基本信息
代锋  男  博导  中国科学院计算技术研究所
电子邮件: fdai@ict.ac.cn
通信地址: 北京市海淀区科学院南路6号中科院计算所
邮政编码: 100190

研究领域

计算机视觉;视频图像分析处理

招生信息

   
招生专业
081203-计算机应用技术

教育背景

2002-09--2008-06   中国科学院计算技术研究所   博士
1998-09--2002-06   清华大学   学士

工作经历

代锋,男,博士,中国科学院计算技术研究所副研究员,博士生导师。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,目前的研究兴趣为农业图像分析处理。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,国家信息安全242计划项目等多个国家级项目。在CVPR/ECCV/AAAI/IJCAI/IEEE T-MM/IEEE T-CSVT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。研究成果批量应用于国家网络安全主管部门。

工作简历
2011-09~现在, 中国科学院计算技术研究所, 副研究员
2008-07~2011-09,中国科学院计算技术研究所, 助理研究员

专利与奖励

   
奖励信息
(1) 北京市科技发明奖, 一等奖, 省级, 2014
专利成果
( 1 ) 基于双目光场相机的深度获取方法和系统, 专利授权, 2021, 第 1 作者, 专利号: CN109840922B

( 2 ) 基于哈达玛矩阵的渐进式压缩感知重建方法和系统, 专利授权, 2020, 第 1 作者, 专利号: CN107749047B

( 3 ) 一种光场图像前后景自动分割方法, 发明专利, 2018, 第 1 作者, 专利号: CN105184808B

( 4 ) 用于压缩微透镜阵列采集的光场图像的方法和系统, 发明专利, 2018, 第 1 作者, 专利号: CN104469372B

( 5 ) 基于偏振瞬态成像的散射场景深度重建方法以及设备, 发明专利, 2018, 第 5 作者, 专利号: CN108335324A

( 6 ) 基于K均值聚类的光场前景分割方法及装置, 发明专利, 2018, 第 4 作者, 专利号: CN107862698A

( 7 ) 压缩感知图像的采集重建方法和系统, 发明专利, 2018, 第 1 作者, 专利号: CN107846592A

( 8 ) 基于自动编码器网络的压缩感知测量矩阵优化方法和系统, 发明专利, 2018, 第 1 作者, 专利号: CN107784676A

( 9 ) 一种基于深度残差网络的压缩感知重建方法和系统, 发明专利, 2018, 第 1 作者, 专利号: CN107730451A

( 10 ) 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, 发明专利, 2018, 第 1 作者, 专利号: CN105067489B

