计算机科学与技术系

Department of Computer Science and Technology

Education background

Bachelor of Electrical Engineering, Tsinghua University, Beijing, China, 1992;

Master of Electrical Engineering, Tsinghua University, Beijing, China, 1994;

Ph.D. in Electrical Engineering, Tsinghua University, Beijing, China, 1996;

Postdoctoral Staff Research Associate, University of California, Los Angeles, USA, 1996-1998.

Social service

IEEE: Senior Member;

IEEE Trans. Circuit and Systems for Video Technology: Associate Editor;

IEEE CAS Society Visual Signal Processing and Communications: Member of Technical Committee;

Chinese Audio Video Standards: Co-Chair of Ad-Hoc Group on Copyright Protection;

ICME, ICIP, ICC, and Globecom: Member of Technical Program Committee;

ISO, MPEG, ITU, VCEG, and US NCITS: Member;

IEEE Trans. on Video Coding and Image Processing, Trans. on Image Processing, IEEE Intl. Data Compression Conference, and IEEE Intl. Conference on Image Processing: Reviewer.

Areas of Research Interests/ Research Projects

Multimedia Communication over Hostile Networks, Video Coding and Communications

Sensor Technologies (including Image Sensors, Imagers and Sensor Networks)

Digital Rights Management, Network Security

UCLA-Samsung Multimedia Project: Simulations of the Application of Reversible Variable Length Codes (RVLCs) for Efficient and Robust Coding of Motion Vectors in H.263+ (1997-1998);

PacketVideo Corp.: MPEG-4-Compliant Encoder, Decoder, and QoS Servers (1998-2002);

Ortiva Wireless: Multimedia Content Adaptation Technology for Wireless Delivery (2006-2008)

Huawei Corp.: Wireless Multimedia Research Project (2010-2011);

Tencent Corp.: Multimedia Coding Technology (2010-2011).

Research Status

From 1996 to 1998, I was a Staff Research Fellow at UCLA, where I conducted cutting-edge research on multimedia coding and communications. Many of my inventions were later adopted by international standards such as H.263, MPEG and H.264. After UCLA, I served as the Principal Scientist of PacketVideo Corp., the CTO of Morphbius Technology Inc., the Director of Video Codec Technologies of Mobilygen Corp, the Senior Director of Technology of Ortiva Wireless and consulted for Stretch Inc. and Ocarina Networks. Since 2009, I have held a Professorship at the Department of Computer Science and Technology of Tsinghua University, where I am also the Director of the Research Center of the Internet of Things. I have also been a Visiting Fellow at Princeton University since 2010.

I am a world-renowned expert in multimedia communication over hostile networks, video coding and communications. I have authored many widely referenced papers in related fields. Products deploying technologies that I developed are currently widely used worldwide. I hold over 30 patents with numerous others pending. I am Senior Member of IEEE, and Associate Editor for IEEE Transactions CSVT.

Honors And Awards

IEEE Transactions on Circuits and Systems for Video Technology: Best Paper Award (2010);

IEEE Circuits and Systems Society: Certifacate of Appreciation (2009);

Emmy Award Nomination (2008);

EE Times ACE Award for Most Promising Technology (2006);

Consumer Electronics Show (CES): Technology Innovation Award (2000);

Red Herring's Top 50 Private Companies in the World (2000);

PacketVideo Corp.: PVCreator Award (2001).

Academic Achievement

[1] Yi Pang, Lifeng Sun, Jiangtao (Gene) Wen*, Fengyan Zhang, Weidong Hu, Wei Feng and Shiqiang Yang, "A framework for heuristic scheduling for parallel processing on multi-core architecture - a case study with multi-view video coding (MVC)", IEEE Trans. Circuits and Systems for Video Technology, Vol.19, No. 11, pp. 1658-1666, Nov. 2009. 

