代锋  副研究员  

研究方向:

所属部门:前瞻研究实验室

导师类别:博导计算机应用技术

联系方式:fdai@ict.ac.cn

个人网页:

简       历:

长期从事计算机视觉,视频图像分析与处理方向的研究工作,目前的研究兴趣为计算机视觉在智能农业领域的应用。作为负责人承担了国家重点研发计划课题,国家自然科学基金面上项目等多个国家项目。在IEEE T-MMIEEE T-CSVTIJCAI等国内外学术期刊和会议上发表论文70余篇,拥有授权发明专利10余项,长期担任IEEE T-CSVT, IEEE T-MM等国际期刊审稿人,IJCAI/AAAI等顶级国际会议PC Member。获得2011年多媒体旗舰会议ICME最佳论文候选,2018年中国多媒体大会最佳论文奖与杰出展示奖。2014年获北京市科学技术一等奖。

工作经历:

202112月 — 今:中国科学院计算技术研究所,博士生导师

20119月 — 今:中国科学院计算技术研究所,副研究员/硕士生导师

20087月 — 20119月:中国科学院计算技术研究所,助理研究员

学习经历:

20029月 — 20087月:中国科学院计算技术研究所,计算机应用,博士

19989月 — 20027月:清华大学,计算机科学与技术,本科

主要论著:

学术文章:

[1] Feng Dai; Bin Chen; Hang Xu; Yike Ma; Xiaodong Li; Bailan Feng; Peng Yuan; Chenggang Yan; Qiang Zhao*; Unbiased IoU for Spherical Image Object Detection, 36th AAAI Conference on Artificial Intelligence (AAAI 2022), Vancouver, BC, Canada. (CCF A类会议)

[2] Qiang Zhao; Yike Ma*; Chen Zhu; Chunfeng Yao; Bailan Feng; Feng Dai; Image Stitching via Deep Homography Estimation, Neurocomputing, 2021, 450, 219-229.(IF=4.685,CCF C类期刊,中科院2区,WOS1区)

[3] Feng Dai; Hao Liu; Yike Ma; Xi Zhang; Qiang Zhao?; Dense Scale Network for Crowd Counting, ACM International Conference on Multimedia Retrieval (ICMR 2021), Taibei, Taiwan. (CCF B类会议)

[4] Hao Liu; Qiang Zhao; Yike Ma; Feng Dai*; Bipartite Matching for Crowd Counting with Point Supervision, The 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), Montreal, Canada. (CCF A类会议)

[5] Feng Dai; Youqiang Zhang; Yike Ma; Hongliang Li; Qiang Zhao*; Dilated Convolutional Neural Networks for Panoramic Image Saliency Prediction, The 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020), Barcelona, Spain. (CCF B类会议)

[6] Qiang Zhao; Feng Dai; Jing Lv; Yike Ma; Yongdong Zhang; Panoramic Light Field From Hand-Held Video and Its Sampling for Real-Time Rendering, IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(4), 1011-1021. (IF=5.719,CCF B类期刊,IEEE Trans,中科院1区,WOS1区)

[7] Feng Dai, Chen Zhu, Yike Ma, Juan Cao, Qiang Zhao*, Yongdong Zhang “Freely Explore the Scene with 360 Field of View”, The 26th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR), 2019. (CCF A类会议)

[8] Xuehui Wang, Feng Dai*, Yike Ma, Junbo Guo, Qiang Zhao, Yongdong Zhang, ” Near-Infrared Image Guided Neural Networks For Color Image Denoising”, International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2019), UK, Brighton.  (CCF B类会议)

[9] Guoqing Jin, Shiwei Shen, Dongming Zhang*, Feng Dai, Yongdong Zhang,”APE-GAN: Adversarial Perturbation Elimination With Gan”, International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2019), UK, Brighton. (CCF B类会议)

[10] Qiang Zhao, Zhu Chen, Feng Dai*, Yike Ma, Guoqing Jin, and Yongdong Zhang, “Distortion-aware CNNs for Spherical Images”, International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden. (CCF A类会议)

[11] Jing Lyu, Feng Dai*, Qiang Zhao, Hongliang Li, Yike Ma and Yongdong Zhang, “Panoramic Light Field Video Acquisition” IEEE International Conference on Multimedia and Expo (ICME) 2018, San Diego, USA.(CCF B类会议)

[12] Rihui Wu; Adrian Jarabo; Jinli Suo; Feng Dai; Yongdong Zhang; Qionghai Dai and Diego Gutierrez “Adaptive Polarization-Difference Transient Imaging for Depth Estimation in Scattering Media”  Optics Letters,43(6), pp. 1299-1302, 2018. (中科院2区,WOS1区)

[13] Qiang Zhao, Feng Dai, Yike Ma, Liang Wan, Jiawan Zhang, and Yongdong Zhang “Spherical Superpixel Segmentation”, IEEE Transactions on Multimedia 2018,20(6), pp1406-1417,2018. (IF=6.513,CCF B类期刊,IEEE Trans,中科院1区,WOS1区)