( 11 ) 基于排序测度特征的图像检索方法及系统, 发明专利, 2018, 第 3 作者, 专利号: CN104408092B

( 12 ) 一种恢复深度信息的图像处理的方法, 发明专利, 2017, 第 1 作者, 专利号: CN105118031B

( 13 ) 局部特征点筛选方法及系统, 发明专利, 2017, 第 6 作者, 专利号: CN106372111A

( 14 ) 一种基于观测矩阵的压缩感知成像及图像重建方法, 发明专利, 2016, 第 2 作者, 专利号: CN105225207A

( 15 ) 一种高分辨率光场图片重建方法与成像装置, 发明专利, 2015, 第 1 作者, 专利号: CN104735351A

( 16 ) 面向排序测度特征的图像匹配方法及系统, 发明专利, 2015, 第 3 作者, 专利号: CN104484869A

( 17 ) 一种媒体播放系统和方法, 发明专利, 2012, 第 2 作者, 专利号: CN102625150A

( 18 ) 一种视频编解码中去块滤波方法, 发明专利, 2011, 第 2 作者, 专利号: CN102075753A

出版信息

   
发表论文
[1] Zhu, Jiaqi, Dai, Feng, Yu, Lingyun, Xie, Hongtao, Wang, Lidong, Wu, Bo, Zhang, Yongdong. Attention-guided transformation-invariant attack for black-box adversarial examples. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS[J]. 2022, 37(5): 3142-3165, http://dx.doi.org/10.1002/int.22808.
[2] Zhao, Qiang, Ma, Yike, Zhu, Chen, Yao, Chunfeng, Feng, Bailan, Dai, Feng. Image stitching via deep homography estimation. NEUROCOMPUTING[J]. 2021, 450: 219-229, http://dx.doi.org/10.1016/j.neucom.2021.03.099.
[3] Huang, Liangjun, Zhu, Luning, Shen, Shihui, Zhang, Qing, Zhang, Jianwei. SRNet: Scale-Aware Representation Learning Network for Dense Crowd Counting. IEEE ACCESS[J]. 2021, 9: 136032-136044, http://dx.doi.org/10.1109/ACCESS.2021.3115963.
[4] Li, Hongliang, Lu, Ke, Xue, Jian, Dai, Feng, Zhang, Yongdong. Dual Optical Path Based Adaptive Compressive Sensing Imaging System. SENSORS[J]. 2021, 21(18): http://dx.doi.org/10.3390/s21186200.
[5] 代锋. Bipartite Matching for Crowd Counting with Point Supervision. The 30th International Joint Conference on Artificial Intelligence. 2020, [6] Zhang, Youqiang, Dai, Feng, Ma, Yike, Li, Hongliang, Zhao, Qiang, Zhang, Yongdong. Saliency Prediction Network for 360 degrees Videos. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING[J]. 2020, 14(1): 27-37, http://dx.doi.org/10.1109/JSTSP.2019.2955824.
[7] Dai, Feng, Zhang, Youqiang, Ma, Yike, Li, Hongliang, Zhao, Qiang, IEEE. DILATED CONVOLUTIONAL NEURAL NETWORKS FOR PANORAMIC IMAGE SALIENCY PREDICTION. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSINGnull. 2020, 2558-2562, [8] Jing, Xiuxiu, Ma, Yike, Zhao, Qiang, Lyu, Ke, Dai, Feng, Ro, YM, Cheng, WH, Kim, J, Chu, WT, Cui, P, Choi, JW, Hu, MC, DeNeve, W. Light Field Reconstruction Using Dynamically Generated Filters. MULTIMEDIA MODELING (MMM 2020), PT Inull. 2020, 11961: 3-13, [9] Zhao, Qiang, Dai, Feng, Lv, Jing, Ma, Yike, Zhang, Yongdong. Panoramic Light Field From Hand-Held Video and Its Sampling for Real-Time Rendering. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2020, 30(4): 1011-1021, http://dx.doi.org/10.1109/TCSVT.2019.2900051.
[10] Wang, Xuehui, Dai, Feng, Ma, Yike, Guo, Junbo, Zhao, Qiang, Zhang, Yongdong, IEEE. NEAR-INFRARED IMAGE GUIDED NEURAL NETWORKS FOR COLOR IMAGE DENOISING. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)null. 2019, 3807-3811, [11] Feng Dai, Chen Zhu, Yike Ma, Juan Cao, Qiang Zhao, Yongdong Zhang. Freely Explore the Scene with 360 degrees Field of View. IEEE VR 2019null. 2019, 888-889, [12] Yao, Hantao, Dai, Feng, Zhang, Shiliang, Zhang, Yongdong, Tian, Qi, Xu, Changsheng. DR2-Net: Deep Residual Reconstruction Network for image compressive sensing. NEUROCOMPUTING[J]. 2019, 359: 483-493, http://dx.doi.org/10.1016/j.neucom.2019.05.006.
[13] Wang, Xuehui, Dai, Feng, Ma, Yike, Gao, Ke, Zhang, Yong Dong. Scene-adaptive coded aperture imaging. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2019, 78(1): 697-711, https://www.webofscience.com/wos/woscc/full-record/WOS:000457317500039.
