081104-模式识别与智能系统
081203-计算机应用技术
085400-电子信息

计算机视觉，机器人，人机交互
计算机视觉，机器人，人机交互
计算机视觉，机器人，人机交互

2002-09--2006-04   香港中文大学   博士
1999-09--2002-07   中国科学技术大学   硕士
1994-09--1999-07   中国科学技术大学   双学士

   

2006-06~现在, 中国科学院深圳先进技术研究院, 研究员/研究室主任

   

（1） 户外全自主移动机器人关键技术及应用, 二等奖, 部委级, 2017
（2） 智能互联网机器人及应用平台, 三等奖, 省级, 2016
（3） 智能互联网机器人及开放平台, 二等奖, 市地级, 2015
（4） 智能互联网机器人, 二等奖, 其他, 2014

[1] 高向阳, 程俊. 一种机器人的控制方法、机器人及存储介质. CN: CN114211486A, 2022-03-22.
[2] 张锲石, 程俊. 一种图像处理方法、终端设备及计算机可读存储介质. CN: CN114219725A, 2022-03-22.
[3] 王磊, 刘薰裕, 马晓亮, 程俊. 一种三维重建方法、装置、设备及计算机存储介质. CN: CN114219890A, 2022-03-22.
[4] 程俊, 郭海光. 缺陷检测方法、装置及终端设备. CN: CN111044522B, 2022-03-11.
[5] 高向阳, 程俊, 任子良, 张锲石, 康宇航, 郭海光. 一种基于语音控制的终端设备及语音控制系统. CN: CN114155851A, 2022-03-08.
[6] 高向阳, 程俊, 康宇航, 任子良, 张锲石. 光源控制电路及视觉检测仪. CN: CN114157816A, 2022-03-08.
[7] 程俊, 吴福祥, 宋呈群. 一种基于文本的图像编辑方法和电子设备. CN: CN114092758A, 2022-02-25.
[8] 许震宇, 张锲石, 程俊. 图像识别方法、装置、电子设备及存储介质. CN: CN114067137A, 2022-02-18.
[9] 牛茂龙, 乔丕业, 程俊, 刘航, 刘朝鹏, 郑浩河, 程钦, 任子良. 工装穿戴检测方法、装置、计算机设备和存储介质. CN: CN113743199A, 2021-12-03.
[10] 曾驳, 宋呈群, 程俊. 视觉SLAM方法、装置、终端设备及存储介质. CN202110805748.9, 2021-11-09.
[11] 郑浩河, 乔丕业, 刘航, 刘朝鹏, 程俊, 牛茂龙, 程钦, 任子良. 人体动作识别方法、装置、计算机设备和存储介质. CN: CN113591647A, 2021-11-02.
[12] 高向阳, 程俊. 一种机器人底座. CN: CN214213846U, 2021-09-17.
[13] 高向阳, 程俊. 一种机器人底座. CN: CN214213846U, 2021-09-17.
[14] 任子良, 程俊, 张锲石, 高向阳, 康宇航. 一种动作检测方法、装置、终端设备和存储介质. CN: CN113326835A, 2021-08-31.
[15] 王磊, 钟宏亮, 林佩珍, 程俊. 一种物体模型的重建方法、装置、终端设备和存储介质. CN: CN113298931A, 2021-08-24.
[16] 程俊, 宋呈群, 曾驳, 吴福祥. 一种机器人的控制方法及机器人. CN202110428814.5, 2021-08-13.
[17] 程俊, 宋呈群. 一种机器人的控制方法及机器人. CN: CN113256716A, 2021-08-13.
[18] 程俊, 宋呈群. 一种机器人的控制方法及机器人. CN: CN113256716A, 2021-08-13.
[19] 王飞, 程俊, 刘鹏磊. 图像场景深度的估计方法、装置、终端设备和存储介质. CN: CN113160294A, 2021-07-23.
[20] 程俊, 郭海光. 缺陷检测方法、装置及终端设备. CN: CN113112442A, 2021-07-13.
[21] 高向阳, 程俊, 康宇航, 任子良, 张锲石, 郭海光. 控制机器人的方法、装置及终端设备. CN: CN112720463A, 2021-04-30.
[22] 高向阳, 程俊, 任子良, 张锲石, 康宇航. 智能车库交互方法和智能车库交互系统. CN: CN112734987A, 2021-04-30.
[23] 张锲石, 程俊, 康宇航, 任子良, 高向阳. 基于时空注意力和多级LSTM信息表达的车辆轨迹预测方法. CN: CN112686281A, 2021-04-20.
[24] 郭海光, 程俊, 高向阳. 一种图像校正系统及方法. CN: CN112689133A, 2021-04-20.
[25] 程俊, 张能波, 郭海光. 一种基于视觉引导的自动化标定系统. CN: CN112669389A, 2021-04-16.
[26] 郭海光, 程俊, 高向阳. 无线网络的接入方法、移动终端及智能设备. CN: CN112616170A, 2021-04-06.
[27] 周毅超, 程俊, 王鹏, 宋呈群, 程波, 栾语, 吴一谦, 张学刚, 栾振华. 核电站控制系统的手势操控方法、装置、设备及存储介质. CN: CN112596603A, 2021-04-02.
[28] 范筱媛, 王磊, 林佩珍, 程俊. 图像语义分割方法、存储介质和计算机设备. CN: CN112560965A, 2021-03-26.
[29] 张锲石, 程俊, 任子良, 康宇航, 高向阳. 一种基于轨迹相似性度量学习的多目标跟踪重定位方法. CN: CN112561960A, 2021-03-26.
[30] 刘鹏磊, 张锲石, 程俊. 一种实时高效的6D姿态估计网络、构建方法及估计方法. CN: CN112561995A, 2021-03-26.
[31] 张锲石, 程俊, 唐梓峰, 吴福祥. 基于互补的多分支深度学习进行三维点云分类方法. CN: CN112541535A, 2021-03-23.
[32] 王磊, 钟宏亮, 马森炜, 程俊, 林佩珍, 范筱媛. 检测车道线的方法、装置、终端设备及可读存储介质. CN: CN112528878A, 2021-03-19.
[33] 刘宝玉, 王磊, 马晓亮, 林佩珍, 程俊. 三维人体重建方法、装置、计算机设备和存储介质. CN: CN112530019A, 2021-03-19.
[34] 程俊, 高向阳, 任子良, 张锲石. 一种人体动作捕捉系统. CN: CN212729816U, 2021-03-19.
[35] 张锲石, 程俊, 欧阳祖薇, 康宇航, 任子良, 高向阳. 模型的训练方法和装置、电子设备、机器可读存储介质. CN: CN112508815A, 2021-03-16.
[36] 张锲石, 程俊, 许震宇, 任子良, 康宇航, 高向阳. 视觉位置识别方法及装置、计算机设备及可读存储介质. CN: CN112463999A, 2021-03-09.
[37] 宋呈群, 程俊. 3D语义地图构建方法和模块、机器人交互方法和系统. CN: CN112465974A, 2021-03-09.
[38] 孙士杰, 程俊, 任子良, 张锲石, 张能波, 李强. 基于视频特征的动作时段定位方法与计算机设备. CN: CN112434604A, 2021-03-02.
[39] 林佩珍, 王磊, 雷泽童, 刘宝玉, 程俊. 一种面部图像风格转换方法、装置、存储介质和电子设备. CN: CN112419477A, 2021-02-26.
[40] 任子良, 程俊, 张锲石, 高向阳, 康宇航. 一种基于特征交互学习的动作识别方法及终端设备. CN: CN112257526A, 2021-01-22.
[41] 程俊, 谢灿, 陈光, 赵文闯, 谢琪, 高向阳, 张丰. 手势识别系统. CN: CN112232217A, 2021-01-15.
[42] 程俊, 张锲石, 王胜文. 一种基于PointNet++的3D点云目标分类和语义分割网络的优化方法. CN: CN109753995B, 2021-01-01.
[43] 宋呈群, 程俊. 基于表检索的同时定位与建图方法和装置. CN: CN112116657A, 2020-12-22.
[44] 张能波, 王磊, 程俊. 位姿估计方法、装置、设备及介质. CN: CN112085789A, 2020-12-15.
[45] 张锲石, 程俊, 林典, 高向阳, 任子良, 康宇航. 一种图像深度估计方法、终端设备及计算机可读存储介质. CN: CN112070817A, 2020-12-11.
[46] 程俊, 向卉, 张锲石. 一种样本数据处理方法、样本数据处理装置及电子设备. CN: CN109344877B, 2020-12-11.
[47] 张能波, 王磊, 程俊. 一种电路板缺陷的检测方法、装置、终端设备及存储介质. CN: CN111982911A, 2020-11-24.
[48] 李卫民, 程俊, 高向阳, 任子良, 张锲石, 王海滨. 一种人体动作捕捉系统及方法. CN: CN111475024A, 2020-07-31.
[49] 程俊, 高向阳, 郭海光. 机器人避障控制方法、装置、终端设备及存储介质. CN: CN109739223B, 2020-07-03.
[50] 高向阳, 程俊, 张锲石, 任子良. 一种汽车驾驶员数据采集系统和穿戴式辅助驾驶设备. CN: CN210742920U, 2020-06-12.
[51] 程俊, 高向阳, 郭海光, 方琎. 穿戴式监测设备及监测系统. CN: CN210727717U, 2020-06-12.
[52] 栾语, 宋呈群, 程俊, 程波, 周毅超, 吴一谦, 张学刚, 刘至垚, 于正龙, 栾振华. 基于深度学习的深度图像获取方法、装置、设备及介质. CN: CN111192312A, 2020-05-22.
[53] 张能波, 王磊, 程俊. 物体姿态估计方法、装置与设备. CN: CN111161349A, 2020-05-15.
[54] 郭海光, 程俊. 绘画方法、装置、玩具机器人及可读存储介质. CN: CN111145315A, 2020-05-12.
[55] 王磊, 范筱媛, 陈嘉豪, 程俊. 一种三维目标检测方法、装置及终端. CN: CN111144242A, 2020-05-12.
[56] 王磊, 李嘉昊, 林佩珍, 程俊, 王雪婷, 康宇航. 对象关系预测方法、装置、终端设备及可读存储介质. CN: CN111126049A, 2020-05-08.
[57] 王磊, 雷泽童, 郭怡宏, 康宇航, 程俊. 一种图像特效处理方法、装置及终端. CN: CN111047509A, 2020-04-21.
[58] 郭海光, 程俊. 视频播放方法、装置、玩具机器人及可读存储介质. CN: CN111050105A, 2020-04-21.
[59] 郑建波, 胡希平, 方静, 卢海锋, 程俊. 三维步态数据处理方法、系统、服务器及存储介质. CN: CN111035393A, 2020-04-21.
[60] 李强, 程俊, 张锲石, 孙士杰. 基于神经网络的导航方法、装置及终端设备. CN: CN111044045A, 2020-04-21.
[61] 程俊, 张能波, 孙士杰. 一种检测金属锈蚀的方法及终端. CN: CN111028197A, 2020-04-17.
[62] 程俊, 郭海光. 活塞杆检测机构. CN: CN110987967A, 2020-04-10.
[63] 程俊, 胡颖, 宋呈群, 杨远源. 一种机器人标定方法及终端. CN: CN110866956A, 2020-03-06.
[64] 徐洋洋, 王磊, 程俊. 基于视频的行为识别方法、行为识别装置及终端设备. CN: CN110738070A, 2020-01-31.
[65] 任子良, 程俊, 张锲石, 高向阳. 一种行为识别方法、装置及终端设备. CN: CN110633630A, 2019-12-31.
[66] 程波, 程俊, 宋呈群, 王鹏, 周毅超, 栾语, 吴一谦, 张学刚, 于正龙, 刘至垚, 张建波, 徐晓梅, 栾振华. 一种核电站控制室多通道融合人机交互方法以及系统. CN: CN110597382A, 2019-12-20.
[67] 郭海光, 程俊, 高向阳, 方琎. 穿戴式人体阻抗测量手环. CN: CN209695186U, 2019-11-29.
[68] 程俊. 一种辅助教学系统. CN: CN209591141U, 2019-11-05.
[69] 程俊. 一种辅助教学系统. CN: CN209591141U, 2019-11-05.
[70] 宋呈群, 程俊, 王鹏. 用于场景认知的神经网络的训练方法、装置及终端设备. CN: CN110378250A, 2019-10-25.
[71] 徐洋洋, 王磊, 程俊. 一种行为识别方法、终端设备及计算机可读存储介质. CN: CN110321761A, 2019-10-11.
[72] 郝洛莹, 程俊, 张锲石. 视觉惯性里程计方法、视觉惯性里程计装置及移动设备. CN: CN110246147A, 2019-09-17.
[73] 程俊, 马征. 一种数据输入的方法及系统. CN: CN110174938A, 2019-08-27.
[74] 王磊, 相鹏, 程俊, 吴福祥, 康宇航. 一种图像去雨方法、装置、可读存储介质及终端设备. CN: CN110163813A, 2019-08-23.
[75] 张锲石, 刘袁, 程俊. 回环检测方法、回环检测装置及终端设备. CN: CN110163095A, 2019-08-23.
[76] 龙信文, 胡希平, 郑建波, 高英, 程俊. 一种信息推送的方法及设备. CN: CN110162695A, 2019-08-23.
[77] 程俊, 马征. 一种自训练脑机接口系统及相关训练方法. CN: CN110123313A, 2019-08-16.
[78] 方琎, 郭海光, 程俊, 高向阳. 一种移动读写终端机. CN: CN209199108U, 2019-08-02.
[79] 郭海光, 程俊, 高向阳, 方琎. 交互式投影仪. CN: CN209199060U, 2019-08-02.
[80] 程俊, 高向阳, 郭海光, 方琎. 地铁投影传媒设备及系统. CN: CN209198858U, 2019-08-02.
[81] 张锲石, 程俊, 田艳玲. 一种精细化车辆识别的神经网络方法及系统. CN: CN109978132A, 2019-07-05.
[82] 高向阳, 程俊, 郭海光. 光标定位方法、交互投影装置及教育系统. CN: CN109814770A, 2019-05-28.
[83] 张维桐, 张锲石, 程俊. 一种全景分割方法、装置及设备. CN: CN109801307A, 2019-05-24.
[84] 沈志娟, 程俊, 胡希平, 王磊. 一种多模态客户满意度综合评价系统、方法. CN: CN109801096A, 2019-05-24.
[85] 张锲石, 程俊, 杜聿博. 具有自我提升能力的金字塔双目深度估计模型. CN: CN109801323A, 2019-05-24.
[86] 程俊, 王鹏. 一种操作提示方法及眼镜. CN: CN109782902A, 2019-05-21.
[87] 张锲石, 程俊, 刘袁, 方璡, 向荣. 机器人的回环检测方法、装置及机器人. CN: CN109785387A, 2019-05-21.
[88] 王磊, 赖坤耀, 程俊. 一种轻量视觉问答系统及方法. CN: CN109784163A, 2019-05-21.
[89] 郭海光, 程俊, 高向阳, 方琎. 一种投影交互方法、装置、系统及终端设备. CN: CN109782962A, 2019-05-21.
[90] 王磊, 陈嘉豪, 程俊. 一种目标检测方法、装置以及行人检测方法、系统. CN: CN109753885A, 2019-05-14.
