高伟

职称:助理教授
电话:0755-26033202
办公室:A214
Email:gaowei262@pku.edu.cn
实验室网站:
研究方向:1、多媒体编码;2、多媒体处理;3、深度学习与人工智能。
职称 助理教授 电话 0755-26033202
办公室 A214 Email gaowei262@pku.edu.cn
研究方向 1、多媒体编码;2、多媒体处理;3、深度学习与人工智能。 实验室网站

​导师与研究领域、方向:

高伟,博士,北京大学信息工程学院助理教授/副研究员/博士生导师,IEEE高级会员,深圳市海外高层次人才。香港城市大学计算机科学博士,曾在美国加州大学洛杉矶分校(UCLA)做访问学者,曾在香港城市大学和新加坡南洋理工大学做博士后研究,曾在CMOS图像传感器制造商OmniVision Technologies公司担任图像信号处理器ASIC芯片设计工程师。研究方向为沉浸式与3D视觉媒体信息处理技术(点云、光场、全景、多视点/双目3D等),主要研究兴趣包括:(1)多媒体编码与处理:点云与视频编码、深度学习智能编码;三维点云处理与分析,以及沉浸式与3D视觉媒体的感知质量评价、视觉注意机制与显著性分割、复原增强、3D目标检测等;(2)深度学习与人工智能:机器学习/深度学习与优化理论及应用、可解释性深度神经网络理论、人工智能中深度学习算法轻量化/结构搜索与软硬件加速。近年来主要科研成果发表在相关领域高水平国际IEEE Transactions期刊(如IEEE TIP、TCSVT、TMM、TCYB、TIM、TII等)和高水平国际会议(如CVPR、AAAI、ACM MM、DCC等)上60余篇,申请或授权美国/中国/PCT专利40余项,积极参与多媒体与人工智能技术的标准提案工作。

由于在3D沉浸式媒体方面的研究荣获ICME 2021多媒体学术新星奖(Multimedia Rising Star,全球仅4人获奖),荣获2021年CCF-腾讯犀牛鸟优秀专利奖、2020年和2019年连续两年的CCF-腾讯犀牛鸟基金(国际公开竞争性基金,科研基金全球遴选入选率12%)、2019年广东省计算机学会优秀论文一等奖(第1作者论文)。受邀担任四个多媒体计算与机器学习领域国际重要SCI期刊编委(Associate Editor),包括JCR一区期刊Signal Processing(Elsevier)、JCR二区期刊Neural Processing Letters(Springer)等,并同时是亚太信号与信息处理协会图像、视频与多媒体技术委员会(APSIPA IVM TC)委员。曾于ICME 2021会议上组织过交互式媒体视觉质量评价与感知建模研讨会(QoEIM Workshop)。国家自然科学基金、广东省与深圳市项目评审专家。担任多个国际顶级期刊IEEE TIP、TCSVT、TMM、TNNLS、TCYB等以及国际重要学术会议CVPR、ECCV、IJCAI等的审稿人,多个国际学术会议程序委员会委员与组织方等。课题组与腾讯多媒体实验室、腾讯图灵实验室和华为技术有限公司等有着密切的项目研发合作。课题组与鹏城实验室合作正在搭建和维护面向点云技术和视觉信息压缩的开源算法库,包括OpenPointCloud、OpenCompression和OpenVision。

课题组致力于提升沉浸式与3D视觉媒体的观看体验与工业应用,促进新兴与未来多媒体与视觉信息处理技术发展。欢迎优秀的本科生和硕士生保送和报考北京大学信息工程学院的硕士和博士研究生,同时欢迎申请课题组的博士后和访问职位,从事多媒体计算与人工智能相关热门与前沿课题的研究探索,更多最新信息请查看个人主页:https://gaowei262.github.io/。

作为项目负责人曾经或正在主持10余项国家级与省部级等重大/重要科研项目,科研经费充足。

近年来发表部分期刊和会议论文(20篇):

1. Wei Gao, Sam Kwong, and Yuheng Jia, “Joint Machine Learning and Game Theory for Rate Control in High Efficiency Video Coding,” IEEE Transactions on Image Processing (TIP), vol. 26, no. 12, pp. 6074-6089, December 2017.

2. Wei Gao, Sam Kwong, Yu Zhou, and Hui Yuan, “SSIM-Based Game Theory Approach for Rate-Distortion Optimized Intra Frame CTU-Level Bit Allocation,” IEEE Transactions on Multimedia (TMM), vol. 18, no. 6, pp. 988-999, June 2016.

3. Wei Gao, Sam Kwong, Hui Yuan, and Xu Wang, “DCT Coefficient Distribution Modeling and Quality Dependency Analysis Based Frame-Level Bit Allocation for HEVC,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 26, no. 1, pp. 139-153, January 2016.

4. Wei Gao, Sam Kwong, Qiuping Jiang, Chi-Keung Fong, Peter H. W. Wong, and Wilson Y. F. Yuen, “Data-Driven Rate Control for Rate-Distortion Optimization in HEVC Based on Simplified Effective Initial QP Learning,” IEEE Transactions on Broadcasting (TBC), vol. 65, no. 1, pp. 94-108, March 2019.

5. Wei Gao, Qiuping Jiang, Ronggang Wang, Siwei Ma, Ge Li, and Sam Kwong, “Consistent Quality Oriented Rate Control in HEVC via Balancing Intra and Inter Frame Coding,” IEEE Transactions on Industrial Informatics (TII), 2021.