[14] Jin, Guoqing, Shen, Shiwei, Zhang, Dongming, Dai, Feng, Zhang, Yongdong, IEEE. APE-GAN: ADVERSARIAL PERTURBATION ELIMINATION WITH GAN. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)[J]. 2019, 3842-3846, [15] 张冬明, 靳国庆, 代锋, 袁庆升, 包秀国, 张勇东. 基于深度融合的显著性目标检测算法. 计算机学报[J]. 2019, 42(9): 2076-2086, http://lib.cqvip.com/Qikan/Article/Detail?id=7002850549.
[16] Zhao, Qiang, Dai, Feng, Ma, Yike, Wan, Liang, Zhang, Jiawan, Zhang, Yongdong. Spherical Superpixel Segmentation. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2018, 20(6): 1406-1417, https://www.webofscience.com/wos/woscc/full-record/WOS:000432400400010.
[17] Wu, Rihui, Jarabo, Adrian, Suo, Jinli, Dai, Feng, Zhang, Yongdong, Dai, Qionghai, Gutierrez, Diego. Adaptive polarization-difference transient imaging for depth estimation in scattering media. OPTICS LETTERS[J]. 2018, 43(6): 1299-1302, http://dx.doi.org/10.1364/OL.43.001299.
[18] Lv, Jing, Dai, Feng, Zhao, Qiang, Li, Hongliang, Ma, Yike, Zhang, Yongdong, IEEE. PANORAMIC LIGHT FIELD VIDEO ACQUISITION. 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2018, [19] 代锋. Semantic Preserving Hash Coding through VAE-GAN. ICIP. 2018, [20] 吴日辉, 代锋, 尹冬, 刘烨斌, 戴琼海, 张勇东. 基于瞬态成像技术的穿透散射介质成像. 计算机学报[J]. 2018, 41(11): 2421-2435, http://lib.cqvip.com/Qikan/Article/Detail?id=7000902877.
[21] Zhou Jianshe, Naren Tuya, Chen Xianyu, Ma Yike, Liu Jie, Dai Feng, Schoeffmann K, Chalidabhongse TH, Ngo CW, Aramvith S, OConnor NE, Ho YS, Gabbouj M, Elgammal A. Light Field Foreground Matting Based on Defocus and Correspondence. MULTIMEDIA MODELING, MMM 2018, PT Inull. 2018, 10704: 317-328, [22] Wang, Xuehui, Dai, Feng, Suo, Jinli, Zhang, Yongdong, Dai, Qionghai, Jiang, S, Zeng, B, Huang, Q, ElSaddik, A, Li, H, Fan, X. Multi-scale Convolutional Neural Networks for Non-blind Image Deconvolution. ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT IInull. 2018, 10736: 911-919, [23] Lv, Jing, Zhao, Qiang, Dai, Feng, Ma, Yike, Zhang, Yongdong. Variable aperture panoramic imaging. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2018, 77(20): 26677-26695, https://www.webofscience.com/wos/woscc/full-record/WOS:000444201500021.
[24] Jin, Guoqing, Zhang, Dongming, Dai, Feng, Zhang, Yongdong. Eigenobject-wise saliency detection based on manifold ranking. NEUROCOMPUTING[J]. 2018, 281: 196-205, http://dx.doi.org/10.1016/j.neucom.2017.12.009.
[25] 代锋. Wide Range Depth Estimation from Binocular Light Field Camera. BMVC. 2018, [26] 代锋. Distortion-aware CNNs for Spherical Images", International Joint Conference on Artificial Intelligence. IJCAI. 2018, [27] Zhao, Qiang, Wan, Liang, Zhang, Jiawan, IEEE. SPHERICAL SUPERPIXEL SEGMENTATION. 2016 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME)null. 2016, [28] Wu, Rihui, Suo, Jinli, Dai, Feng, Zhang, Yongdong, Dai, Qionghai. Scattering robust 3D reconstruction via polarized transient imaging. OPTICS LETTERS[J]. 2016, 41(17): 3948-3951, http://www.corc.org.cn/handle/1471x/2375816.
[29] 张峻, 代锋, 马宜科, 张勇东. 多层次细粒度并行HEVC帧内模式选择算法. 计算机研究与发展[J]. 2016, 53(4): 873-883, http://lib.cqvip.com/Qikan/Article/Detail?id=668556503.
[30] Chen, Xing, Yan, Chenggang Clarence, Zhang, Xiaotian, Zhang, Xu, Dai, Feng, Yin, Jian, Zhang, Yongdong. Drug-target interaction prediction: databases, web servers and computational models. BRIEFINGS IN BIOINFORMATICS[J]. 2016, 17(4): 696-712, https://www.webofscience.com/wos/woscc/full-record/WOS:000383151200013.
[31] Chen Xianyu, Dai Feng, Ma Yike, Zhang Yongdong, IEEE. Automatic Foreground Segmentation Using Light Field Images. 2015 VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP)null. 2015, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000399132000103.
[32] 沈燕飞, 李锦涛, 朱珍民, 张勇东, 代锋. 基于非局部相似模型的压缩感知图像恢复算法. 自动化学报[J]. 2015, 41(2): 261-272, https://d.wanfangdata.com.cn/periodical/zdhxb2015020004.
