{"id":591436,"date":"2019-06-06T16:26:06","date_gmt":"2019-06-06T23:26:06","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-event&p=591436"},"modified":"2019-07-08T08:53:53","modified_gmt":"2019-07-08T15:53:53","slug":"microsoft-cvpr-2019","status":"publish","type":"msr-event","link":"https:\/\/www.microsoft.com\/en-us\/research\/event\/microsoft-cvpr-2019\/","title":{"rendered":"Microsoft @ CVPR 2019"},"content":{"rendered":"
Venue: <\/strong>Long Beach Convention & Entertainment Center (opens in new tab)<\/span><\/a><\/p>\n Website:<\/strong> CVPR 2019 (opens in new tab)<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Venue: Long Beach Convention & Entertainment Center Website: CVPR 2019<\/p>\n","protected":false},"featured_media":591529,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_startdate":"2019-06-16","msr_enddate":"2019-06-20","msr_location":"Long Beach, CA, USA","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"http:\/\/cvpr2019.thecvf.com\/attend\/registration","msr_event_link_redirect":false,"msr_event_time":"","msr_hide_region":false,"msr_private_event":false,"footnotes":""},"research-area":[13562],"msr-region":[197900],"msr-event-type":[197941],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-591436","msr-event","type-msr-event","status-publish","has-post-thumbnail","hentry","msr-research-area-computer-vision","msr-region-north-america","msr-event-type-conferences","msr-locale-en_us"],"msr_about":"Venue: <\/strong>Long Beach Convention & Entertainment Center<\/a>\r\n\r\nWebsite:<\/strong> CVPR 2019<\/a>","tab-content":[{"id":0,"name":"About","content":"Microsoft is excited to be a Diamond sponsor of CVPR 2019<\/a> June 16 \u2013 20 in Long Beach, CA. Stop by our booth to chat with our experts, see demos of our latest research and find out about\u00a0career opportunities<\/a>\u00a0with Microsoft.\r\nArea chairs<\/h3>\r\nAndrew Fitzgibbon<\/a>\r\nDavid Wipf<\/a>\r\nHarpreet Sawhney\r\nLu Yuan<\/a>\r\nZicheng Liu<\/a>\r\n
Microsoft attendees<\/h3>\r\nAbedelkader Asi\r\nAlex Hagiopol\r\nAlexandros Neophytou\r\nAli Ulusoy\r\nAman Orazaev\r\nAmey Parulkar\r\nAndrew Duan\r\nAndrew Fitzgibbon<\/a>\r\nAndrey Konin\r\nBaochen Sun<\/a>\r\nBaoguang Shi\r\nBogdan Burlacu\r\nBrent Ellwein\r\nBugra Tekin\r\nChengcheng Liu\r\nChien-Yi Wang\r\nChris Nuesmeyer\r\nChristopher Mei\r\nDianmu Zhang\r\nDinei Florencio<\/a>\r\nEmad Barsoum<\/a>\r\nEric Sommerlade\r\nFaezeh Amjadi\r\nFanny Nina Paravecino\r\nFederica Bogo<\/a>\r\nGeorg Klein\r\nG\u00fcnter Loch\r\nHamid Vaezi Joze<\/a>\r\nHanieh Deilamsalehy\r\nHao Jiang\r\nHao Yang\r\nHarpreet Sawhney\r\nHendrik Langerak\r\nHongli Deng\r\nHoudong Hu\r\nIshani Chakraborty\r\nIvan Razumeni\u0107\r\nIvan Tarapov<\/a>\r\nJianfeng Wang\r\nJingjing Shen\r\nJohannes Sch\u00f6nberger\r\nJohn Corring\r\nJohn Weiss<\/a>\r\nJun Ye\r\nKuan Lu\r\nLars Hulstaert\r\nLei Zhang<\/a>\r\nLeonardo Nunes\r\nLi Huang\r\nLiang-Chun Tsai\r\nLijuan Wang<\/a>\r\nLu Yuan<\/a>\r\nMandar Dixit\r\nMaria Zontak\r\nMax