[91] 程俊, 张锲石, 王胜文. 一种基于3D目标分类和场景语义分割的网络优化结构. CN: CN109753995A, 2019-05-14.
[92] 程俊, 高向阳, 郭海光. 机器人避障控制方法、装置及终端设备. CN: CN109739223A, 2019-05-10.
[93] 张锲石, 程俊, 刘志强. 一种3D导航语义地图更新方法、装置及设备. CN: CN109737974A, 2019-05-10.
[94] 王磊, 徐成俊, 程俊. 一种基于深度学习的类别敏感型边缘检测方法. CN: CN109741351A, 2019-05-10.
[95] 李宏建, 程俊, 方璡. 一种文件扫描方法、装置及设备. CN: CN109729231A, 2019-05-07.
[96] 郭海光, 程俊, 高向阳. 一种投影画面自动校正方法、系统. CN: CN109688390A, 2019-04-26.
[97] 郭海光, 程俊, 高向阳. 一种生物信号的分析处理方法、装置及设备. CN: CN109512395A, 2019-03-26.
[98] 程俊, 姬晓鹏, 赵青松. 人体动作识别方法、装置、终端设备及存储介质. CN: CN109522874A, 2019-03-26.
[99] 张维桐, 田艳玲, 张锲石, 程俊. 一种目标检测方法、系统及终端设备. CN: CN109447943A, 2019-03-08.
[100] 程俊, 张丰, 王鹏, 姬晓鹏, 方璡. 一种拍摄人像的方法及装置. CN: CN109429002A, 2019-03-05.
[101] 程俊, 李凯, 张锲石. 一种触控指令的生成方法及设备. CN: CN109375833A, 2019-02-22.
[102] 程俊, 向卉, 张锲石. 一种样本数据处理方法、样本数据处理装置及电子设备. CN: CN109344877A, 2019-02-15.
[103] 张家访, 卢宗庆, 王肇, 程俊, 姜军. 夹持装置. CN: CN109304632A, 2019-02-05.
[104] 高向阳, 程俊, 郭海光. 交互方法及装置. KY: CN109246168A, 2019-01-18.
[105] 程俊, 沈三明, 姜军. 屏幕检测装置及方法. CN: CN108474718A, 2018-08-31.
[106] 姬晓鹏, 程俊, 张丰, 潘亮亮, 方琎. 一种穿戴式输入装置. CN: CN207663393U, 2018-07-27.
[107] 程俊, 郝洛莹. 图像拼接方法、图像拼接装置及电子设备. CN: CN108230245A, 2018-06-29.
[108] 胡希平, 韩问寒, 张佳, 王飞, 程俊. 一种数据文件及其访问方法、装置及设备. CN: CN108108633A, 2018-06-01.
[109] 吴世豪, 胡希平, 程俊. 人脸表情识别方法及装置. CN: CN107958230A, 2018-04-24.
[110] 相鹏, 王磊, 程俊. 一种图像修复方法、装置及设备. CN: CN107945140A, 2018-04-20.
[111] 郭海光, 程俊, 方璡, 高向阳. 一种具有数据处理功能的电子相框. CN: CN207200855U, 2018-04-06.
[112] 郭海光, 程俊, 方璡, 高向阳. 一种全景视频拍摄架. CN: CN207196012U, 2018-04-06.
[113] 程俊, 高向阳, 郭海光, 方璡. 一种全景摄像装置及全景监控系统. CN: CN207166659U, 2018-03-30.
[114] 程俊, 高向阳, 郭海光, 方璡. 一种监控机器人及监控系统. CN: CN207166657U, 2018-03-30.
[115] 李懿, 程俊, 姬晓鹏, 方璡. 一种动作识别方法、系统及终端设备. CN: CN107704819A, 2018-02-16.
[116] 胡希平, 吴世豪, 王飞, 郭舜, 程俊. 一种广告显示方法及移动终端. CN: CN107704223A, 2018-02-16.
[117] 郭海光, 程俊, 方璡, 高向阳. 一种交互投影方法、系统及计算机可读存储介质. CN: CN107682595A, 2018-02-09.
[118] 钟春斌, 程俊, 方璡. 全景图像拼接方法、终端设备及计算机可读存储介质. CN: CN107578373A, 2018-01-12.
[119] 吴世豪, 胡希平, 程俊, 张星明. 人脸表情识别方法及装置. CN: CN107392193A, 2017-11-24.
[120] 姬晓鹏, 程俊, 潘亮亮, 张丰, 方琎. 一种精细化手势识别方法、装置及设备. CN: CN107368820A, 2017-11-21.
[121] 程俊, 李懿. 人体动作识别方法及装置. CN: CN107358210A, 2017-11-17.
[122] 宋呈群, 程俊, 方璡. 摄像机‑投影交互触控方法、装置及计算机可读存储介质. CN: CN107357422A, 2017-11-17.
[123] 程俊, 潘亮亮, 姬晓鹏, 王鹏. 场景的三维重建方法、装置及终端设备. CN: CN107292949A, 2017-10-24.
[124] 胡希平, 程俊, 王飞, 潘亮亮. 应用于应用系统迁移的升级控制方法及升级控制设备. CN: CN107256167A, 2017-10-17.
[125] 高向阳, 程俊, 郭海光. 一种中控系统. CN: CN206533520U, 2017-09-29.
[126] 侯云江, 程俊. 一种智能解锁方法、装置和锁设备. CN: CN106934264A, 2017-07-07.
[127] 王鹏, 程俊, 冯伟. 一种语义地图构建方法、装置及一种机器人. CN: CN106780735A, 2017-05-31.
[128] 高向阳, 程俊, 郭海光. 一种机器人. 中国: CN106782519A, 2017-05-31.
[129] 郭海光, 程俊, 高向阳. 基于二维码的无线热点配置方法及系统. CN: CN106792802A, 2017-05-31.
[130] 程俊, 宋呈群, 姜军. 交互投影方法及装置. CN: CN106774846A, 2017-05-31.
[131] 姜军, 罗威, 程俊. 一种用于芯片集成的立体匹配方法和装置. CN: CN106780711A, 2017-05-31.
[132] 程俊, 张丰. 机器人的通讯方法及系统. CN: CN106686092A, 2017-05-17.
[133] 宋呈群, 程俊. 一种全景3D视频拼接系统及方法. CN: CN106657809A, 2017-05-10.
[134] 张丰, 程俊. 一种铲雪机器人及其铲雪方法. CN: CN106592499A, 2017-04-26.
[135] 张锲石, 程俊, 胡灵. 车辆轨迹预测方法及装置. CN: CN106558219A, 2017-04-05.
[136] 高向阳, 程俊, 郭海光. 一种中控系统. CN: CN106507244A, 2017-03-15.
[137] 郭海光, 程俊. 物联网设备及其网络配置方法、装置、系统和终端. CN: CN106411621A, 2017-02-15.
[138] 程俊, 侯云江. 酒店入住管理系统及方法. CN: CN106302547A, 2017-01-04.
[139] 王鹏, 程俊. 自动调料机. CN: CN205814227U, 2016-12-21.
[140] 侯云江, 程俊. 一种新型的智能锁具. CN: CN205302437U, 2016-06-08.
[141] 程俊, 姬晓鹏. 一种人体动作的识别方法及装置. CN: CN105608421A, 2016-05-25.
[142] 丁毅, 程俊. 基于双角度多频率条纹投影的三维形貌获取方法及装置. CN: CN105588518A, 2016-05-18.
[143] 程俊, 郭海光, 高向阳. 基于声波配置连接无线热点网络的摄像头. CN: CN205232324U, 2016-05-11.
[144] 程俊, 高向阳, 郭海光. 一种学习机. 中国: CN205230404U, 2016-05-11.
[145] 程俊, 郭海光, 高向阳. 一种安防读写终端. CN: CN205230083U, 2016-05-11.
[146] 程俊. 基于双角度单频率条纹投影的三维形貌测量方法及装置. CN: CN105547190A, 2016-05-04.
[147] 姬晓鹏, 程俊, 陶大鹏. 基于深度图像序列的人体动作识别的方法及系统. CN: CN105354528A, 2016-02-24.
[148] 陶大鹏, 程俊, 吴俊宏, 林旭, 潘亮亮. 一种室内场景的识别方法及装置. CN: CN104732209A, 2015-06-24.
[149] 庞建新, 程俊, 高向阳, 张丰. 一种可自动校正几何失真的投影机. CN: CN204302650U, 2015-04-29.
[150] 王鹏, 程俊, 何明. 一种导航方法及导航器. CN: CN104535072A, 2015-04-22.
[151] 王鹏, 程俊, 何明. 一种投影机的安装定位方法及装置. CN: CN104535051A, 2015-04-22.
[152] 何明, 程俊, 王鹏. 基于立体视觉匹配的图像采集抖动消除方法及装置. CN: CN104506775A, 2015-04-08.
[153] 庞建新, 程俊, 高向阳, 张丰. 一种可自动校正几何失真的投影机及其校正方法. CN: CN104460197A, 2015-03-25.
[154] 程俊, 何明, 王鹏. 一种图像前景的检测方法和检测系统. CN: CN104361584A, 2015-02-18.
[155] 王鹏, 程俊. 一种可穿戴式设备. CN: CN104238749A, 2014-12-24.
[156] 程俊, 沈三明, 姜军. 一种屏幕检测系统及方法. CN: CN103902953A, 2014-07-02.
[157] 方琎, 唐沐, 陈妍, 杜健, 梁璟彪, 王涛, 万喜, 金劲松, 程俊. 一种人机交互方法、终端及系统. CN: CN103777746A, 2014-05-07.
[158] 程俊, 王群, 张子锐, 郭疆, 沈三明. 一种虚拟触摸屏的方法、系统及计算设备. CN: CN103761011A, 2014-04-30.
[159] 方琎, 杜健, 陈妍, 唐沐, 金劲松, 程俊. 一种人机交互方法及相关设备、系统. CN: CN103729131A, 2014-04-16.
[160] 方琎, 金劲松, 程俊. 激光发射装置及人机交互系统. CN: CN103713797A, 2014-04-09.
[161] 方琎, 金劲松, 程俊. 人机交互系统及红外影像捕捉装置. CN: CN103713729A, 2014-04-09.
[162] 程俊, 姜军, 陈裕华, 吴新宇, 肖谦. 一种体感交互的方法及系统. CN: CN103646425A, 2014-03-19.
[163] 程俊, 姜军, 陈裕华, 吴新宇, 肖谦. 一种双目摄像机的标定方法、装置及双目摄像机. CN: CN103606149A, 2014-02-26.
[164] 朱金娟. 一种辅助教学系统. CN: CN103514768A, 2014-01-15.
[165] 程俊, 王鹏. 车载人机交互系统及方法. CN: CN103455144A, 2013-12-18.
[166] 庞建新, 程俊. 一种基于徒手和单目摄像头实现人机交互的方法和装置. CN: CN103440034A, 2013-12-11.
[167] 庞建新, 程俊. 一种基于徒手和单目摄像头实现人机交互的方法和装置. CN: CN103440033A, 2013-12-11.
[168] 程俊, 王群, 沈三明. 一种基于指尖定位的投影交互方法、系统及计算设备. CN: CN103383731A, 2013-11-06.
[169] 程俊, 姜军, 沈三明. 机器人（老人服务）. CN: CN302612604S, 2013-10-23.
[170] 程俊, 姜军, 沈三明. 机器人（下棋）. CN: CN302612605S, 2013-10-23.
[171] 程俊, 姜军, 陈裕华. 冲压件表面缺陷检测装置及方法. CN: CN103245671A, 2013-08-14.
[172] 卢宗庆, 张家访, 王肇, 程俊, 姜军. 同轴调节方法. CN: CN103115925A, 2013-05-22.
[173] 程俊, 陶大程, 陈裕华, 姜军, 张子锐. 一种用于目标跟踪的人机交互装置及方法. CN: CN103020983A, 2013-04-03.
[174] 程俊, 陶大程, 陈裕华, 张子锐. 人机交互设备及人机交互方法. CN: CN102945078A, 2013-02-27.
[175] 程俊, 陶大程, 沈三明, 姜军. 平整度检测装置和方法. CN: CN102853786A, 2013-01-02.
[176] 程俊, 陈裕华, 张子锐. 基于云计算的智能头盔网络系统及其视频信息处理方法. CN: CN102833516A, 2012-12-19.
[177] 程俊, 陈裕华, 张子锐. 一种提供实时场景地图的装置. CN: CN102831816A, 2012-12-19.
[178] 张家访. 夹持装置. CN: CN202330303U, 2012-07-11.
[179] 卢宗庆, 王肇, 张家访, 程俊, 姜军. 灯检机. 中国: CN202330302U, 2012-07-11.
[180] 程俊, 姜军, 卢宗庆, 王肇, 李坡. 基于机器视觉的表面缺陷检测装置. CN: CN202330294U, 2012-07-11.
[181] 郭海光, 程俊, 高向阳. 网络摄像头. CN: CN301715060S, 2011-11-02.
[182] 程俊, 姜军, 宋展, 王肇, 郭海光, 陈曦, 袁术海, 陈光. 人机交互系统. CN: CN201955771U, 2011-08-31.
[183] 徐扬生, 覃剑钊, 程俊, 吴新宇, 李崇国. 一种智能音频辨识系统及辨识方法. CN: CN101067930B, 2011-06-29.
[184] 程俊, 高向阳, 薛源, 王群, 张丰, 陈光, 赵文闯. 跌倒监测与报警系统. CN: CN201829026U, 2011-05-11.
[185] 程俊, 姜军, 宋展, 王肇, 郭海光, 陈曦, 袁术海, 陈光. 人机交互方法及系统. CN: CN102012740A, 2011-04-13.
[186] 程俊, 赵文闯, 陈光, 谢灿, 谢琪, 高向阳, 张丰. 人体中标记物的识别方法及装置. CN: CN101996317A, 2011-03-30.
[187] 程俊, 谢灿, 陈光, 赵文闯, 谢琪, 高向阳, 张丰. 手势识别方法和系统. CN: CN101976330A, 2011-02-16.
[188] 程俊, 高向阳, 张丰, 薛源, 王群, 陈光, 赵文闯. 跌倒监测与报警的方法和系统. CN: CN101950464A, 2011-01-19.
[189] 毕亚雷, 胡晓伟, 程俊, 刘伟, 沈玲玲. 即时通讯伴侣机器人. CN: CN201611889U, 2010-10-20.
[190] 毕亚雷, 胡晓伟, 程俊, 刘伟, 沈玲玲. 即时通讯伴侣机器人及具有通讯伴侣的即时通讯方法. CN: CN101808047A, 2010-08-18.
[191] 程俊, 张丰, 王峰. 一种基于图像识别技术的嵌入式豆类分类系统. CN: CN101788497A, 2010-07-28.
[192] 程俊, 姜军. 一种针对投射条纹图像的残差滤波方法. CN: CN101726264A, 2010-06-09.
[193] 徐扬生, 李崇国, 阎镜予, 程俊, 吴新宇. 一种智能聊天系统及其实现方法. CN: CN101075435A, 2007-11-21.