[33] 代锋. Lenselet Image Compression Scheme Based On Subaperture Images Streaming. The International Conference on Image Processing. 2015, [34] Yan, Chenggang, Zhang, Yongdong, Dai, Feng, Wang, Xi, Li, Liang, Dai, Qionghai. Parallel deblocking filter for HEVC on many-core processor. ELECTRONICS LETTERS[J]. 2014, 50(5): 367-+, https://www.webofscience.com/wos/woscc/full-record/WOS:000333395500023.
[35] Yan, Chenggang, Zhang, Yongdong, Xu, Jizheng, Dai, Feng, Li, Liang, Dai, Qionghai, Wu, Feng. A Highly Parallel Framework for HEVC Coding Unit Partitioning Tree Decision on Many-core Processors. IEEE SIGNAL PROCESSING LETTERS[J]. 2014, 21(5): 573-576, https://www.webofscience.com/wos/woscc/full-record/WOS:000333365100004.
[36] Yan, C, Zhang, Y, Dai, F, Zhang, J, Li, L, Dai, Q. Efficient parallel HEVC intra-prediction on many-core processor. ELECTRONICS LETTERS[J]. 2014, 50(11): 805-U53, https://www.webofscience.com/wos/woscc/full-record/WOS:000337911200014.
[37] Tong, Lingling, Dai, Feng, Zhang, Dongming, Wang, Dong, Zhang, Yongdong. Encoder combined video moving object detection. NEUROCOMPUTING[J]. 2014, 139: 150-162, http://dx.doi.org/10.1016/j.neucom.2014.02.049.
[38] Yan, Chenggang, Zhang, Yongdong, Xu, Jizheng, Dai, Feng, Zhang, Jun, Dai, Qionghai, Wu, Feng. Efficient Parallel Framework for HEVC Motion Estimation on Many-Core Processors. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2014, 24(12): 2077-2089, https://www.webofscience.com/wos/woscc/full-record/WOS:000346150200006.
[39] 代锋. VTrans: A Distributed Video Transcoding Platform. International Conference on MultiMedia Modeling(MMM). 2013, [40] Zhang, Jun, Dai, Feng, Ma, Yike, Zhang, Yongdong, IEEE. Highly Parallel Mode Decision Method for HEVC. 2013 PICTURE CODING SYMPOSIUM (PCS)null. 2013, 281-284, [41] Yan, Chenggang, Zhang, Yongdong, Dai, Feng, Li, Liang, Bilgin, A, Marcellin, MW, SerraSagrista, J, Storer, JA. Efficient Parallel Framework for HEVC Deblocking Filter on Many-core Platform. 2013 DATA COMPRESSION CONFERENCE (DCC)null. 2013, 530-530, [42] 代锋. A real-time peak discovering method for audio fingerprinting. Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service(ICIMCS). 2013, [43] Dai Feng, Zhang Dongming, Li Jintao. Encoder/Decoder for Privacy Protection Video with Privacy Region Detection and Scrambling. International Conference on MultiMedia Modeling(MMM)[J]. 2013, [44] Yan Chenggang, Zhang Yongdong, Dai Feng, Li Liang, Bilgin A, Marcellin MW, SerraSagrista J, Storer JA. Highly Parallel Framework for HEVC Motion Estimation on Many-core Platform. 2013 DATA COMPRESSION CONFERENCE (DCC)null. 2013, 63-72, [45] 代锋. A Large Scale Audio Fingerprinting System. Pacific-Rim Conference on Multimedia (PCM). 2013, [46] Mengmeng ZhangJianfeng QuHuihui Bai. Fast Intra Prediction Mode Decision Algorithm for HEVC. TELKOMNIKA INDONESION JOURNAL OF ELECTRICAL ENGINEERING[J]. 2013, 11(10): http://gooa.las.ac.cn/external/index?type=-1&pid=981588.
[47] 代锋. Efficient HEVC to H.264/AVC Transcoding with Fast Intra Mode Decision. International Conference on MultiMedia Modeling(MMM). 2013, [48] 俞力克, 代锋, 张勇东, 林守勋. 基于纹理和亮度感知特性的率失真优化策略. 中国图象图形学报[J]. 2012, 17(1): 54-61, http://lib.cqvip.com/Qikan/Article/Detail?id=40404591.
[49] Zhang, Yongdong, Yan, Chenggang, Dai, Feng, Ma, Yike. Efficient Parallel Framework for H.264/AVC Deblocking Filter on Many-Core Platform. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2012, 14(3): 510-524, https://www.webofscience.com/wos/woscc/full-record/WOS:000304166300003.