Kaznady\r\nMeenaz Merchant\r\nMei Chen\r\nMichael Bleyer\r\nMing Tan\r\nMithun Das Gupta\r\nMoshe Lutz<\/a>\r\nNaoto Usuyama\r\nNick Burton\r\nNick Ray\r\nNikola Milosavljevi\u0107\r\nNing Ma<\/a>\r\nNoranart Vesdapunt\r\nOlivia Klose\r\nOreste Ungureanu\r\nPablo Sala<\/a>\r\nPing Jin\r\nPrakruti Gogia\r\nPramod Sharma\r\nQi Ye\r\nQuanzeng You\r\nRamesh Kamasamodram\r\nRavi Theja Yada\r\nSamuel Ogden<\/a>\r\nSaurajit Mukherjee\r\nSean Kuno<\/a>\r\nSebastian Hack\r\nShang-Hong Lai\r\nSharat Chikkerur\r\nSilvano Galliani\r\nSophia Velastegui\r\nSurendra Ulabala\r\nTaras Khapko\r\nVictor Fragoso<\/a>\r\nWaleed Shahid\r\nXiaowei Hu\r\nXiaoyue Pu\r\nXikang Zhang\r\nXiyang Dai\r\nYale Song\r\nYatao Zhong\r\nYaw-Chern Lee\r\nYijuan Lu\r\nYi-Ling Chen\r\nZeyu Chen\r\nZhijun Zhang\r\nZhuangfei Wu"},{"id":1,"name":"Presentations","content":"
Microsoft presentation schedule<\/h2>\r\n
Sunday, June 16<\/h3>\r\n8:45 AM\u20135:05 PM | Hyatt Regency E (workshop)\r\nLearning from Unlabeled Videos<\/strong><\/a>\r\nCo-organizer: Yale Song<\/strong><\/a>\r\n\r\nMorning Session | Hyatt Regency A (workshop)\r\nImage Matching: Local Features & Beyond<\/strong><\/a>\r\nCo-organizer: Johannes L. Sch\u00f6nberger<\/strong>\r\n\r\n1:50 PM\u20136:00 PM | Hyatt Shoreline B (workshop)\r\nCEFRL 2019: 3rd International Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision 2019<\/strong><\/a>\r\nInvited Speaker: Jingdong Wang<\/strong><\/a>\r\n
Monday, June 17<\/h3>\r\n9:00 AM\u20135:00 PM | 102C (workshop)\r\nComputer Vision for Microscopy Image Analysis (CVMI)<\/strong><\/a>\r\nChair, Organizing Committee: Mei Chen<\/strong>\r\n\r\n9:00 AM\u20135:30 PM | Hyatt Regency G (workshop)\r\nDynaVis: The 1st International Workshop on Dynamic Scene Reconstruction<\/strong><\/a>\r\nKeynote Speaker: Andrew Fitzgibbon<\/strong><\/a>\r\n\r\n9:00 AM\u20135:00 PM | 103C (workshop)\r\nTarget Re-identification and Multi-Target Multi-Camera Tracking<\/strong><\/a>\r\nCo-organizers: Jingdong Wang<\/strong><\/a>\r\n\r\n9:00 AM\u20135:10 PM | 202C (workshop)\r\nThird Workshop on Computer Vision for AR\/VR<\/strong><\/a>\r\n9:10 AM\u20139:35 AM Keynote Speaker: Marc Pollefeys<\/strong><\/a>\r\n3:25 PM\u20133:50 PM Keynote Speaker: Andrew Fitzgibbon<\/strong><\/a>\r\n\r\nAfternoon Session | Hyatt Regency F (workshop)\r\nComputer Vision Applications for Mixed Reality Headsets<\/strong><\/a>\r\nOrganizers: Marc Pollefeys<\/strong><\/a>, Federica Bogo<\/strong><\/a>, Johannes Sch\u00f6nberger<\/strong>, Osman Ulusoy<\/strong>\r\nKeynote Speaker: Marc Pollefeys<\/strong><\/a>\r\n\r\nAfternoon session | Hyatt Beacon B (workshop)\r\nLong-Term Visual Localization under Changing Conditions<\/strong><\/a>\r\nCo-organizers: Marc Pollefeys<\/strong><\/a>, Johannes Sch\u00f6nberger<\/strong>, Pablo Speciale<\/strong>\r\n
