PUBLICATIONS


    PhD. Thesis


  1. Cosatto, E. "Sample-Based Talking-Head Synthesis" (US letter, color) (A4 b&w)”, Signal Processing Lab, Swiss Federal Institute of Techology, Lausanne, Switzerland, October 2002

    Book Chapters

  2. Cosatto, E. and Graf, H.P.,"A high speed image understanding system", in Adaptive Analog VLSI Neural Systems, Jabri, M. A., Coggins, R. J. and Flower, B. G. (Ed.), Chapman & Hall, 1996, pp. 201-222.
  3. Jackel, L., Battista, M., Baird, H., Ben, J., Bromley, J., Burges, C., Cosatto, E., Denker, J., Graf, H., Katseff, H., LeCun, Y., Noh, C., Sackinger, E., Shamilian, J., Shoemaker, T., Stenard, C., Strom, I., Ting, R., Wood, T. and Zuraw, C., "Neural-net applications in character recognition and document analysis", in Neural-Net Applications in Telecommunications, Kluwer Academic, 1995.

    Journals and Magazines

  4. Cosatto, E., Graf, H.P., Ostermann, J., Schroeter, J., Lifelike Talking Faces for Interactive Services, Proceedings of the IEEE, special issue on multimedia human computer interfaces, September 2003.
  5. Cosatto, E. and Graf, H. P., "Photo-realistic talking-heads from image samples", IEEE Trans. on Multimedia, vol. 2, no. 3, Sept. 2000, pp. 152-163.
  6. Cosatto, E. and Graf, H. P., "A neural network accelerator for image analysis", IEEE Micro, vol. 15, no. 3, IEEE Computer Society Press, June 1995, pp. 32-38.

    Conference Proceedings

  7. Graf, H.P., Cosatto E., Strom, V., Huang, F.J., "Visual Prosody; Facial Movements Accompanying Speech", FG 2002, May 2002
  8. Huang, F.J., Graf, H.P., Cosatto E., "Triphone-Based Unit Selection for Concatenative Visual Speech Synthesis", ICASSP 2002, May 2002
  9. Basso, A., Cosatto, E., Graf, H. P., Gibbon, D. and Liu, S., "Virtual light: Digitally-generated lighting for video conferencing applications", ICIP 2001, Oct. 2001
  10. Graf, H.P., Cosatto, E., "Sample-Based Synthesis of Talking-Heads", ICCV-RATFG-RTS, pp. 3-7
  11. Cosatto, E. and Graf, H. P., "Audio-visual unit selection for the synthesis of photo-realistic talking-heads", ICME 2000
  12. Schroeter, J., Graf, H.P., Beutnagel, M., Cosatto, E., Syrdal, A., Conkie, A., Stylianou, Y., "Multimodal speech synthesis", ICME 2000
  13. Graf, H. P., Cosatto, E. and Ezzat, T., "Face analysis for the synthesis of photo-realistic talking heads", FG 2000, pp. 189-194
  14. Cosatto, E. and Graf, H. P., "Sample-based synthesis of photo-realistic talking heads", Computer Animation 98, pp. 103-110
  15. Graf, H. P., Cosatto, E. and Potamianos, G., "Machine vision of faces and facial features", Proc. of the Second RIEC International Symp. on Design and Architecture of Information Processing Systems Based on the Brain Information Principle, 1998, pp. 48-53
  16. Potamianos, G., Graf, H. P. and Cosatto, E., "An image transform approach for HMM based automatic lipreading", ICIP 1998, pp. 173-177
  17. Graf, H. P., Cosatto, E. and Potamianos, G., "Robust recognition of faces and facial features with a multi-modal system", Proc. of the International Conf. on Systems, Man, and Cybernetics, pp. 2034-2039
  18. Potamianos, G., Cosatto, E., Graf, H. P. and Roe, D. B., "Speaker independent audio-visual database for bimodal ASR", Proceedings of the ESCA/ESCOP Workshop on Audio-Visual Speech Processing, September 1997, pp. 65-68
  19. Cloutier, J., Cosatto, E., Pigeon, S., Boyer F. and Simard S., "VIP: An FPGA-based Processor for Image Processing and Neural Networks", MicroNeuro 1996
  20. Graf, H. P., Cosatto, E., Gibbon, D., Kocheisen, M. and Petajan, E., "Multi-modal system for locating heads and faces", FG 1996, pp. 88-93
  21. Graf, H. P., Cosatto, E., Gibbon, D., Kocheisen, M. and Petajan, E., "Locating faces and facial parts", FG 1995, pp. 41-46
  22. Graf, H.P., Burges, C., Cosatto, E. and Nohl, C., "Analysis of complex and noisy check images", ICIP 1995, pp. 316-319
  23. Cosatto, E. and Graf, H.P., "NET32K high speed image understanding system", Microneuro 1994, pp. 413-421
  24. Graf, H.P. and Cosatto, E., "Address block location with a neural net system", NIPS 1994, pp 785-792