   

[1] 许震宇, 孟乐年, 张锲石, 程俊, Hamad AlJassmi, Babitha Philip. AGA-RFNN: Adaptive genetic algorithm-based random forest neural network for pavement deterioration prediction. IEEE International Conference on Real-time Computing and Robotics (RCAR)null. 2023, [2] 刘鹏磊, 张锲石, 程俊. GSNet: model reconstruction network for category-level 6D object pose and size estimation. IEEE International Conference on Robotics and Automation (ICRA)null. 2023, [3] Hao, Fusheng, Wu, Fuxiang, He, Fengxiang, Zhang, Qieshi, Song, Chengqun, Cheng, Jun. Semantic-Aware Feature Aggregation for Few-Shot Image Classification. NEURAL PROCESSING LETTERS. 2023, [4] Wang, Lei, Liu, Xunyu, Ma, Xiaoliang, Wu, Jiaji, Cheng, Jun, Zhou, Mengchu. A Progressive Quadric Graph Convolutional Network for 3D Human Mesh Recovery. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2023, 33(1): 104-117, http://dx.doi.org/10.1109/TCSVT.2022.3199201.
[5] 张锲石, 欧阳祖薇, 任子良, 许震宇, 程俊. CUCN: Continuously updated connection network for low-light image enhancement. Journal of Electronic Imaging[J]. 2023, 32(3): [6] 吴福祥, 郝富生, 张锲石, 程俊. InDecGAN: Learning to Generate Complex Images from Captions via Independent Object-Level Decomposition and Enhancement. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2023, [7] 王玥, 龚茗荣, Lei Xia, 张锲石, 程俊. Efficiently fusing sparse LiDAR for enhanced Self-supervised Monocular Depth Estimation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)null. 2023, [8] 程俊, 张胜. BMFN3D: Bidirectional multilayer fusion network for indoor 3D object detectionBMFN3D: Bidirectional multilayer fusion network for indoor 3D object detection. ELECTRONICS LETTERS[J]. 2022, 696-698, [9] 程俊. EEP-Net:Enhancing Local Neighborhood Features and Efficient Semantic Segmentation of Scale Point Clouds. Conference on Pattern Recognition and Computer Visionnull. 2022, [10] Hushan Qin, Jun Cheng, Chengqun Song, Fusheng Hao, Qin Cheng. Structure-Preserving View-Invariant Skeleton Representation for Action Detection. 26th International Conference on Pattern Recognition (ICPR2022)null. 2022, [11] Tong Su, Chengqun Song, Jun Cheng. Vision Transformer with Imformation Bottleneck for Fine-grained. 2022 International Conference on Guidance, Navigation and Control (ICGNC 2022)null. 2022, [12] Cheng, Jun, Wang, Lei, Wu, Jiaji, Hu, Xiping, Jeon, Gwanggil, Tao, Dacheng, Zhou, Mengchu. Visual Relationship Detection: A Survey. IEEE TRANSACTIONS ON CYBERNETICS[J]. 2022, 52(8): 8453-8466, http://dx.doi.org/10.1109/TCYB.2022.3142013.
[13] 程俊. Heuristic semantic segmentation using the weights of local voxel structure. International Conference on Guidance, Navigation and Controlnull. 2022, [14] Liu, Zhen, Cheng, Jun, Liu, Libo, Ren, Ziliang, Zhang, Qieshi, Song, Chengqun. Dual-stream cross-modality fusion transformer for RGB-D action recognition. KNOWLEDGE-BASED SYSTEMS[J]. 2022, 255: http://dx.doi.org/10.1016/j.knosys.2022.109741.
[15] Cheng, Jun, Wu, Fuxiang, Tian, Yanling, Wang, Lei, Tao, Dapeng. RiFeGAN2: Rich Feature Generation for Text-to-Image Synthesis From Constrained Prior Knowledge. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2022, 32(8): 5187-5200, http://dx.doi.org/10.1109/TCSVT.2021.3136857.
[16] 康宇航, 程俊. 联合连通有向切换拓扑条件下无人机集群鲁棒编队控制. 中国科学-技术科学[J]. 2022, [17] Wu, Yiqiang, Wang, Ruxin, Gong, Mingming, Cheng, Jun, Yu, Zhengtao, Tao, Dapeng. Adversarial UV-Transformation Texture Estimation for 3D Face Aging. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2022, 32(7): 4338-4350, http://dx.doi.org/10.1109/TCSVT.2021.3133313.
[18] Kang, Yuhang, Luo, Delin, Xin, Bin, Cheng, Jun, Yang, Tangwen, Zhou, Shaolei. Robust Leaderless Time-Varying Formation Control for Nonlinear Unmanned Aerial Vehicle Swarm System With Communication Delays. IEEE TRANSACTIONS ON CYBERNETICS. 2022, http://dx.doi.org/10.1109/TCYB.2022.3165007.
[19] 吴福祥, 程俊. Language-based Image Manipulation Built on Language-Guided Ranking. IEEE Transactions on Multimedia[J]. 2022, [20] Tong Su, Shuo Ye, Chengqun Song, Jun Cheng. MASK-VIT: An object mask embedding in vision transformer for fine-grained visual classification. 2022 IEEE International Conference on Image Processing (ICIP 2022)null. 2022, [21] 吴福祥, 程俊. 基于自编码器生成对抗网络的可配置文本图像编辑. 软件学报[J]. 2022, 33(9): 3139-3151, http://lib.cqvip.com/Qikan/Article/Detail?id=7108016763.
[22] 程俊. 自动驾驶场景下的轨迹预测综述. 计算机工程[J]. 2022, [23] 程俊. Mask-ViT: An Object Mask Embedding in Vision Transformer for Fine-Graind Visual Classification. International Conference on Image Processingnull. 2022, [24] Cheng, Jun, Hao, Fusheng, Liu, Liu, Tao, Dacheng. Imposing Semantic Consistency of Local Descriptors for Few-Shot Learning. IEEE TRANSACTIONS ON IMAGE PROCESSING[J]. 2022, 31: 1587-1600, http://dx.doi.org/10.1109/TIP.2022.3143692.
[25] 宋呈群, 程俊, 曾驳, 苏童, 张可, 张锲石. 基于深度扭曲的无监督深度学习视觉SLAM. 2022国际制导、导航与控制学术会议（ICGNC2022）null. 2022, [26] 程俊. GAN-SLAM: GAN based Monocular Visual-Inertial Simultaneous Localization and Mapping in Dark Environments. International Symposium on Autonomous Systemsnull. 2022, [27] 程俊. Reject Decoding via Language-Vision Models for Text-to-Image Synthesis. AAAI Conference on Artificial Intelligencenull. 2022, [28] 程俊. Text-to-Image Synthesis based on Object-Guided Joint-Decoding Transformer. Conference on Computer Vision and Pattern Recognitionnull. 2022, [29] 程俊. Character animation and retargeting from video streams. IEEE International Conference on Systems, Man, and Cyberneticsnull. 2022, [30] Chengqun Song, Bo Zeng, Tong Su, Ke Zhang, Jun Cheng. Data association and loop closure in semantic dynamic SLAM using the table retrieval method. Applied Intelligence[J]. 2022, 2022: https://doi.org/10.1007/s10489-021-03091-x.
[31] Zhou, Yichao, Wu, Wanyin, Zou, Jie, Qiao, Jianwang, Cheng, Jun. Weighted ensemble networks for multiview based tiny object quality assessment. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE[J]. 2021, 33(6): http://dx.doi.org/10.1002/cpe.5995.
[32] Jun Cheng. Cross-Modality Compensation Convolutional Neural Networks for RGB-D Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2021, [33] Luo, Yun, Li, Gang, Xu, Weihai, Liu, Jianguo, Cheng, Jun, Zhao, Jianxin, Yan, Wen. The effect of diagenesis on rare earth element geochemistry of the Quaternary carbonates at an isolated coral atoll in the South China Sea. SEDIMENTARY GEOLOGY[J]. 2021, 420: http://dx.doi.org/10.1016/j.sedgeo.2021.105933.
[34] 康宇航, 戴洪德, 祁亚辉, 张邦楚, 刘玄冰, 程俊. 无人集群系统时变编队H_（∞）控制. 北京航空航天大学学报[J]. 2021, 47(2): 271-280, http://lib.cqvip.com/Qikan/Article/Detail?id=7104431144.
[35] Ji, Xiaopeng, Zhao, Qingsong, Cheng, Jun, Ma, Chenfei. Exploiting spatio-temporal representation for 3D human action recognition from depth map sequences. KNOWLEDGE-BASED SYSTEMS[J]. 2021, 227: http://dx.doi.org/10.1016/j.knosys.2021.107040.
[36] Zhang, Jin, Wu, Fuxiang, Wei, Bo, Zhang, Qieshi, Huang, Hui, Shah, Syed W, Cheng, Jun. Data Augmentation and Dense-LSTM for Human Activity Recognition Using WiFi Signal. IEEE INTERNET OF THINGS JOURNAL[J]. 2021, 8(6): 4628-4641, http://dx.doi.org/10.1109/JIOT.2020.3026732.
[37] Wu, Wanyin, Tao, Dapeng, Li, Hao, Yang, Zhao, Cheng, Jun. Deep features for person re-identification on metric learning. PATTERN RECOGNITION[J]. 2021, 110: http://dx.doi.org/10.1016/j.patcog.2020.107424.
[38] Rao, Haocong, Xu, Shihao, Hu, Xiping, Cheng, Jun, Hu, Bin. Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition. INFORMATION SCIENCES[J]. 2021, 569: 90-109, http://dx.doi.org/10.1016/j.ins.2021.04.023.
[39] Wang, Lei, Lin, Peizhen, Cheng, Jun, Liu, Feng, Ma, Xiaoliang, Yin, Jianqin. Visual relationship detection with recurrent attention and negative sampling. NEUROCOMPUTING[J]. 2021, 434: 55-66, http://dx.doi.org/10.1016/j.neucom.2020.12.099.
[40] Ren, Ziliang, Zhang, Qieshi, Cheng, Jun, Hao, Fusheng, Gao, Xiangyang. Segment spatial-temporal representation and cooperative learning of convolution neural networks for multimodal-based action recognition. NEUROCOMPUTING[J]. 2021, 433: 142-153, http://dx.doi.org/10.1016/j.neucom.2020.12.020.
[41] Zhang, Jin, Wei, Bo, Wu, Fuxiang, Dong, Limeng, Hu, Wen, Kanhere, Salil S, Luo, Chengwen, Yu, Shui, Cheng, Jun. Gate-ID: WiFi-Based Human Identification Irrespective of Walking Directions in Smart Home. IEEE INTERNET OF THINGS JOURNAL[J]. 2021, 8(9): 7610-7624, http://dx.doi.org/10.1109/JIOT.2020.3040782.
[42] Zhu, Kaijun, Wang, Ruxin, Zhao, Qingsong, Cheng, Jun, Tao, Dapeng. A Cuboid CNN Model With an Attention Mechanism for Skeleton-Based Action Recognition. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2020, 22(11): 2977-2989, http://dx.doi.org/10.1109/TMM.2019.2962304.
[43] Wang, Lei, Fan, Xiaoyun, Chen, Jiahao, Cheng, Jun, Tan, Jun, Ma, Xiaoliang. 3D object detection based on sparse convolution neural network and feature fusion for autonomous driving in smart cities. SUSTAINABLE CITIES AND SOCIETY[J]. 2020, 54: http://dx.doi.org/10.1016/j.scs.2019.102002.
[44] Ma, Zheng, Cheng, Jun, Tao, Dapeng. Online learning using projections onto shrinkage closed balls for adaptive brain-computer interface. PATTERN RECOGNITION[J]. 2020, 97: http://dx.doi.org/10.1016/j.patcog.2019.107017.
[45] Ren, Ziliang, Zhang, Qieshi, Qiao, Piye, Niu, Maolong, Gao, Xiangyang, Cheng, Jun. Joint learning of convolution neural networks for RGB-D-based human action recognition. ELECTRONICS LETTERS[J]. 2020, 56(21): 1112-1114, http://dx.doi.org/10.1049/el.2020.2148.
[46] Wang, Xueting, Cheng, Jun, Wang, Lei. A reinforcement learning-based predator-prey model. ECOLOGICAL COMPLEXITY[J]. 2020, 42: http://dx.doi.org/10.1016/j.ecocom.2020.100815.
[47] Wang, Peng, Cheng, Jun, Hao, Fusheng, Wang, Lei, Feng, Wei. Embedded adaptive cross-modulation neural network for few-shot learning. NEURAL COMPUTING & APPLICATIONS[J]. 2020, 32(10): 5505-5515, https://www.webofscience.com/wos/woscc/full-record/WOS:000529745200018.
[48] Cheng, Bo, Wu, Wanyin, Tao, Dapeng, Mei, Shibo, Mao, Ting, Cheng, Jun. Random Cropping Ensemble Neural Network for Image Classification in a Robotic Arm Grasping System. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT[J]. 2020, 69(9): 6795-6806, http://dx.doi.org/10.1109/TIM.2020.2976420.
[49] Ziliang Ren, Qieshi Zhang, Xiangyang Gao, Pengyi Hao, Jun Cheng. Multi-modality learning for human action recognition 多模态学习用于人体动作识别. MULTIMEDIA TOOLS AND APPLICATIONS,. 2020, http://kns.cnki.net/KCMS/detail/detail.aspx?QueryID=0&CurRec=32&recid=&FileName=SSJD3E0DB31BE7BDF4C8930F02BA964CB8C6&DbName=SSJD_01&DbCode=SSJD&yx=&pr=&URLID=&bsm=.