[2] Hyungjin Kim, Jiangtao Wen, John Villasenor, "Secure arithmetic coding", IEEE Trans. Signal Processing, Vol. 55, No. 5, pp. 2263-2272, 2007.

[3] Jiangtao Wen, Hyungjin Kim, John Villasenor, "Binary arithmetic coding with key-based interval splitting", IEEE Signal Processing Letters, Vol. 13, No. 2, Feb. 2006.

[4] Ming Jia, Jiangtao Wen, Shaozhi Ye, Xing Li, "Error restricted fast MAP decoding of VLC", IEEE Communications Letters, Vol.9, No.10, pp. 909-911, Oct. 2005.

[5] Wenjun Zeng, Jiangtao Wen, "3G wireless multimedia: technologies and practical issues", Journal of Wireless Communications and Mobile Computing, Special Issue on Multimedia over Mobile IP, Vol. 2, Issue 6, pp. 563-572, 2002.

[6] Jiangtao Wen, Wenjun Zeng, Mike Severa, "A format compliant configurable encryption framework for access control of video", IEEE Trans. Circuits and Systems for Video Technology, Special Issue on Wireless Video, Vol. 12, No.6, pp. 545-557, June 2002.

[7] Jiangtao Wen, John Villasenor, "Soft-input soft-output decoding of variable length codes". IEEE Transactions on Communications, Vol. 50, No. 5, pp. 689-692, May 2002.

[8] Jiangtao Wen, Max Luttrell, John Villasenor, "Trellis-based R-D optimal quantization in H.263+". IEEE Transactions on Image Processing, pp. 1431 - 1434, Aug. 2000.

[9] Yao Wang, Stephan Wenger, Jiangtao Wen, Aggelos K. Katsaggelos, "Error resilient video coding techniques". IEEE Signal Processing Magazine, pp. 61-82, July 2000.

[10] John Villasenor, Ya-Qin Zhang, Jiangtao Wen, "Robust video coding algorithms and systems". Proceedings of the IEEE, Vol. 87, No. 10, pp. 1724-1733, Oct. 1999.

[11] Jiangtao Wen, John Villasenor, "Structured prefix codes for quantized generalized Gaussian sources". IEEE Trans. on Information Theory, pp. 1307 - 1314, May 1999.

[12] Thomas Stockhammer, Jiangtao Wen , "3GPP Video Services - Video Codecs, Content Delivery Protocols, and Optimization Potentials", appeared as a chapter in Video and Multimedia Transmission over Cellular Networks, John Wiley & Sons, 2009.

[13] Avni Rambhia, Jiangtao Wen, Spencer Cheng, "ContentMorphing: A Novel System for Broadcast Delivery of Personalizable Content". Appeared as a chapter in Personalization And Interactivity In Future TV, Kluwer Academic Publishers, 2004.

[14] John Villasenor, Jiangtao Wen, "Low-Complexity Compression of Run Length Coded Image Subbands". Appeared as a chapter in Wavelet Image and Video Compression, Pankaj Topiwala Ed., Springer-Verlag, 1998.

[15] Xuan Dong, Yi Pang, Jiangtao Wen,"Fast efficient algorithm for enhancement of low lighting video", SIGGRAPH 2010 Poster, Los Angeles, CA, July 27-29, 2010.

[16] Jiangtao Wen, Zhuoyuan Chen, Yuxing Han, John Villasenor, Shiqiang Yang, "Reconstruction of sparse binary signals using compressive sensing", Proc. 2010 IEEE Data Compression Conference, Snowbird, UT, March, 2010.

[17] Jiangtao Wen, Mou Xiao, Jianwen Chen, Pin Tao, "Fast rate-distortion quantization for H.264/AVC, " Proc. 2010 IEEE Data Compression Conference, Snowbird, UT, March, 2010.

[18] Zhuoyuan Chen, Jiangtao Wen, Yuxing Han, John Villasenor, Shiqiang Yang, "A compressive sensing image compression algorithm using quantized DCT and noiselet information," Proc. IEEE ICASSP 2010, Dallas, March 2010.