Tuesday, June 18<\/h3>\r\n9:05 AM\u20139:10 AM (Oral)\r\nBAD SLAM: Bundle Adjusted Direct RGB-D SLAM<\/strong>\r\nThomas Sch\u00f6ps, Torsten Sattler, Marc Pollefeys<\/strong><\/a>\r\n\r\n9:10 AM\u20139:18 AM (Oral)\r\nRevealing Scenes by Inverting Structure from Motion Reconstructions<\/strong>\r\nFrancesco Pittaluga, Sanjeev J Koppal, Sing Bing Kang, Sudipta Sinha<\/strong><\/a>\r\n\r\n10:15 AM\u20131:00 PM | Poster #14\r\nLarge Scale Incremental Learning <\/strong>\r\nYue Wu, Yinpeng Chen<\/strong><\/a>, Lijuan Wang<\/strong><\/a>, Yuancheng Ye, Zicheng Liu<\/strong><\/a>, Yandong Guo; Yun Fu\r\n\r\n10:15 AM\u20131:00 PM | Poster #44\r\nDensely Semantically Aligned Person Re-Identification<\/strong>\r\nZhizheng Zhang, Cuiling Lan<\/strong><\/a>, Wenjun Zeng<\/strong><\/a>, Zhibo Chen\r\n\r\n10:15 AM\u20131:00 PM | Poster #47\r\nCyclic Guidance for Weakly Supervised Joint Detection and Segmentation<\/strong>\r\nYunhang Shen, Rongrong Ji, Yan Wang<\/strong>, Yongjian Wu, Liujuan Cao\r\n\r\n10:15 AM\u20131:00 PM | Poster #73\r\nBAD SLAM: Bundle Adjusted Direct RGB-D SLAM<\/strong>\r\nThomas Sch\u00f6ps, Torsten Sattler, Marc Pollefeys<\/strong><\/a>\r\n\r\n10:15 AM\u20131:00 PM | Poster #74\r\nRevealing Scenes by Inverting Structure from Motion Reconstructions<\/strong>\r\nFrancesco Pittaluga, Sanjeev J Koppal, Sing Bing Kang, Sudipta Sinha<\/strong><\/a>\r\n\r\n10:15 AM\u20131:00 PM | Poster #106\r\nImproving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training <\/strong>\r\nMahdi Abavisani, Hamid Vaezi Joze<\/strong><\/a>, Vishal Patel\r\n\r\n10:15 AM\u20131:00 PM | Poster #150\r\nLearning Pyramid-Context Encoder Network for High-Quality Image Inpainting <\/strong>\r\nYanhong Zeng, Jianlong Fu<\/strong><\/a>, Hongyang Chao, Baining Guo<\/strong><\/a>\r\n\r\n10:15 AM\u20131:00 PM | Poster #200\r\nPolysemous Visual-Semantic Embedding for Cross-Modal Retrieval<\/strong>\r\nYale Song<\/strong><\/a>, Mohammad Soleymani\r\n\r\n1:48 PM\u20131:53 PM (Oral)\r\nProgressive Pose Attention Transfer for Person Image Generation<\/strong>\r\nZhen Zhu, Tengteng Huang, Baoguang Shi<\/strong>, Miao Yu, Bofei Wang, Xiang Bai\r\n\r\n2:34 PM\u20132:42 PM (Oral)\r\nStructured Knowledge Distillation for Semantic Segmentation<\/strong>\r\nYifan Liu, Ke Chen<\/strong>, Chris Liu<\/strong>, Zengchang Qin, Zhenbo Luo, Jingdong Wang<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #83\r\nUnderstanding the Limitations of CNN-based Absolute Camera Pose Regression<\/strong>\r\nTorsten Sattler, Qunjie Zhou, Marc Pollefeys<\/strong><\/a>, Laura Leal-Taix\u00e9\r\n\r\n3:20 PM\u20136:00 PM | Poster #84\r\nDeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image <\/strong>\r\nJiaxiong Qiu, Zhaopeng Cui, Yinda Zhang, Xingdi Zhang, Shuaicheng Liu, Bing Zeng, Marc Pollefeys<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #96\r\nMask-Guided Portrait Editing with Conditional GANs<\/strong>\r\nShuyang V Gu, Jianmin Bao, Hao Yang<\/strong>, Dong Chen<\/strong><\/a>, Fang Wen<\/strong><\/a>, Lu Yuan<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #97\r\nGroup Sampling for Scale Invariant Face Detection <\/strong>\r\nXiang Ming, Fangyun Wei<\/strong>, Ting Zhang<\/strong><\/a>, Dong