[50] Ning, Zhaolong, Hu, Xiping, Chen, Zhikui, Zhou, Mengchu, Hu, Bin, Cheng, Jun, Obaidat, Mohammad S. A Cooperative Quality-Aware Service Access System for Social Internet of Vehicles (vol 5, pg 2506, 2018). IEEE INTERNET OF THINGS JOURNALnull. 2020, 7(7): 6663-6663, https://www.webofscience.com/wos/woscc/full-record/WOS:000548817900083.
[51] Zhang, Qieshi, Cheng, Jun, Wang, Shengwen, Xu, Chengjun, Gao, Xiangyang. Point-selection and multi-level-point-feature fusion-based 3D point cloud classification. ELECTRONICS LETTERS[J]. 2020, 56(6): 291-+, https://www.webofscience.com/wos/woscc/full-record/WOS:000526243800012.
[52] Nie, Laisen, Ning, Zhaolong, Wang, Xiaojie, Hu, Xiping, Cheng, Jun, Li, Yongkang. Data-Driven Intrusion Detection for Intelligent Internet of Vehicles: A Deep Convolutional Neural Network-Based Method. IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING[J]. 2020, 7(4): 2219-2230, http://dx.doi.org/10.1109/TNSE.2020.2990984.
[53] Jun Cheng. Image Hallucination from Attribute Pairs. IEEE Transactions on Cybernetics. 2020, [54] Tian, Yanling, Du, Yubo, Zhang, Qieshi, Cheng, Jun, Yang, Zhuo. Depth estimation for advancing intelligent transport systems based on self-improving pyramid stereo network. IET INTELLIGENT TRANSPORT SYSTEMS[J]. 2020, 14(5): 338-345, https://doaj.org/article/0c3d0fc3adc743a3ad1285d16e7ce68e.
[55] Ma, Zheng, Xie, Zexin, Qiu, Tianshuang, Cheng, Jun. Driving event-related potential-based speller by localized posterior activities: An offline study. MATHEMATICAL BIOSCIENCES AND ENGINEERING[J]. 2020, 17(1): 789-801, https://doaj.org/article/c7fcc1b04853425787bfff06f33a724e.
[56] Xiang, Peng, Wang, Lei, Wu, Fuxiang, Cheng, Jun, Zhou, Mengchu. Single-Image De-Raining With Feature-Supervised Generative Adversarial Network. IEEE SIGNAL PROCESSING LETTERS[J]. 2019, 26(5): 650-654, https://www.webofscience.com/wos/woscc/full-record/WOS:000462389500001.
[57] Du, Yali, Fang, Meng, Yi, Jinfeng, Xu, Chang, Cheng, Jun, Tao, Dacheng. Enhancing the Robustness of Neural Collaborative Filtering Systems Under Malicious Attacks. IEEE TRANSACTIONS ON MULTIMEDIA[J]. 2019, 21(3): 555-565, http://dx.doi.org/10.1109/TMM.2018.2887018.
[58] Hao, Fusheng, Cheng, Jun, Wang, Lei, Cao, Jianzhong. Instance-Level Embedding Adaptation for Few-Shot Learning. IEEE ACCESS[J]. 2019, 7: 100501-100511, https://doaj.org/article/63b677d1964149348759f538effa9f34.
[59] Zhang, Jiao, Hu, Xiping, Ning, Zhaolong, Ngai, Edith CH, Zhou, Li, Wei, Jibo, Cheng, Jun, Hu, Bin, Leung, Victor C M. Joint Resource Allocation for Latency-Sensitive Services Over Mobile Edge Computing Networks With Caching. IEEE INTERNET OF THINGS JOURNAL[J]. 2019, 6(3): 4283-4294, https://www.webofscience.com/wos/woscc/full-record/WOS:000472596200024.
[60] Wang, Jiaqi, Wang, Siqi, Guo, Yanxiang, Hu, Xiping, Li, Xitong, Cheng, Jun, Bui, TX. Towards Intelligent Decision Making in Emotion-aware Applications. PROCEEDINGS OF THE 52ND ANNUAL HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCESnull. 2019, 2326-2334, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000625294902048.
[61] Wang, Jiaqi, Guo, Yanxiang, Han, Wenhan, Zheng, Jianbo, Peng, Hong, Hu, Xiping, Cheng, Jun. Mobile crowdsourcing based context-aware smart alarm sound for smart living. PERVASIVE AND MOBILE COMPUTING[J]. 2019, 55: 32-44, http://dx.doi.org/10.1016/j.pmcj.2019.02.003.
[62] Wang, Xueting, Cheng, Jun, Wang, Lei. Deep-Reinforcement Learning-Based Co-Evolution in a Predator-Prey System. ENTROPY[J]. 2019, 21(8): https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7515302/.
[63] Liu, Weifeng, Ma, Xuegi, Zhou, Yicong, Tao, Dapeng, Cheng, Jun. p-Laplacian Regularization for Scene Recognition. IEEE TRANSACTIONS ON CYBERNETICS[J]. 2019, 49(8): 2927-2940, http://dx.doi.org/10.1109/TCYB.2018.2833843.
[64] Hao, Fusheng, He, Fengxiang, Cheng, Jun, Wang, Lei, Cao, Jianzhong, Tao, Dacheng, IEEE. Collect and Select: Semantic Alignment Metric Learning for Few-Shot Learning. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)null. 2019, 8459-8468, [65] Tao, Dapeng, Cheng, Jun, Yu, Zhengtao, Yue, Kun, Wang, Lizhen. Domain-Weighted Majority Voting for Crowdsourcing. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2019, 30(1): 163-174, http://dx.doi.org/10.1109/TNNLS.2018.2836969.
[66] Shen, Zhijuan, Cheng, Jun, Hu, Xiping, Dong, Qian, IEEE. EMOTION RECOGNITION BASED ON MULTI-VIEW BODY GESTURES. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2019, 3317-3321, [67] Zhang Weitong, Zhang Qieshi, Cheng Jun, Bai Cong, Hao Pengyi, IEEE. END-TO-END PANOPTIC SEGMENTATION WITH PIXEL-LEVEL NON-OVERLAPPING EMBEDDING. 2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)null. 2019, 976-981, [68] 程俊, 王淑红, 黄怡, 颜文. 天然气水合物赋存区甲烷渗漏活动的地球化学响应特征. 海洋科学[J]. 2019, 43(5): 110-122, http://lib.cqvip.com/Qikan/Article/Detail?id=7100062907.
[69] Zhou, Lihua, Du, Guowang, Wang, Ruxin, Tao, Dapeng, Wang, Lizhen, Cheng, Jun, Wang, Jing. A tensor framework for geosensor data forecasting of significant societal events. PATTERN RECOGNITION[J]. 2019, 88: 27-37, http://dx.doi.org/10.1016/j.patcog.2018.10.021.
[70] Ma, Senwei, Fan, Xiaoyuan, Wang, Lei, Cheng, Jun, Xu, Chengjun, Yu, H, Liu, J, Liu, L, Ju, Z, Liu, Y, Zhou, D. Neural Network Based Electronics Segmentation. INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2019, PT Vnull. 2019, 11744: 528-540, [71] Cheng, Jun, Huang, Yi, Wang, Shuhong, Miao, Li, Yan, Wen. Transect variations and controlling factors of redox-sensitive trace element compositions of surface sediments in the South China Sea. CONTINENTAL SHELF RESEARCH[J]. 2019, 190: http://dx.doi.org/10.1016/j.csr.2019.103978.
[72] He, Kangjian, Wang, Ruxin, Tao, Dapeng, Cheng, Jun, Liu, Weifeng. Color Transfer Pulse-Coupled Neural Networks for Underwater Robotic Visual Systems. IEEE ACCESS[J]. 2018, 6: 32850-32860, http://ir.siat.ac.cn:8080/handle/172644/13579.
[73] Qin Wu, Jiashuo Cao, Chuang Zhou, Ji Huang, Zhuo Li, ShinMing Cheng, Jun Cheng, Guanghui Pan. Intelligent Smoke Alarm System with Wireless Sensor Network Using ZigBee. WIRELESS COMMUNICATIONS AND MOBILE COMPUTING[J]. 2018, https://doaj.org/article/db5a8255033e4fbf8d48bd528fec63b6.
[74] Liu, Weifeng, Zhang, Lianbo, Tao, Dapeng, Cheng, Jun. Reinforcement online learning for emotion prediction by using physiological signals. PATTERN RECOGNITION LETTERS[J]. 2018, 107: 123-130, http://ir.siat.ac.cn:8080/handle/172644/13569.
[75] Liu, Weifeng, Yang, Xinghao, Tao, Dapeng, Cheng, Jun, Tang, Yuanyan. Multiview dimension reduction via Hessian multiset canonical correlations. INFORMATION FUSION[J]. 2018, 41: 119-128, http://ir.siat.ac.cn:8080/handle/172644/13566.
[76] Zhang, Jiao, Hu, Xiping, Ning, Zhaolong, Ngai, Edith C H, Zhou, Li, Wei, Jibo, Cheng, Jun, Hu, Bin. Energy-Latency Tradeoff for Energy-Aware Offloading in Mobile Edge Computing Networks. IEEE INTERNET OF THINGS JOURNAL[J]. 2018, 5(4): 2633-2645, http://ir.siat.ac.cn:8080/handle/172644/13580.
[77] Wang Peng, Cheng Jun, Feng Wei, IEEE. An Approach for Construct Semantic Map with Scene Classification and Object Semantic Segmentation. PROCEEDINGS OF 2018 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (IEEE RCAR)null. 2018, 270-275, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000459211400046.
[78] Tian, Yanling, Zhang, Weitong, Zhang, Qieshi, Cheng, Jun, Hao, Pengyi, Lu, Gang, Cheng, L, Leung, ACS, Ozawa, S. Co-consistent Regularization with Discriminative Feature for Zero-Shot Learning. NEURAL INFORMATION PROCESSING (ICONIP 2018), PT Inull. 2018, 11301: 33-45, http://dx.doi.org/10.1007/978-3-030-04167-0_4.
[79] Wang, Peng, Cheng, Jun, Feng, Wei. Efficient construction of topological semantic map with 3D information. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS[J]. 2018, 35(3): 3011-3020, http://ir.siat.ac.cn:8080/handle/172644/13570.
[80] Wang, Lei, Xu, Yangyang, Cheng, Jun, Xia, Haiying, Yin, Jianqin, Wu, Jiaji. Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks. IEEE ACCESS[J]. 2018, 6: 17913-17922, https://doaj.org/article/dfc201b37e5246aa93d59f56c0e38c59.
[81] Pan Liangliang, Cheng Jun, Zhang Qieshi, IEEE. UFSM_VO: STEREO ODOMETRY BASED ON UNIFORMLY FEATURE SELECTION AND STRICTLY CORRESPONDENCE MATCHING. 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)null. 2018, 4148-4152, [82] Xu, Yangyang, Cheng, Jun, Wang, Lei, Xia, Haiying, Liu, Feng, Tao, Dapeng. Ensemble One-Dimensional Convolution Neural Networks for Skeleton-Based Action Recognition. IEEE SIGNAL PROCESSING LETTERS[J]. 2018, 25(7): 1044-1048, http://dx.doi.org/10.1109/LSP.2018.2841649.
[83] Hu, Xiping, Cheng, Jun, Zhou, Mengchu, Hu, Bin, Jiang, Xin, Guo, Yi, Bai, Kun, Wang, Fei. Emotion-Aware Cognitive System Multi-Channel Cognitive Radio Ad Hoc Networks. IEEE COMMUNICATIONS MAGAZINE[J]. 2018, 56(4): 180-187, http://dx.doi.org/10.1109/MCOM.2018.1700728.
[84] Ji, Xiaopeng, Cheng, Jun, Feng, Wei, Tao, Dapeng. Skeleton embedded motion body partition for human action recognition using depth sequences. SIGNAL PROCESSING[J]. 2018, 143: 56-68, http://dx.doi.org/10.1016/j.sigpro.2017.08.016.
[85] Hu, Xiping, Li, Xitong, Tan, Wei, Cheng, Jun, Zhou, Mengchu, Kwok, Ricky Y K. Special Issue on Advancing Intelligent Automation in Sharing Economy. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERINGnull. 2018, 15(4): 1443-1447, https://www.webofscience.com/wos/woscc/full-record/WOS:000446862400002.
[86] Guo, Yanxiang, Hu, Xiping, Hu, Bin, Cheng, Jun, Zhou, Mengchu, Kwok, Ricky Y K. Mobile Cyber Physical Systems: Current Challenges and Future Networking Applications. IEEE ACCESS[J]. 2018, 6: 12360-12368, https://doaj.org/article/4d171b8fcb424655b783888d581b012c.
[87] Li Yi, Cheng Jun, Ji Xiaopeng, Feng Wei, Tao Dapeng, IEEE. Real-time Action Recognition by Feature-level Fusion of Depth and Inertial Sensor. 2017 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (RCAR)null. 2017, 109-114, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000428364400019.
[88] Song, Chengqun, Cheng, Jun, Feng, Wei. A Crowdsensing-Based Real-Time System for Finger Interactions in Intelligent Transport System. WIRELESS COMMUNICATIONS & MOBILE COMPUTING[J]. 2017, https://doaj.org/article/b885260ec3014b69b843bbf3e1e763fd.
