on (2002) (link)

Graf, H.P. and Cosatto, E.: Sample-Based Synthesis of Talking Heads. Proceedings of the IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS'01) (2001) (link)

Graf, Hans Peter and Cosatto, Eric: Sample-Based Synthesis of Talking Heads. Proc. Int. 2nd Workshop on Recognition, Analysis and Tracking of Faces and Gestures in Realtime (2001)

Syrdal, A.K. and Ostermann, J. and Cosatto, E. and Graf, H.P.: Recent advances in audio and video text-to-speech synthesis. The Journal of the Acoustical Society of America (2001)

Basso, Andrea and Graf, Hans Peter and Gibbon, David and Cosatto, Eric and Liu, S.: Virtual Light: Digitally Generated Light for Video Conferencing. Image Processing, 2001. Proceedings. 2001 International Conference on (2001) (link)

Cosatto, E. and Graf, HP: Photo-realistic talking-heads from image samples. Multimedia, IEEE Transactions on (3) (2000) (link)

Graf, Hans Peter and Cosatto, Eric and Ezzat, Tony: Face analysis for the synthesis of photo-realistic talking heads. Proc. Fourth IEEE Int. Conf. Automatic Face and Gesture Recognition (2000) (link)

Schroeter, J. and Ostermann, J. and Graf, HP and Beutnagel, M. and Cosatto, E. and Syrdal, A. and Conkie, A. and Stylianou, Y.: MULTIMODAL SPEECH SYNTHESIS. Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on (2000) (link)

Cosatto, E. and Potamianos, G. and Graf, HP: Audio-visual unit selection for the synthesis of photo-realistictalking-heads. Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on (2000) (link)

Potamianos, G. and Graf, HP and Cosatto, E.: An image transform approach for HMM based automatic lipreading. Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on (1998) (link)

Graf, H.P. and Cosatto, E. and Potamianos, G.: Machine Vision of Faces and Facial Features. Proc. The 2nd R.I.E.C. Int. Symposium on Design and Architectures of Information Processing Systems Based on the Brain Information Principle (1998)

Cosatto, E. and Graf, H.P.: Sample-Based Synthesis of Photo-Realistic Talking Heads. Proc. Computer Animation'98 (1998)

Cosatto, E. and Graf, HP: Sample-based synthesis of photo-realistic talking heads. Computer Animation 98. Proceedings (1998) (link)

Potamianos, G. and Cosatto, E. and Graf, H.P. and Roe, D.B.: Speaker independent audio-visual database for bimodal ASR. Proc. AVSP’97 (1997)

Graf, HP and Cosatto, E. and Potamianos, M.: Robust recognition of faces and facial features with a multi-modalsystem. Systems, Man, and Cybernetics, 1997.'Computational Cybernetics and Simulation'., 1997 IEEE International Conference on (1997) (link)

Cosatto, E. and Graf, HP: A high speed image understanding system. Adaptive Analog VLSI Neural Systems (1996)

Graf, H.P. and Cosatto, E. and Gibbon, D. and Kocheisen, M. and Petajan, E.: Multi-Modal System for Locating Heads and Faces. Proc. Second Int’l Conf. Automatic Face and Gesture Recognition (1996) (link)

Cloutier, J. and Cosatto, E. and Pigeon, S. and Boyer, F. and Simard, P.: VIP: an FPGA-based processor for image processing and neural networks. Proc. MicroNeuro (1996) (link)

Cosatto, E. and Graf, H.P.: A Robust High Speed Image Understanding System. Adaptive Analogue VLSI Neural Systems (1996)

Graf, H.P. and Burges, C.J.C. and Cosatto, E. and Nohl, C.R.: Analysis of Complex and Noisy Check Images. Proc. IEEE Int. Conf. Image Processing (1995) (link)

Jackel, L. and Battista, M. and Baird, H. and Ben, J. and Bromley, J. and Burges, C. and Cosatto, E. and Denker, J. and Graf, H.P. and Katseff, H. and LeCun, Y. and Nohl, C. and Sackinger, E. and Shamilian, J. and Shoemaker, T. and Stenard, C. and Strom, I. and Ting, R. and Wood, T. and Zuraw, C.: Neural-net applications in character recognition and document analysis. Neural-Net Applications in Telecommunications (1995)

Cosatto, E. and Graf, HP: A neural network accelerator for image analysis. Micro, IEEE (3) (1995) (link)

Graf, H.P. and Chen, T. and Petajan, E. and Cosatto, E.: Locating Faces and Facial Parts. Proc. First Int’l Workshop Automatic Face and Gesture Recognition (1995)

Cosatto, E. and Graf, HP: NET32K high speed image understanding system. Microelectronics for Neural Networks and Fuzzy Systems, 1994., Proceedings of the Fourth International Conference on (1994) (link)

Cosatto, E. and Graf, HP: NET32K high speed image understanding system. Microelectronics for Neural Networks and Fuzzy Systems, Proceedings of the Fourth International Conference on (1994) (link)