[19] Yi Pang, Jiangtao Wen, Lifeng Sun, Weidong Hu, Shiqiang Yang, "Frame-level heuristic scheduling of multi-view video coding on symmetric multi-core architecture", Proc. 2009 IEEE International Conference on Image Processing, Cairo, Egypt, Nov. 2009.

[20] Jiangtao Wen, Yuxing Han, John Villasenor, "Entropy coding using equiprobable partitioning", 46th Annual Allerton Conference, October 23-26, 2008.

[21] Hyungjin Kim, Jiangtao Wen, John Villasenor, "Permutation based secure arithmetic coding", 2006 Picture Coding Symposium", April 22-24, 2006.

[22] Jiangtao Wen, Rui Zhang, "Efficient entropy coding with lexicographical indexing", 2006 Picture Coding Symposium", April 22-24, 2006.

[23] Jiangtao Wen, Hyungjin Kim, John Villasenor, "Secure arithmetic coding using interval splitting", Proc. 39th Asilomar Conf. On Signals, Systems and Computers, Asilomar, CA, Nov. 2005.

[24] Yali Liu, Jiangtao Wen, "Heuristic search based soft-input soft-output decoding of arithmetic codes", Proc. 2004 IEEE Data Compression Conference, Snowbird, UT, March 2004.

[25] Wenjun Zeng, Jiangtao Wen, Mike Severa, "Fast self-synchronous content scrambling by spatially shuffling codewords of compressed bitstreams", Proc. 2002 IEEE International Conference on Image Processing, Rochester, New York, Sept. 2002.

[26] Wenjun Zeng, Jiangtao Wen, "3G wireless multimedia: technologies and practical issues", Special Session on Wireless Imaging, Proc. 2002 IEEE International Conference on Image Processing, Rochester, New York, Sept. 2002.

[27] Jiangtao Wen, Mike Severa, Wenjun Zeng, Max Luttrell, Weiyin Jin, "A configurable framework for format compliant encryption of multimedia." Proc. IEEE International Workshop on Multimedia Signal Processing, Nice, France, Oct. 2001.

[28] Jiangtao Wen, Max Luttrell, Mike Severa, "Access control of standard video bitstreams". Proc. International Conference on Media Futures, May 8-9, Florence, Italy, 2001.

[29] Max Luttrell, Jiangtao Wen, John Villasenor, "Trellis-based R-D optimal quantization in H.263+". IEEE International Conference on Image Processing, Sept. 10 - 13, Vancouver, Canada, 2000.

[30] Jiangtao Wen, John Villasenor, "Utilizing soft information in decoding of variable length codes", Proc. of IEEE 1999 Data Compression Conference, pp. 131 - 139. Snowbird, UT, March 1999.

[31] Jiangtao Wen, John Villasenor, "Reversible variable length codes for efficient and robust image and video coding". Proc. of IEEE 1998 Data Compression Conference, Snowbird, UT, March 1998.

[32] Jiangtao Wen, John Villasenor, "Reversible variable length codes for robust image and video transmission". Proc. 1997 Asilomar Conference, Pacific Groove, CA, Nov. 1997.

[33] Jiangtao Wen, John Villasenor, "A class of reversible variable length codes for robust image and video coding". Proc. 1997 IEEE International Conference on Image Processing, Santa Barbara, CA, Oct. 1997.

[34] Nickolay Pakoulin, Alexander Monakhob, Chunyen Cheng, Jiangtao Wen, "Enhancing IPMP-2 for conformance", AVS document 1487, 2004.

[35] Spencer Cheng, Gene Wen, Nickolay Pakoulin, Vitaly Omelchenko, Alexander Koptelov, Alexandre Petrenko, Alexander Kossatchev, "Improving MPEG-21 IPMP conformance - experience from MPEG-2/4 IPMPX", ISO/IEC JTC1/SC29/WG11 M10874, MPEG-04.