[89] Liu, Weifeng, Ma, Tengzhou, Xie, Qiangsheng, Tao, Dapeng, Cheng, Jun. LMAE: A large margin Auto-Encoders for classification. SIGNAL PROCESSING[J]. 2017, 141: 137-143, http://dx.doi.org/10.1016/j.sigpro.2017.05.030.
[90] Zhan, Shu, Chang, Lele, Zhao, Jingjing, Kurihara, Toru, Du, Hao, Tang, Yucheng, Cheng, Jun. Real-time 3D face modeling based on 3D face imaging. NEUROCOMPUTING[J]. 2017, 252: 42-48, http://dx.doi.org/10.1016/j.neucom.2016.10.091.
[91] Liu, Rong, Wang, Yongxuan, Wu, Xinyu, Cheng, Jun. Sequential Probability Ratio Testing with Power Projective Base Method Improves Decision-Making for BCI. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE[J]. 2017, 2017: https://doaj.org/article/e68f7e527561474e9a7bf824f23d4ec0.
[92] Yang, Xinghao, Liu, Weifeng, Tao, Dapeng, Cheng, Jun. Canonical correlation analysis networks for two-view image recognition. INFORMATION SCIENCES[J]. 2017, 385: 338-352, http://dx.doi.org/10.1016/j.ins.2017.01.011.
[93] Ji, Xiaopeng, Cheng, Jun, Tao, Dapeng, Wu, Xinyu, Feng, Wei. The spatial Laplacian and temporal energy pyramid representation for human action recognition using depth sequences. KNOWLEDGE-BASED SYSTEMS[J]. 2017, 122: 64-74, http://dx.doi.org/10.1016/j.knosys.2017.01.035.
[94] Tao, Dapeng, Cheng, Jun, Gao, Xinbo, Li, Xuelong, Deng, Cheng. Robust Sparse Coding for Mobile Image Labeling on the Cloud. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2017, 27(1): 62-72, http://dx.doi.org/10.1109/TCSVT.2016.2539778.
[95] Xiang Peng, Wang Lei, Cheng Jun, Zhang Bin, Wu Jiaji, IEEE. A Deep Network Architecture for Image Inpainting. PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC)null. 2017, 1851-1856, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000440623601179.
[96] Xu Yangyang, Wang Lei, Cheng Jun, Xia Haiying, Yin Jianqin, IEEE. DTA:Double LSTM with Temporal-wise Attention Network for Action Recognition. PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC)null. 2017, 1676-1680, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000440623601145.
[97] Xiping Hu, Jun Cheng, Xitong Li, Wei Tan, Qiang Liu, Zhengguo Sheng. Mobile Cyber-Physical System. MOBILE INFORMATION SYSTEMS[J]. 2017, 2017: https://doaj.org/article/f27df4261fd647e9a75677b2b96bdfae.
[98] Guo, Yanan, Tao, Dapeng, Liu, Weifeng, Cheng, Jun. Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS[J]. 2017, 47(4): 617-627, http://dx.doi.org/10.1109/TSMC.2016.2617465.
[99] Song, Chengqun, Cheng, Jun. A robust projector-camera interactive display system based on finger touch control by fusing finger and its shadow. JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY[J]. 2017, 25(9): 568-576, https://www.webofscience.com/wos/woscc/full-record/WOS:000418201800005.
[100] 宋呈群, 程俊. 基于视觉的投影-摄像机指尖触控系统. 集成技术[J]. 2017, 6(1): 8-15, http://lib.cqvip.com/Qikan/Article/Detail?id=671192404.
[101] Ding, Yi, Xi, Jiangtao, Yu, Yanguang, Deng, Fuqin, Cheng, Jun. Recovering the absolute phase maps of three selected spatial-frequency fringes with multi-color channels. NEUROCOMPUTING[J]. 2017, 252: 17-23, http://dx.doi.org/10.1016/j.neucom.2016.04.074.
[102] Chengqun Song, Jun Cheng, Wei Feng. A Crowdsensing-Based Real-Time System for Finger Interactions in Intelligent Transport System. WIRELESS COMMUNICATIONS AND MOBILE COMPUTING[J]. 2017, https://doaj.org/article/b885260ec3014b69b843bbf3e1e763fd.
[103] Zhang, Peng, Zhuo, Tao, Zhang, Yanning, Tao, Dapeng, Cheng, Jun. Online tracking based on efficient transductive learning with sample matching costs. NEUROCOMPUTING[J]. 2016, 175: 166-176, http://dx.doi.org/10.1016/j.neucom.2015.10.046.
[104] Zhang, Jian, Yu, Jun, You, Jane, Tao, Dapeng, Li, Na, Cheng, Jun. Data-driven facial animation via semi-supervised local patch alignment. PATTERN RECOGNITION[J]. 2016, 57: 1-20, http://dx.doi.org/10.1016/j.patcog.2016.02.021.
[105] Tao, Dapeng, Cheng, Jun, Song, Mingli, Lin, Xu. Manifold Ranking-Based Matrix Factorization for Saliency Detection. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2016, 27(6): 1122-1134, https://www.webofscience.com/wos/woscc/full-record/WOS:000377113300002.
[106] Chen Baowen, Jiang Jun, Cheng Jun, Chen Jie, IEEE. Integration of a Stereo Matching Algorithm on Chip for Real-Time 3-D Sensing. 2016 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (IEEE RCAR)null. 2016, 416-421, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000391370200075.
[107] Hong, Chaoqun, Zhu, Jianke, Yu, Jun, Cheng, Jun, Chen, Xuhui. Realtime and robust object matching with a large number of templates. MULTIMEDIA TOOLS AND APPLICATIONS[J]. 2016, 75(3): 1459-1480, [108] Yang, Xipeng, Cheng, Jun, Feng, Wei, Liang, Hong, Bai, Zhengyao, Tao, Dapeng. Cauchy estimator discriminant analysis for face recognition. NEUROCOMPUTING[J]. 2016, 199: 144-153, http://dx.doi.org/10.1016/j.neucom.2016.03.026.
[109] Chen, YenLun, Wu, Xinyu, Li, Teng, Cheng, Jun, Ou, Yongsheng, Xu, Mingliang. Dimensionality reduction of data sequences for human activity recognition. NEUROCOMPUTING[J]. 2016, 210: 294-302, http://www.corc.org.cn/handle/1471x/2156126.
[110] Li, Xiaoyan, He, Hongjie, Wang, Ruxin, Cheng, Jun. Superpixel-guided nonlocal means for image denoising and super-resolution. SIGNAL PROCESSING[J]. 2016, 124: 173-183, http://dx.doi.org/10.1016/j.sigpro.2015.09.021.
[111] Yang Xipeng, Cheng Jun, Feng Wei, Liang Hong, Bai Zhengyao, Tao Dapeng, IEEE. Face Recognition By Combining Cauchy Estimator and Discriminant Analysis. 2016 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (IEEE RCAR)null. 2016, 352-356, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000391370200063.
[112] Guo, Huiwen, Wu, Xinyu, Cai, Shibo, Li, Nannan, Cheng, Jun, Chen, YenLun. Quaternion discrete cosine transformation signature analysis in crowd scenes for abnormal event detection. NEUROCOMPUTING[J]. 2016, 204: 106-115, http://dx.doi.org/10.1016/j.neucom.2015.07.153.
[113] 何明, 程俊. 基于指尖触控的互动投影系统. 集成技术[J]. 2016, 48-56, http://lib.cqvip.com/Qikan/Article/Detail?id=667935361.
[114] Cheng, Jun, Wang, Qun, Song, Rui, Wu, Xinyu. Fingertip-based interactive projector-camera system. SIGNAL PROCESSING[J]. 2015, 110: 54-66, http://dx.doi.org/10.1016/j.sigpro.2014.08.043.
[115] Li, Xiaoyan, He, Hongjie, Yin, Zhongke, Chen, Fan, Cheng, Jun. KPLS-based image super-resolution using clustering and weighted boosting. NEUROCOMPUTING[J]. 2015, 149: 940-948, http://dx.doi.org/10.1016/j.neucom.2014.07.040.
[116] Tao, Dapeng, Cheng, Jun, Lin, Xu, Yu, Jiang. Local structure preserving discriminative projections for RGB-D sensor-based scene classification. INFORMATION SCIENCES[J]. 2015, 320: 383-394, https://www.webofscience.com/wos/woscc/full-record/WOS:000359029900023.
[117] Yu, Jun, Tao, Dapeng, Li, Jonathan, Cheng, Jun. Semantic preserving distance metric learning and applications. INFORMATION SCIENCES[J]. 2014, 281: 674-686, http://dx.doi.org/10.1016/j.ins.2014.01.025.
[118] Qiao, Maoying, Cheng, Jun, Bian, Wei, Tao, Dacheng. Biview Learning for Human Posture Segmentation from 3D Points Cloud. PLOS ONE[J]. 2014, 9(1): http://dx.doi.org/10.1371/journal.pone.0085811.
[119] Liu, Weifeng, Tao, Dacheng, Cheng, Jun, Tang, Yuanyan. Multiview Hessian discriminative sparse coding for image annotation. COMPUTER VISION AND IMAGE UNDERSTANDING[J]. 2014, 118: 50-60, http://dx.doi.org/10.1016/j.cviu.2013.03.007.
[120] Gui, Jie, Sun, Zhenan, Cheng, Jun, Ji, Shuiwang, Wu, Xindong. How to Estimate the Regularization Parameter for Spectral Regression Discriminant Analysis and its Kernel Version?. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY[J]. 2014, 24(2): 211-223, https://www.webofscience.com/wos/woscc/full-record/WOS:000331379600004.
[121] Li, Xiaoyan, He, Hongjie, Yin, Zhongke, Chen, Fan, Cheng, Jun. Single image super-resolution via subspace projection and neighbor embedding. NEUROCOMPUTING[J]. 2014, 139: 310-320, http://dx.doi.org/10.1016/j.neucom.2014.02.026.
[122] Liu, Jigang, Liu, Dongquan, Cheng, Jun, Tang, Yuanyan. Conditional simultaneous localization and mapping: A robust visual SLAM system. NEUROCOMPUTING[J]. 2014, 145: 269-284, http://dx.doi.org/10.1016/j.neucom.2014.05.034.
[123] He, Ming, Cheng, Jun, Feng, Wei, IEEE. Real-time Albedo Contrast-based Hand Segmentation in Projector-Camera System. 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS IEEE-ROBIO 2014null. 2014, 937-942, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000380399500156.
[124] Jun Jiang, Jun Cheng, Baowen Chen, Wu, Xinyu. Disparity prediction between adjacent frames for dynamic scenes. NEUROCOMPUTING[J]. 2014, 142: 335-342, http://dx.doi.org/10.1016/j.neucom.2014.04.027.
[125] Haifeng Zhao, Jun Cheng, Jun Jiang, Dacheng Tao, IEEE. MULTIPLE INSTANCE LEARNING VIA DISTANCE METRIC OPTIMIZATION. 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)[J]. 2013, 2617-2621, [126] Cheng, Jun, Bian, Wei, Tao, Dacheng. Locally regularized sliced inverse regression based 3D hand gesture recognition on a dance robot. INFORMATION SCIENCES[J]. 2013, 221: 274-283, http://dx.doi.org/10.1016/j.ins.2012.09.002.
[127] Jun Cheng. Accurate and Robust Background Subtraction Method in Projector-camera System. International Conference on Artificial Intelligence and Computational Intelligence. 2013, [128] Guo, Jiang, Cheng, Jun, Pang, Jianxin, Guo, Yu, IEEE. REAL-TIME HAND DETECTION BASED ON MULTI-STAGE HOG-SVM CLASSIFIER. 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013)null. 2013, 4108-4111, [129] Cheng, Jun, Zheng, Shiguang, Wu, Xinyu. Structured light-based shape measurement system. SIGNAL PROCESSING[J]. 2013, 93(6): 1435-1444, http://dx.doi.org/10.1016/j.sigpro.2012.05.004.
[130] Jun Jiang, Jun Cheng. Rapid disparity prediction for dynamic scenes. International Symposium on Visual Computingnull. 2013, [131] Jiang Jun, Cheng Jun, Chen Baowen, Bebis G, Boyle R, Parvin B, Koracin D, Li B, Porikli F, Zordan V, Klosowski J, Coquillart S, Luo X, Chen M, Gotz D. Rapid Disparity Prediction for Dynamic ScenesA. ADVANCES IN VISUAL COMPUTING, ISVC 2013, PT Inull. 2013, 8033: 333-342, [132] Jun Cheng. Convert any Display Screen into a Touchscreen. 2013, [133] Jun Cheng. Human Action Recognition Framework by Fusing Multiple Features. IEEE International Conference on Information and Automation. 2013, [134] Yu, Jun, Tao, Dacheng, Rui, Yong, Cheng, Jun. Pairwise constraints based multiview features fusion for scene classification. PATTERN RECOGNITION[J]. 2013, 46(2): 483-496, http://dx.doi.org/10.1016/j.patcog.2012.08.006.