    Conference Abstracts

  25. Cosatto, E., Graf, H.P., "Synthetic Talking Heads with Sample-Based Graphics", Learning workshop, Snowbird, April 2001
  26. Graf, H.P., Cosatto, E., Potamianos, G., "Sample-Based 3D Computer Graphics", Learning workshop, Snowbird, April 1999
  27. Cosatto, E., Graf, H.P., "Synthesizing Photo-Realistic Talking-Heads from Local Views", Lifelike Computer Characters workshop, Snowbird, April 1998
  28. Graf, H.P., Cosatto, E., "Tracking Motion of Facial Features", Machines that learn workshop, Snowbird, April 1997
  29. Graf, H.P., Cosatto, E., "Computer Model of the Human Face", Lifelike Computer Characters workshop, Snowbird, April 1996
  30. Graf, H.P., Cosatto, E., Flowers, B., Chen, T., Petajan, E., "Locating and Recognizing Faces and Facial Parts", Machines that learn workshop, Snowbird, April 1995

PATENTS

    Issued

  1. Cosatto, E. and Graf, H. P., "Method of modeling objects to synthesize three-dimensional, photo-realistic animations", US Patent #6,504,546, 2002
  2. Cosatto, E., Graf, H. P. and Potamianos, G., "Robust multi-modal method for recognizing objects", US Patent #6,118,887, 2001
  3. Cosatto, E., Graf, H. P. and Schroeter, J., "Coarticulation method for audio-visual text-to-speech synthesis", US Patent #6,112,177, 2001
  4. Cosatto, E., Graf, H. P., "Method for generating photo-realistic animated characters", US Patent #5,995,119, 1999
  5. Graf, H. P. and Cosatto, E., "Multi-modal system for locating objects in images", US Patent #5,864,630, 1999
  6. Burges, C., Cosatto, E. and Graf, H. P., "Method of image enhancements using convolution kernels", US Patent #5,647,027, 1997

    Filed

  7. Cosatto, E., Graf, H. P., Huang, "System And Method For Triphone-Based Unit Selection For Visual Speech Synthesis", US Patent filed March 2002
  8. Ostermann, J., Cosatto, E., Graf, H.P., "System Method Of Providing Conversational Visual Prosody For Talking Heads", US Patent filed June 2002
  9. Cosatto, E., Graf, H. P., Potamianos, G. and Schroeter, J., "Audio-visual selection process for the synthesis of photo-realistic talking-head animations", US Patent filed March 2001
  10. Bottou, L., Cosatto, E., LeCun, Y., Mueller, U., "Virtual Light: Digitally-Generated Lighting For Video Conferencing Applications", US Patent filed February 2001
  11. Basso, A., Cosatto, E., Greenspan, S. L. and Weimer, D. M., "System and method for generating coded video sequences from still media", US Patent filed August 2000
  12. Bottou, L., Cosatto, E., LeCun, Y. and Muller, U., "System and method for controlling the delivery of mass messages", US Patent filed December 1999
  13. Potamianos, G., Graf, H. P. and Cosatto, E., "Speaker independent, image sequence transform based automatic speechreading", US Patent filed July 1998