[50] 代锋. Perceptual Motivated Coding Strategy for Quality Consistency. International Conference on MultiMedia Modeling(MMM). 2011, [51] 代锋. Efficient VideoCoding Optimization using a Novel Perceptual Distortion Model. Data Compression Conference (DCC). 2011, [52] Yan Chenggang, Dai Feng, Zhang Yongdong, Lee KT, Tsai WH, Liao HYM, Chen T, Hsieh JW, Tseng CC. Parallel Deblocking Filter for H.264/AVC on the TILERA Many-Core Systems. ADVANCES IN MULTIMEDIA MODELING, PT Inull. 2011, 6523: 51-61, [53] Yan Chenggang, Dai Feng, Zhang Yongdong, Ma Yike, Chen Licheng, Fan Lingjun, Zheng Yasong, IEEE. PARALLEL DEBLOCKING FILTER FOR H.264/AVC IMPLEMENTED ON TILE64 PLATFORM. 2011 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2011, [54] Li Jintao. Compressive Sensing based Video Scrambling for Privacy Protection. IEEE conference on Visual Communications and Image Processing(VCIP). 2011, [55] Dai, Feng, Tong, Lingling, Zhang, Yongdong, Li, Jintao. Restricted H.264/AVC video coding for privacy protected video scrambling. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION[J]. 2011, 22(6): 479-490, http://dx.doi.org/10.1016/j.jvcir.2011.05.006.
[56] Tong Lingling, Dai Feng, Zhang Yongdong, Li Jintao, IEEE. RESTRICTED H.264/AVC VIDEO CODING FOR PRIVACY REGION SCRAMBLING. 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSINGnull. 2010, 2089-2092, [57] Tong, L, Dai, F, Zhang, Y, Li, J. Prediction restricted H.264/AVC video scrambling for privacy protection. ELECTRONICS LETTERS[J]. 2010, 46(1): 47-48, http://www.corc.org.cn/handle/1471x/2415114.
[58] 代锋. Visual Security Evaluation for Video Encryption. ACM International Conference on Multimedia (ACM MM). 2010, [59] Dai, Feng, Huang, Sheng, Xia, Kaiwen, Tan, Zhuoying. Some Fundamental Issues in Dynamic Compression and Tension Tests of Rocks Using Split Hopkinson Pressure Bar. ROCK MECHANICS AND ROCK ENGINEERING[J]. 2010, 43(6): 657-666, http://119.78.100.198/handle/2S6PX9GI/3247.
[60] Dai, Feng, Shen, Yanfei, Zhang, Yongdong, Lin, Shouxun. Selection of the most efficient tile size in tile-based cylinder panoramic video coding and transmission. VISUAL COMPUTER[J]. 2007, 23(9-11): 891-896, http://www.corc.org.cn/handle/1471x/2380235.
[61] 代锋. he Most Efficient Tile Size In Tile-Based Cylinder Panoramic Video Coding And Its Selection Under Restriction Of Bandwidth. IEEE International Conference on Multimedia and Expo. 2007, [62] Yu Lejun, Dai Feng, Zhang Yongdong, Li Jintao, Yuan BZ, Ruan QQ, Tang XF. Entropy coding based on code-value compact memory structure for AVS video coding standard. 2006 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-4null. 2006, 1409-+, [63] Shen Yanfei, Dai Feng, Zhang Yongdong, Li Jintao, Yuan BZ, Ruan QQ, Tang XF. Improved fractional pixel motion estimation algorithm for H.264/AVC. 2006 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-4null. 2006, 1448-+, [64] Dai, Feng, Zhang, Yongdong, Shen, Yanfei, Lin, Shouxun, Yuan, BZ, Ruan, QQ, Tang, XF. Transcoing-based data transmission of sphere panoramic videos. 2006 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-4null. 2006, 1416-+, [65] 代锋. Transcoding-based Data Transmission of Sphere Panoramic Videos. IEEE International Conference on Signal Processing. 2006, [66] 代锋, 张勇东, 林守勋. 引入Foveation视觉模型的MPEG视频码流码率转换. 中国图象图形学报[J]. 2005, 10(12): 1567-1574, http://lib.cqvip.com/Qikan/Article/Detail?id=20744811.
[67] 代锋, 张勇东, 林守勋. 引入Foveation视觉模型的MPEG视频码流码率转换. 中国图象图形学报[J]. 2005, 10(12): 1567-1574, http://lib.cqvip.com/Qikan/Article/Detail?id=20744811.
[68] 代锋. Efficient Block Size Selection for MPEG-2 to H.264 Transcoding. ACM International Conference on Multimedia (ACM MM). 2004, [69] 代锋. Fast 4×4 Intra-prediction Mode Selection for H.264. International Conference on Multimedia and Expo(ICME). 2004, 