[135] Chen, YenLun, Cheng, Jun, Lin, Chuan, Wu, Xinyu, Ou, Yongsheng, Xu, Yangsheng. Classification-based learning by particle swarm optimization for wall-following robot navigation. NEUROCOMPUTING[J]. 2013, 113: 27-35, http://dx.doi.org/10.1016/j.neucom.2012.12.037.
[136] Deng, Xiaoyu, Liu, Xiao, Song, Mingli, Cheng, Jun, Bu, Jiajun, Chen, Chun. LF-EME: Local features with elastic manifold embedding for human action recognition. NEUROCOMPUTING[J]. 2013, 99: 144-153, http://dx.doi.org/10.1016/j.neucom.2012.06.011.
[137] Guo Jiang, Cheng Jun, Guo Yu, Pang Jianxin, Yarlagadda P, Kim YH. A Real-Time Dynamic Gesture Recognition System. MEASUREMENT TECHNOLOGY AND ENGINEERING RESEARCHES IN INDUSTRY, PTS 1-3null. 2013, 333-335: 849-855, [138] Chen Baowen, Jiang Jun, Cheng Jun, Shen Sanming, Verikas A, Vuksanovic B, Zhou J. A Defects Detection System for the Surfaces of Stampings. SIXTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2013)null. 2013, 9067: [139] Yu, Jun, Cheng, Jun, Tao, Dacheng. Interactive cartoon reusing by transfer learning. SIGNAL PROCESSING[J]. 2012, 92(9): 2147-2158, http://dx.doi.org/10.1016/j.sigpro.2012.01.028.
[140] Liu, Li, Liu, Jianming, Cheng, Jun, Wani, MA, Khoshgoftaar, T, Zhu, X, Seliya, N. Age-Group Classification of Facial Images. 2012 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2012), VOL 1null. 2012, 693-696, http://dx.doi.org/10.1109/ICMLA.2012.129.
[141] Jun Jiang, Jun Cheng, Dacheng Tao. Color Biological Features-Based Solder Paste Defects Detection and Classification on Printed Circuit Boards. IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY[J]. 2012, 2(9): 1536-1544, https://www.webofscience.com/wos/woscc/full-record/WOS:000308464200017.
[142] Jun Cheng. Energy Model Approach to Crowd Density Estimation for Abnormal Crowd Behavior Detection. Neurocomputing. 2012, [143] Yu, Jun, Bian, Wei, Song, Mingli, Cheng, Jun, Tao, Dacheng. Graph based transductive learning for cartoon correspondence construction. NEUROCOMPUTING[J]. 2012, 79: 105-114, http://dx.doi.org/10.1016/j.neucom.2011.10.003.
[144] 阮传扬, 邓飞其, 姜军, 程俊. 基于虚拟体育运动的散斑测距研究. 激光与光电子学进展[J]. 2012, 49(7): 071002-1, http://lib.cqvip.com/Qikan/Article/Detail?id=42520360.
[145] Cheng, Jun, Xie, Can, Bian, Wei, Tao, Dacheng. Feature fusion for 3D hand gesture recognition by learning a shared hidden space. PATTERN RECOGNITION LETTERS[J]. 2012, 33(4): 476-484, http://dx.doi.org/10.1016/j.patrec.2010.12.009.
[146] 赵文闯, 程俊. 深度图像中基于部位位置及尺寸的人体识别方法. 集成技术[J]. 2012, 10-14, http://lib.cqvip.com/Qikan/Article/Detail?id=3000000602.
[147] Xiong, Guogang, Cheng, Jun, Wu, Xinyu, Chen, YenLun, Ou, Yongsheng, Xu, Yangsheng. An energy model approach to people counting for abnormal crowd behavior detection. NEUROCOMPUTING[J]. 2012, 83: 121-135, http://dx.doi.org/10.1016/j.neucom.2011.12.007.
[148] Yu, Jun, Tao, Dacheng, Wang, Meng, Cheng, Jun. Semi-automatic cartoon generation by motion planning. MULTIMEDIA SYSTEMS[J]. 2011, 17(5): 409-419, https://www.webofscience.com/wos/woscc/full-record/WOS:000295040000005.
[149] Jun Jiang, Jun Cheng, Ying Zhou, Guang Chen. Clustering-driven residue filter for profile measurement system. JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION[J]. 2011, 28(2): 214-221, https://www.webofscience.com/wos/woscc/full-record/WOS:000286941900014.
[150] Jun Cheng. 3D Human Posture Segmentation by Constrained Spectral Clustering. Signal Processing. 2011, [151] Cheng Jun, Zheng Shiguang, Wu Xinyu, Wang DH, Reynolds M. Structured Light-Based Shape Measurement System of Human Body. AI 2011: ADVANCES IN ARTIFICIAL INTELLIGENCEnull. 2011, 7106: 531-539, [152] Jun Jiang, Jun Cheng, Bruno Luong. Unsupervised-clustering-driven noise-residue filter for phase images. APPLIED OPTICS[J]. 2010, 49(11): 2143-2150, https://www.webofscience.com/wos/woscc/full-record/WOS:000276612200020.
[153] Yuan Ruifeng, Cheng Jun, Li Pengcheng, Chen Guang, Xie Can, Xie Qi, IEEE. View Invariant Hand Gesture Recognition using 3D Trajectory. 20108THWORLDCONGRESSONINTELLIGENTCONTROLANDAUTOMATIONWCICAnull. 2010, 6315-6320, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000295959507005.
[154] Bian, Wei, Cheng, Jun, Tao, Dacheng, IEEE. BIASED ISOMAP PROJECTIONS FOR INTERACTIVE RERANKING. ICME: 2009 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-3null. 2009, 1632-+, [155] Wu, Xinyu, Chung, Wing Kwong, Cheng, Jun, Tong, Hang, Xu, Yangsheng. A Parallel-Structure Solder Paste Inspection System. IEEE-ASME TRANSACTIONS ON MECHATRONICS[J]. 2009, 14(5): 590-597, https://www.webofscience.com/wos/woscc/full-record/WOS:000269518700007.
[156] Yu, Zhai, Wang, Zhao, Cheng, Jun, Tian, Hw, Bi, K, Cai, J. Preliminary Study of a New Process to Improve the Strength of Thermo-sonic Ball Solder Joint. 2009 INTERNATIONAL CONFERENCE ON ELECTRONIC PACKAGING TECHNOLOGY & HIGH DENSITY PACKAGING (ICEPT-HDP 2009)null. 2009, 666-+, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000289501700141.
[157] 余斋, 王肇, 程俊, 田怀文. 热压超声球引线键合机理的探讨. 电子工艺技术[J]. 2009, 30(4): 190-195, http://lib.cqvip.com/Qikan/Article/Detail?id=30964477.
[158] Jun Cheng. NI Vision based Automatic Optical Inspection for Surface Mount Devices:Principle and Design. 2009 IEEE International Conference on Applied Superconductivity and ElectroMagnetic Devices. 2009, [159] 程俊, 王黎, 高晓蓉, 姜军, 薛骏. 基于圆投影与矢量和的旋转不变量检测方案. 计算机工程[J]. 2009, 35(21): 181-182,185, http://lib.cqvip.com/Qikan/Article/Detail?id=32019858.
[160] Jun Jiang, Jun Cheng, Xinglin Chen. Registration for 3-D point cloud using angular-invariant feature. NEUROCOMPUTING[J]. 2009, 72(16-18): 3839-3844, http://dx.doi.org/10.1016/j.neucom.2009.05.013.
[161] Jiang Jun, Cheng Jun, Chen Xinglin, Bebis G, Boyle R, Parvin B, Koracin D, Kuno Y, Wang J, Pajarola R, Lindstrom P, Hinkenjann A, Encarnacao ML, Silva CT, Coming D. Noise-Residue Filtering Based on Unsupervised Clustering for Phase Unwrapping. ADVANCES IN VISUAL COMPUTING, PT 2, PROCEEDINGSnull. 2009, 5876: 719-+, [162] Li Pengcheng, Cheng Jun, Yuan Ruifeng, Zhao Wenchuang, Bebis G, Boyle R, Parvin B, Koracin D, Kuno Y, Wang J, Pajarola R, Lindstrom P, Hinkenjann A, Encarnacao ML, Silva CT, Coming D. Robust 3D Marker Localization Using Multi-spectrum Sequences. ADVANCES IN VISUAL COMPUTING, PT 2, PROCEEDINGSnull. 2009, 5876: 529-537, [163] Zhao Huibin, Jin Jianxun, Cheng Jun, IEEE. Virtual Instrument Based Fuzzy Control System for PMLSM Drive. 2009 INTERNATIONAL CONFERENCE ON APPLIED SUPERCONDUCTIVITY AND ELECTROMAGNETIC DEVICESnull. 2009, 295-+, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000275122100073.
[164] Cheng, Jun, Chung, ChiKit Ronald, Lam, Edmund Y, Fung, Kenneth S M, Wang, Fan, Leung, W H. Structured-light based sensing using a single fixed fringe grating: Fringe boundary detection and 3-D reconstruction. IEEE TRANSACTIONS ON ELECTRONICS PACKAGING MANUFACTURING[J]. 2008, 31(1): 19-31, https://www.webofscience.com/wos/woscc/full-record/WOS:000252338300003.
[165] Zhang, Jianghua, Zeng, Youwen, Cheng, Jun, Tang, Xian. Optimization of permanent magnet guideway for HTS maglev vehicle with numerical methods. IEEE TRANSACTIONS ON APPLIED SUPERCONDUCTIVITY[J]. 2008, 18(3): 1681-1686, https://www.webofscience.com/wos/woscc/full-record/WOS:000259572500002.
[166] Jun Jiang, Jun Cheng, Xinlin Chen. A registration method based on angular-invariant feature. International Symposium on Systems & Controlnull. 2008, http://ir.siat.ac.cn:8080/handle/172644/2172.
[167] Jiang Jun, Cheng Jun, Chen Xinglin, Li D, Deng G. An effective automatic image enhancement method. CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 3, PROCEEDINGSnull. 2008, 289-293, http://dx.doi.org/10.1109/CISP.2008.351.
[168] Cheng, Jun, Chung, Ronald, Lam, Edmund Y, Fung, Kenneth S M, IEEE. Handling of Multi-reflections in Wafer Bump 3D Reconstruction. 2008 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC), VOLS 1-6null. 2008, 1557-+, [169] Xue Jun, Cheng Jun, Wang Li, Gao Xiaorong, Li D, Deng G. Visual monitoring-based railway grade crossing surveillance system. CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 2, PROCEEDINGSnull. 2008, 427-+, http://dx.doi.org/10.1109/CISP.2008.491.
[170] Xu, Fang, Cheng, Jun, Wang, Chao, IEEE. Real Time Face Tracking Using Particle Filtering and Mean Shift. 2008 IEEE INTERNATIONAL CONFERENCE ON AUTOMATION AND LOGISTICS, VOLS 1-6null. 2008, 2252-+, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000263554801143.
[171] Jun Cheng. Structure-Light based Sensing using a Single Fixed Fringe Grating: Fringe Boundary Detection and 3D Reconstruction. IEEE Trans. on Electronics Packaging Manufacturing. 2008, [172] Crowd Density Estimation Based on Image Potential Energy Model. http://ir.siat.ac.cn:8080/handle/172644/3426.
[173] Sub-pixel locating of surface mounting components. http://ir.siat.ac.cn:8080/handle/172644/2384.
[174] A robot dance system based on real-time beat prediction. http://ir.siat.ac.cn:8080/handle/172644/3842.
[175] A Spatiotemporal Tensor-Based Multi-Object Matching Algorithm. http://ir.siat.ac.cn:8080/handle/172644/2830.
[176] Model-based human pose estimation with hierarchical ICP from single depth images. http://ir.siat.ac.cn:8080/handle/172644/3251.
[177] 3D Reconstruction Based on Digital Speckle Correlation in Virtual Sport. http://ir.siat.ac.cn:8080/handle/172644/3837.
[178] Vision-based Hand Gesture Spotting and Recognition. http://ir.siat.ac.cn:8080/handle/172644/2833.
[179] Modeling and Simulation for the Permanent Magnet Linear Synchronous Motor based on Space Vector Pulse Width Modulation. http://ir.siat.ac.cn:8080/handle/172644/2831.
[180] LOCAL MEAN SPATIO-TEMPORAL FEATURE FOR DEPTH IMAGE-BASED SPEED-UP ACTION RECOGNITION. http://ir.siat.ac.cn:8080/handle/172644/6798.
[181] Fingertip-based interactive projector-camera system. http://ir.siat.ac.cn:8080/handle/172644/6682.
[182] Object Tracking and Trajectory Recognition Using Improved CAMSHIFT and Hidden Markov Model. http://ir.siat.ac.cn:8080/handle/172644/3843.
[183] A Locating Algorithm Based on OGHT for PCB Mark Orientation. http://ir.siat.ac.cn:8080/handle/172644/2829.
[184] Projection optics design for tilted projection of fringe pattern. http://ir.siat.ac.cn:8080/handle/172644/2144.