Chen<\/strong><\/a>, Fang Wen<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #117\r\nSPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking<\/strong>\r\nGuangting Wang, Chong Luo<\/strong><\/a>, Zhiwei Xiong, Wenjun Zeng<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #121\r\nProgressive Pose Attention Transfer for Person Image Generation<\/strong>\r\nZhen Zhu, Tengteng Huang, Baoguang Shi<\/strong>, Miao Yu, Bofei Wang, Xiang Bai\r\n\r\n3:20 PM\u20136:00 PM | Poster #177\r\nStructured Knowledge Distillation for Semantic Segmentation<\/strong>\r\nYifan Liu, Ke Chen<\/strong>, Chris Liu<\/strong>, Zengchang Qin, Zhenbo Luo, Jingdong Wang<\/strong><\/a>\r\n\r\n3:20 PM\u20136:00 PM | Poster #186\r\nRelational Knowledge Distillation<\/strong>\r\nWonpyo Park, Dongju Kim, Yan Lu<\/strong><\/a>, Minsu Cho\r\n\r\n3:20 PM\u20136:00 PM | Poster #194\r\nContext-Reinforced Semantic Segmentation<\/strong>\r\nYizhou Zhou, Xiaoyan Sun<\/strong><\/a>, Zheng-Jun, Wenjun Zeng<\/strong><\/a>\r\n
Wednesday, June 19<\/h3>\r\n8:40 AM\u20138:48 AM (Oral)\r\nDeeper and Wider Siamese Networks for Real-Time Visual Tracking<\/strong>\r\nZhipeng Zhang, Houwen Peng<\/strong>\r\n\r\n9:24 AM\u20139:29 AM (Oral)\r\nH+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions<\/strong>\r\nBugra Tekin<\/strong>, Federica Bogo<\/strong><\/a>, Marc Pollefeys<\/strong><\/a>\r\n\r\n9:42 AM\u20139:47 AM (Oral)\r\nA Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images<\/strong>\r\nJiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong<\/strong><\/a>\r\n\r\n9:52 AM\u201310:00 AM (Oral)\r\nGait Recognition via Disentangled Representation Learning<\/strong>\r\nZiyuan Zhang, Luan Tran, Xi Yin<\/strong>, Yousef A Atoum, Xiaoming Liu, Jian Wan, Nanxin Wang,\r\n\r\n10:00 AM\u201312:45 PM | Poster #46\r\nLooking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition<\/strong>\r\nHeliang Zheng, Jianlong Fu<\/strong><\/a>,<\/strong> Zheng-Jun Zha, Jiebo Luo\r\n\r\n10:00 AM\u201312:45 PM | Poster #95\r\nPrivacy Preserving Image-based Localization<\/strong>\r\nPablo Speciale<\/strong>, Johannes L Sch\u00f6nberger<\/strong>, Sing Bing Kang, Sudipta Sinha<\/strong><\/a>, Marc Pollefeys<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #99\r\nSynthesizing 3D Shapes from Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks<\/strong>\r\nXiao Li, Yue Dong<\/strong><\/a>, Pieter Peers, Xin Tong<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #115\r\nH+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions<\/strong>\r\nBugra Tekin<\/strong>, Federica Bogo<\/strong><\/a>, Marc Pollefeys<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #118\r\nA Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images<\/strong>\r\nJiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #126\r\nFace Parsing with RoI Tanh-warping<\/strong>\r\nJinpeng Lin, Hao Yang<\/strong>, Dong Chen<\/strong><\/a>, Ming Zeng, Fang Wen<\/strong><\/a>, Lu Yuan<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #130\r\nDeep