科研活动

   
科研项目
( 1 ) 基于隐私区域的视频加密技术研究(61102101), 负责人, 国家任务, 2012-01--2014-12
( 2 ) 移动互联网与宽带网融合总体架构和关键评估方法及移动互联网与电信宽带网融合技术方案及应用示范, 参与, 国家任务, 2012-01--2014-12
( 3 ) XXXXXX(242)2009A45, 负责人, 国家任务, 2009-09--2010-08
( 4 ) xxxxx(2007CB311105), 参与, 国家任务, 2007-07--2011-06
( 5 ) 网络视频信息发现与内容分析关键技术研究(2007AA01Z416), 参与, 国家任务, 2007-07--2009-12
( 6 ) 动态可配置的压缩感知成像系统, 参与, 国家任务, 2014-01--2017-12
( 7 ) 基于GPU平台的HEVC并行编码算法研究, 负责人, 国家任务, 2014-01--2017-12
( 8 ) 面向众核处理器的高并行度视频编码关键技术研究, 参与, 国家任务, 2013-01--2016-12
( 9 ) 基于深度学习的压缩感知成像技术研究, 负责人, 国家任务, 2018-01--2021-12
( 10 ) 面向互联网+的视听媒体内容审计技术研究, 负责人, 国家任务, 2018-12--2022-12
( 11 ) 鱼眼视觉关键技术研究合作项目, 负责人, 企业委托, 2020-04--2021-04
( 12 ) 智能农机关键技术研发创制, 负责人, 中国科学院计划, 2021-07--2026-06
( 13 ) 无人化农机作业环境识别与场景构建技术研究, 负责人, 国家任务, 2022-11--2026-10