[14] Rihui Wu, Jinli Suo, Feng Dai, Yongdong Zhang, and Qionghai Dai, "Scattering robust 3D reconstruction via polarized transient imaging," Optics Letters, 2016, 41(17), 3948-3951. (光学顶级期刊,中科院2区)

[15] Chenggang Yan, Yongdong Zhang, Jizheng Xu, Feng Dai, Jun Zhang, Qionghai Dai, Feng Wu, "Efficient Parallel Framework for HEVC Motion Estimation on Many-Core Processors," Circuits and Systems for Video Technology, IEEE Transactions on , vol.24, no.12, pp.2077-2089, 2014. (CCF B类期刊,IEEE Trans,中科院1区,WOS1区)

[16] Lingling Tong, Feng Dai*, Dongming Zhang and Yongdong Zhang,” Encoder combined video moving object detection”, Neurocomputing, 139 (2014): 150-162. (Neurocomputing)

[17] Chenggang Yan, Yongdong Zhang, Feng Dai and Liang Li, “Highly Parallel Framework for HEVC Motion Estimation on Many-core Platform”, Data Compression Conference (DCC),2013. (CCF B类会议)

[18] Chenggang Yan, Yongdong Zhang, Feng Dai and Liang Li, “Efficient Parallel Framework for HEVC Deblocking Filter on Many-core Platform”, Data Compression Conference (DCC),2013. (CCF B类会议)

[19] Yongdong Zhang, Chenggang Yan, Feng Dai, Yike Ma, “Efficient Parallel Framework for H.264/AVC Deblocking Filter on Many-core Platform”,IEEE Transactions on Multimedia, VOL. 14, NO. 3, pp 510-524, June 2012. (CCF B类期刊,IEEE Trans,中科院1区,WOS1区)

[20] Chenggang Yan, Feng Dai, Yongdong Zhang, Yike Ma, Licheng Chen, LingjunFan, Yasong Zheng: “Parallel Deblocking Filter For H.264/AVC Implemented On Tile64 Platform”,International Conference on Multimedia and Expo(ICME),2011. (CCF B类会议, 最佳论文候选)

[21] Like Yu, Feng Dai, Yongdong Zhang and Shouxun Lin, “Efficient Video Coding Optimization using a Novel Perceptual Distortion Model”, Data Compression Conference (DCC),2011. (CCF B类会议)

[22] Lingling Tong, Feng Dai, Yongdong Zhang and Jintao Li, “Visual Security Evaluation for Video Encryption,” ACM International Conference on Multimedia (ACM MM), 2010. (CCF A类会议)

[23] Feng Dai, Yanfei Shen, Yongdong Zhang, Shouxun Lin, “The Most Efficient Tile Size In Tile-Based Cylinder Panoramic Video Coding And Its Selection Under Restriction Of Bandwidth”, 2007 IEEE International Conference on Multimedia & Expo(ICME’07) ) (CCF B类会议)

[24] Zhang Yong-dong, Dai Feng, Lin Shou-xun. “Fast 4×4 Intra-prediction Mode Selection for H.264”, 2004 IEEE Int. Conf. Multimedia &Expo (ICME2004), TaiWan, China, July 2004.(CCF B类会议)

专利:

[1] 一种恢复深度信息的图像处理的方法(授权号:201510490628.9) 

[2] 一种基于观测矩阵的压缩感知成像及图像重建方法(授权号:201510551103.1) 

[3] 一种基于动态光散射技术的悬浮颗粒粒径测量装置及方法(授权号: 201510483564.X) 

[4] 一种光场图像前后景自动分割方法(申请号:201510670734.5)

[5] 面向排序测度特征的图像匹配方法及系统(授权号:201410646014.0) 

[6] 基于排序测度特征的图像检索方法及系统 (授权号:201410645743.4) 

[7] 一种视频编解码中去块滤波方法 (授权号:201110007133.8)

[8] 支持音视频解码自适应的系统及其方法(授权号:200910084861.1) 

[9] 保证特定区域显示质量的视频编码的方法和装置(授权号:200910083722.7) 

[10] 隐私区域置乱的视频中误差漂移的抑制方法与系统(授权号:200910093974.8) 

[11] 一种柱面全景视频编码的块尺寸计算方法和传输方法(授权号:200710175443.4) 

科研项目:

[1] 基于深度学习的压缩感知成像技术研究 (61771458) 国家自然科学基金  课题负责人 2018年1月-2021年12月
[2] 动态可配置的压缩感知成像系统 (61327013)国家自然科学基金科学仪器基础研究专项  课题技术负责人 2014年1月-2017年12月
[3] 基于GPU平台的HEVC并行编码算法研究(61379084) 国家自然科学基金 课题负责人 2014年1月-2017年12月
[4] 基于隐私区域的视频加密技术研究(61102101) 国家自然科学基金 课题负责人 2012年1月-2014年12月 

获奖及荣誉:

2018年中国多媒体大会最佳论文奖

2018年中国多媒体大会杰出展示奖

2014年北京市科学技术奖一等奖 (排名第8)

2011年ICME最佳论文候选