Graf, H.P. and Cosatto, E.: Address Block Location with a Neural Net System. Neural Information Processing Systems (1994)

Theses

Cosatto, E.: Sample-Based Talking-Head Synthesis. PhD Thesis, Signal Processing Lab, Swiss Federal Institute of Techology, Lausanne, Switzerland (2002) (link)

Patents

Graf, H.P. and Cosatto, E. and Schroeter, J.: Caoarticulation Method for Audio-Visual Text-to-Speech Synthesis. USA (7,630,897) (December 8, 2009)

Graf, H.P. and Cosatto, E. and Ostermann, J.: System for low-latency animation of talking heads. USA (7,627,478) (December 1, 2009)

Graf, H.P. and Cosatto, E. and Durdanovic, I. and Vladimir, V.: Spread Kernel Support Vector Machine. USA (7,406,450) (July 29, 2008)

Graf, H.P. and Cosatto, E. and Schroeter, J.: Coarticulation Method for Audio-Visual Text-to-Speech Synthesis. USA (7,392,190) (June 24, 2008)

Graf, H.P. and Cosatto, E. and Huang, F.J.: System and Method for Triphone-Based Unit Selection for Visual Speech Synthesis. USA (7,369,992) (May 6, 2008)

Graf, H.P. and Cosatto, E. and Isaacson, T. and Strom, V.F..: System and Method of Providing Conversational Visual Prosody for Talking Heads. USA (7,353,177) (April 1, 2008)

Graf, H.P. and Basso, A. and Cosatto, E. and Gibbon, D. and Liu, S.: Digitally Generated Lighting for Video Conferencing Applications. USA (7,231,099) (June 12, 2007)

Graf, H.P. and Ostermann, J. and Buda, B. and Civanlar, M.R. and Cosatto, E. and Isaacson, T.M., and LeCun, Y.A.: Method for sending multi-media messages using customizable background images. USA (7,177,811) (February 13, 2007)

Graf, H.P. and Cosatto, E. and Huang, F.J.: System and method for triphone-based unit selection for visual speech synthesis. USA (7,209,882) (April 24, 2007)

Graf, H.P. and Cosatto, E. and Ostermann, J.: System for low-latency animation of talking heads. USA (7,260,539) (August 21, 2007)

Graf, H.P. and Cosatto, E. and Isaacson, T. and Strom, V.: System and Method of Providing Conversational Visual Prosody for Talking Heads. USA (7,076,430) (July 11, 2006)

Graf, H.P. and Cosatto, E. and Strom, V.: System and method of providing conversational visual prosody for talking heads. USA (7,136,818) (November 14, 2006)

Graf, H.P. and Ostermann, J. and Civanlar, M.R. and Cosatto, E. and Lecun, Y.: Method for sending multi-media messages using emoticons. USA (6,990,452) (January 24, 2006)

Graf, H.P. and Ostermann, J. and Buda, B. and Civanlar, M.R. and Cosatto, E. and Isaacson, T. and Lecun, Y.: Method for sending multi-media messages using Customizable Background Images. USA (7,035,803) (April 25, 2006)

Graf, H.P. and Cosatto, E. and Schroeter, J.: Coarticulation Method for Audio-Visual Text-to-Speech Synthesis. USA (7,117,155) (October 3, 2006)

Graf, H.P. and Basso, A. and Cosatto, E. and Gibbon, D. and Liu, S.: Digitally-generated lighting for video conferencing applications. USA (6,980,697) (December 27, 2005)

Graf, H.P. and Cosatto, E. and Schroeter, J.: Coarticulation method for audio-visual text-to-speech synthesis. USA (6,662,161) (December 9, 2003)

Graf, H.P. and Cosatto, E. and Potamianos, G. and Schroeter, J.: Audio-visual selection process for the synthesis of photo-realistic talking-head animations. USA (6,654,018) (November 25, 2003)

Graf, H.P. and Cosatto, E.: Method Of Modeling Objects To Synthesize Three-Dimensional Photo-Realistic Animations. USA (6,504,546) (January 7, 2003)

Graf, H.P. and Cosatto, E. and Schroeter, J.: Coarticulation Method for Audio-Visual Text-to-Speech Synthesis. USA (6,112,177) (August 29, 2000)

Graf, H.P. and Cosatto, E. and Potamianos, G.: Robust Multi-Modal Method for Recognizing Objects. USA (6,118,887) (September 12, 2000)

Graf, H.P. and Cosatto, E.: Method for generating photo-realistic animated characters. USA (5,995,119) (Nov. 30, 1999)

Graf, H.P. and Cosatto, E.: Multi-modal system for locating objects in images. USA (5,864,630) (Jan. 26, 1999)

Graf, H.P. and Burges, C. and Cosatto, E.: Method of image enhancement using convolution kernels. USA (5,647,027) (July 8, 1997)