6. Wei Gao, Guibiao Liao, Siwei Ma, Ge Li, Yongsheng Liang, and Weisi Lin, “Unified Information Fusion Network for Multi-Modal RGB-D and RGB-T Salient Object Detection,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.

7. Wenbo Zhao, Xianming Liu, Zhiwei Zhong, Junjun Jiang, Wei Gao, Ge Li, Xiangyang Ji, “Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), accepted in March 2022.

8. Xianghao Zang, Ge Li, Wei Gao, “Multi-dimension and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval,” IEEE Transactions on Industrial Informatics (TII), accepted in Feburary 2022.

9. Yang Guo, Wei Gao, Siwei Ma, Ge Li, “Accelerating Transform Algorithm Implementation for Efficient Intra Encoder of 8K UHD Videos,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), accepted in December 2021.

10. Chunyang Fu, Ge Li, Rui Song, Wei Gao, Shan Liu, “OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression,” AAAI Conference on Artificial Intelligence (AAAI), accepted in December 2021.

11. Zhenyu Peng, Qiuping Jiang, Feng Shao, Wei Gao, Weisi Lin, “LGGD+: Image Retargeting Quality Assessment by Measuring Local and Global Geometric Distortions,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), September 2021.

12. Fei Song, Yiting Shao, Wei Gao, Haiqiang Wang, and Thomas Li, “Layer-Wise Geometry Aggregation Framework for Lossless LiDAR Point Cloud Compression,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), July, 2021.

13. Zhuangzi Li, Ge Li, Thomas Li, Shan Liu, Wei Gao, “Information-Growth Attention Network for Image Super-Resolution,” ACM International Conference on Multimedia (ACM MM), Chengdu, China, October 20-24, 2021.

14. Yudong Mao, Qiuping Jiang, Runmin Cong, Wei Gao, Feng Shao, Sam Kwong, “Cross-modality Fusion and Progressive Integration Network for Saliency Prediction on Stereoscopic 3D Images,” IEEE Transactions on Multimedia (TMM), 2021.

15. Wei Gao, Linjie Zhou, and Lvfang Tao, “A Fast View Synthesis Implementation Method for Light Field Applications,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2021.

16. Qiuping Jiang, Wei Gao, Shiqi Wang, Guanghui Yue, Feng Shao, Yo-Sung Ho, Sam Kwong, “Blind Image Quality Measurement by Exploiting High Order Statistics with Deep Dictionary Encoding Network,” IEEE Transactions on Instrumentation and Measurement (TIM), vol. 69, no. 10, pp. 7398-7410, April 2020.

17. Guibiao Liao, Wei Gao, Qiuping Jiang, Ronggang Wang, Ge Li, “MMNet: Multi-Stage and Multi-Scale Fusion Network for RGB-D Salient Object Detection,” ACM International Conference on Multimedia (ACM MM), Seattle, WA, USA, pp. 2436–2444, October 2020.

18. Mingliang Zhou, Xuekai Wei, Shiqi Wang, Sam Kwong, Chi-Keung Fong, Peter H. W. Wong, Wilson Y. F. Yuen, and Wei Gao, “SSIM-Based Global Optimization for CTU-Level Rate Control in HEVC,” IEEE Transactions on Multimedia (TMM), vol. 21, no. 8, pp. 1921-1933, August 2019.

19. Qiuping Jiang, Feng Shao, Wei Gao, Zhuo Chen, Gangyi Jiang, and Yo-Sung Ho, “Unified No-reference Quality Assessment of Singly and Multiply Distorted Stereoscopic Images,” IEEE Transactions on Image Processing (TIP), vol. 28 , no. 4, pp. 1866-1881, April 2019.

20. Yuheng Jia, Sam Kwong, Wenhui Wu, Ran Wang, and Wei Gao, “Sparse Bayesian Learning Based Kernel Poisson Regression,” IEEE Transactions on Cybernetics (TCYB), vol. 49, no. 1, pp. 56-68, January 2019.

美国专利和PCT专利:

1. Systems and Methods for Rate Control in Video Coding using Joint Machine Learning and Game Theory, United States Patent, US10542262B2, Jan. 21, 2020.

2. Method for Initial Quantization Parameter Optimization in Video Coding, United States Patent, US10560696B2, Feb. 11, 2020.

3. Methods, Apparatus, and Computer Readable Storage Mediums for Determination of Neural Network Pruning, United States Patent, Filed in Dec. 9, 2021.

4. Methods, Apparatus, Devices, Mediums and Products for Object Detection Network Design, PCT International Patent, Filed in May 14, 2021.

5. 目标检测网络构建优化方法、装置、设备、介质及产品,PCT国际专利,PCT/CN2021/093911,2021年5月14日。

6. 基于压缩感知的神经网络模型压缩方法、设备及存储介质,PCT国际专利,WO2022000373A1,2020年7月1日。

7. 视频编码质量平滑度的优化方法、装置、设备及存储介质,PCT国际专利,WO2020042177A1, 2020年3月5日。

开设课程:

(近年来,为计算机应用技术专业研究生开设以下两门选修课程,受到同学们的欢迎。)

1. 《三维视觉与计算摄像学》(Fall Semester,选修)

2. 《现代视频处理专题》(Spring Semester,选修)

对计划招收的硕士和博士研究生的基本要求(点击查看招生要求):

1. 专业范围:计算机、电子信息、自动化等信息科学类专业的本科和硕士毕业生。

2. 外语/数学能力:英语六级。

3. 研究/开发能力:熟练的程序设计能力,具有一定的探索能力和创新精神。

4. 其他要求:对做科研工作有热情、有兴趣,自我驱动力强。