[36] Jiangtao Wen, Chunyen Cheng, "ContentMorphing: user directed content adaptation", AVS document M1030, 2002.

[37] Gene Wen, Wenjun Zeng, David Kosiba, Mike Severa, "A Configurable Message Format for Selective Encryption Tools", ISO/IEC JTC1/SC29/WG11 M7216, MPEG-01.

[38] Gene Wen, Wenjun Zeng, David Kosiba, Mike Severa, "A Format-compliant configurable Encryption Framework for Access Control of Multimedia", ISO/IEC JTC1/SC29/WG11 M7213, MPEG-01.

[39] Gene Wen, Wenjun Zeng, David Kosiba, Mike Severa, "Rationale for Format-compliant Configurable Selective Encryption in IPMP Standardization", ISO/IEC JTC1/SC29/WG11 M7212, MPEG-01.

[40] Bruce Chaplin, Gene Wen, "Rationale for IPMP Profiles with Standardized Encryption Tools", ISO/IEC JTC1/SC29/WG11 M7151, MPEG-01.

[41] Adam Li, Jiangtao Wen, John Villasenor, J.H. Park, "Model implementation of error resilience mode in H.263+ code." ITU-T document Q15-E19. Presented at the ITU meeting at Whistler, British Columbia, Canada, July 1998.

[42] Adam Li, Matthew Fong, Jiangtao Wen, John Villasenor, J.H. Park, "Test results of error resilience with modified error resilient syntax with data partitioning and RVLC." ITU-T document Q15-E20. Presented at the ITU meeting at Whistler, British Columbia, Canada, July 1998.

[43] Max Luttrell, Jiangtao Wen, John Villasenor, J.H. Park, "Simulation results for adaptive quantization using trellis based R-D information." ITU-T document Q15-E21. Presented at the ITU meeting at Whistler, British Columbia, Canada, July 1998.

[44] Jiangtao Wen, Gregg Kamosa, John Villasenor, J.H. Park, "Simulation results for proposed segmented error resilient mode for H.26L." ITU-T document Q15-D37. Presented at the ITU meeting at Tampere, Finland, April 1998.

[45] Jiangtao Wen, Max Luttrell, John Villasenor, J.H. Park, "Simulation results on trellis based adaptive quantization." ITU-T document Q15-D40. Presented at the ITU meeting at Tampere, Finland, April 1998.

[46] Jiangtao Wen, John Villasenor, Raj Talluri, "Report of results on core experiment E8 with single thread motion vector prediction." ISO/IEC JTC1/SC29/WG11 M2968, MPEG-98.

[47] Jiangtao Wen, John Villasenor, H.D. Shin, "Proposal for single-thread motion vector prediction in H.263L", ITU-T document Q15-C35. Presented at the ITU meeting at Eibsee, Germany, Dec. 1997.

[48] Jiangtao Wen, John Villasenor, H.D Shin, "Proposal for error resilience in H.263L", ITU-T document Q15-C36. Presented at the ITU meeting at Eibsee, Germany, Dec. 1997.

[49] Gregg Kamosa, Jiangtao Wen, John Villasenor, H.D Shin, "Proposal for motion dependent COD syntax". ITU-T document Q15-C-37. Presented at the ITU meeting at Eibsee, Germany, Dec. 1997.

[50] Torbjorn Einarsson, Jiangtao Wen, John Villasenor, "Proposal for longer motion vectors in H.263+", ITU-T document Q15-B-21. The proposal was adopted at the ITU meeting at Sunriver, OR in Sept. 1997, and it is now the new Annex D of H.263+.

[51] Jiangtao Wen, John Villasenor, Yashoda Nag, Raj Talluri, "Report of results on core experiment on error resilience for motion data with strucutred RVLC-E8", ISO/IEC JTC1/SC29/WG11 M2382