   

（ 1 ） 广东省机器人与智能信息技术创新团队, 参与, 省级, 2011-03--2015-12
（ 2 ） 印刷电路板自动化制造系统产业化, 主持, 部委级, 2014-04--2015-12
（ 3 ） 面向可穿戴设备的人体行为识别关键技术研究, 主持, 省级, 2014-05--2016-04
（ 4 ） 基于机器视觉的人体三维运动捕捉系统关键技术研究, 主持, 省级, 2013-06--2015-05
（ 5 ） 基于深度图像的体感交互系统研究, 主持, 省级, 2013-07--2015-06
（ 6 ） 互联网机器人智能应用平台和人机交互关键技术研究, 参与, 省级, 2012-01--2015-01
（ 7 ） 基于移动互联网的智能穿戴式设备关键技术研究与产业化, 参与, 国家级, 2014-01--2015-12
（ 8 ） 面向智能制造的机器视觉关键技术研究, 参与, 省级, 2014-07--2016-06
（ 9 ） 中国科学院人机智能协同系统重点实验室, 参与, 部委级, 2015-01--2016-12
（ 10 ） 大推力潜油直线电机关键技术研究, 参与, 省级, 2014-07--2016-06
（ 11 ） 智能深度相机及体感交互关键技术研究与产业化, 主持, 省级, 2016-01--2017-12
（ 12 ） 基于增强现实技术的智能教育互动关键技术研究, 主持, 省级, 2016-06--2018-06
（ 13 ） 面向智能硬件的云服务平台, 主持, 省级, 2016-06--2018-06
（ 14 ） 基于视觉跟踪技术的增强现实系统关键技术研发, 主持, 省级, 2016-04--2018-03
（ 15 ） 智能服务机器人联合实验室, 主持, 院级, 2015-11--2018-10
（ 16 ） 可穿戴设备智能云服务技术研究, 主持, 院级, 2015-12--2018-06
（ 17 ） 深圳3D内容制作技术工程实验室, 主持, 省级, 2016-01--2017-12
（ 18 ） 基于RGB-D图像序列和加速度信号融合的人体动作识别方法研究, 主持, 国家级, 2018-01--2021-12
（ 19 ） 面向柔性定制作业的工业机器人视觉感知与理解问题研究, 主持, 国家级, 2018-01--2021-12
（ 20 ） 头戴式智能显示设备与智能感知交互系统关键技术研发和产业化, 主持, 省级, 2017-06--2019-06
（ 21 ） 深圳3D内容制作技术工程实验室, 主持, 省级, 2017-05--2018-12
（ 22 ） 基于视觉的自动驾驶汽车行驶轨迹预测关键算法研究, 主持, 省级, 2019-02--2022-01
（ 23 ） 面向五金行业制造的国产机器人系统应用示范, 主持, 国家级, 2019-05--2022-04
（ 24 ） 机器人多机协同与智能控制技术, 参与, 省级, 2019-05--2022-04
（ 25 ） 核电站复杂系统人机交互研究, 主持, 院级, 2019-01--2020-06