High-Resolution Representation Learning for Human Pose Estimation<\/strong>\r\nKe Sun, Bin Xiao<\/strong>, Dong Liu, Jingdong Wang<\/strong><\/a>\r\n\r\n10:00 AM\u201312:45 PM | Poster #131\r\nFeature Transfer Learning for Face Recognition with Under-Represented Data<\/strong>\r\nXi Yin<\/strong>, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker\r\n\r\n10:00 AM\u201312:45 PM | Poster #137\r\nDeeper and Wider Siamese Networks for Real-Time Visual Tracking<\/strong>\r\nZhipeng Zhang, Houwen Peng<\/strong>\r\n\r\n10:00 AM\u201312:45 PM | Poster #149\r\nGait Recognition via Disentangled Representation Learning<\/strong>\r\nZiyuan Zhang, Luan Tran, Xi Yin<\/strong>, Yousef A Atoum, Xiaoming Liu, Nanxin Wang, Jian Wan\r\n\r\n10:00 AM\u201312:45 PM | Poster #187\r\nS4Net: Single Stage Salient-Instance Segmentation<\/strong>\r\nRuochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang<\/strong><\/a>, Shimin Hu\r\n\r\n10:00 AM\u201312:45 PM | Poster #210\r\nStoryGAN: A Sequential Conditional GAN for Story Visualization<\/strong>\r\nYitong Li, Zhe Gan<\/strong>, Yelong Shen<\/strong>, Jingjing Liu<\/strong><\/a>, Yu Cheng<\/strong>, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao<\/strong><\/a>\r\n\r\n1:58 PM\u20132:06 PM (Oral)\r\nReinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation<\/strong>\r\nXin Wang, Qiuyuan Huang<\/strong><\/a>, Asli Celikyilmaz<\/strong><\/a>, Jianfeng Gao<\/strong><\/a>, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, Lei Zhang<\/strong><\/a>\r\n\r\n3:05 PM\u20133:10 PM (Oral)\r\nTactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation<\/strong>\r\nLiyiming Ke, Xiujun Li<\/strong><\/a>, Yonatan Bisk, Ari Holtzman, Zhe Gan<\/strong>, Jingjing Liu<\/strong><\/a>, Jianfeng\u00a0Gao<\/strong><\/a>, Yejin Choi, Siddhartha Srinivasa\r\n\r\n3:20 PM\u20136:00 PM | Poster #1\r\nBidirectional Learning for Domain Adaptation of Semantic Segmentation<\/strong>\r\nYunsheng Li, Lu Yuan<\/strong><\/a>, Nuno Vasconcelos\r\n\r\n3:20 PM\u20136:00 PM | Poster #89\r\nTriangulation Learning Network: from Monocular to Stereo 3D Object Detection<\/strong>\r\nZengyi Qin, Jinglu Wang<\/strong><\/a>, Yan Lu<\/strong>\r\n\r\n3:20 PM\u20136:00 PM | Poster #93\r\nHybrid Scene Compression for Visual Localization<\/strong>\r\nFederico Camposeco, Andrea Cohen, Marc Pollefeys<\/strong><\/a>, Torsten Sattler\r\n\r\n3:20 PM\u20136:00 PM | Poster #155\r\nD2-Net: A Trainable CNN for Joint Description and Detection of Local Features<\/strong>\r\nMihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys<\/strong><\/a>, Josef Sivic, Akihiko Torii, Torsten Sattler\r\n\r\n3:20 PM\u20136:00 PM | Poster #164\r\nSingle Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements<\/strong>\r\nKaixuan Wei, Jiaolong Yang<\/strong><\/a>, Ying Fu, David Wipf<\/strong><\/a>, Hua Huang\r\n\r\n3:20 PM\u20136:00 PM | Poster #151\r\nDeep Exemplar-based Video Colorization<\/strong>\r\nBo Zhang, Mingming He, Jing Liao, Pedro Sander,