已指导学生

李鹏程  硕士研究生  081201-计算机系统结构  

袁瑞丰  硕士研究生  081201-计算机系统结构  

谢琪  硕士研究生  081203-计算机应用技术  

谢灿  硕士研究生  081203-计算机应用技术  

乔卯英  硕士研究生  081203-计算机应用技术  

郑士光  硕士研究生  430112-计算机技术  

王群  硕士研究生  430112-计算机技术  

郭疆  硕士研究生  430112-计算机技术  

张子锐  硕士研究生  430112-计算机技术  

肖谦  硕士研究生  085208-电子与通信工程  

何明  硕士研究生  081002-信号与信息处理  

李懿  硕士研究生  081104-模式识别与智能系统  

王鹏  博士研究生  081104-模式识别与智能系统  

姬晓鹏  博士研究生  081104-模式识别与智能系统  

潘亮亮  硕士研究生  085208-电子与通信工程  

郝洛莹  硕士研究生  081104-模式识别与智能系统  

赵青松  硕士研究生  085211-计算机技术  

李宏建  硕士研究生  085211-计算机技术  

沈志娟  硕士研究生  085210-控制工程  

现指导学生

王飞  博士研究生  081104-模式识别与智能系统  

孙士杰  硕士研究生  085211-计算机技术  

刘鹏磊  博士研究生  081104-模式识别与智能系统  

范筱媛  硕士研究生  085211-计算机技术  

闫浩  硕士研究生  085211-计算机技术  

马科伟  硕士研究生  085400-电子信息  

刘桢  硕士研究生  085400-电子信息  

秦虎山  硕士研究生  085400-电子信息  

曾驳  硕士研究生  085400-电子信息