{"id":24,"date":"2019-10-22T14:14:02","date_gmt":"2019-10-22T14:14:02","guid":{"rendered":"http:\/\/wenxiusun.com\/wordpress\/?page_id=24"},"modified":"2024-10-08T05:51:37","modified_gmt":"2024-10-08T05:51:37","slug":"wenxiu-sun-%e5%ad%ab%e6%96%87%e7%a7%80-ph-d","status":"publish","type":"page","link":"http:\/\/wenxiusun.com\/","title":{"rendered":"Homepage"},"content":{"rendered":"\n<div class=\"hero-image\"><p><\/p><h3>Wenxiu Sun (\u5b6b\u6587\u79c0, Ph.D.)<\/h3><br>Research Director at <a href=\"https:\/\/www.sensetime.com\/\">SenseTime Group Limited<\/a><br>Email: sunwx at sensetime dot com<p><\/p><\/div>\n\n\n\n<h3 class=\"wp-block-heading has-text-align-left\"><strong>Biography<\/strong><\/h3>\n\n\n\n<p>I received the Ph.D. degree from the Electronic and Computer Engineering,\u00a0<a href=\"https:\/\/hkust.edu.hk\/home\">The Hong Kong University of Science and Technology (HKUST)<\/a>\u00a0in 2014, and B.Eng. degree from the School of Electronic &amp; Electrical Engineering,\u00a0<a href=\"https:\/\/www.nju.edu.cn\/en\/main.psp\">Nanjing University<\/a>\u00a0in 2009. During my Ph.D. study from Sep. 2009 to Mar. 2014, I was supervised by Prof. Oscar C. Au. From Sep. to Dec. 2012, I visited\u00a0<a href=\"http:\/\/www.nii.ac.jp\/\">National Institute of Informatics (NII)<\/a>\u00a0as a research intern under the supervision of\u00a0<a href=\"https:\/\/www.eecs.yorku.ca\/~genec\/index.html\">Prof. Gene Cheung<\/a>. <br><br>I&#8217;m interested in large language models and computer vision. In particular, I worked on depth sensing, segmentation, and image processing to solve real-world problems. Currently, I&#8217;m focusing on LLM evaluation and development to advance the progress of the next AGI.<br><br>I am currently working at SenseTime as a Research Director and <strong>recruiting self-motivated researchers and engineers<\/strong> who is eager and patient to make contributions to the world. If interested, please drop your CV to my email.<br><br><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>News<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>We are hosting an ECCV 2022 workshop, details will be available soon!<\/li>\n\n\n\n<li>2 papers accepted to ICCV 2021<\/li>\n\n\n\n<li>2 papers accepted to CVPR 2021<\/li>\n\n\n\n<li>1 paper accepted to ICLR 2021<\/li>\n\n\n\n<li>1 paper accepted to TPAMI 2020<\/li>\n\n\n\n<li>2 papers accepted to ECCV 2020<\/li>\n\n\n\n<li>No. 1 in ECCV <a href=\"https:\/\/data.vision.ee.ethz.ch\/cvl\/aim20\/\">AIM 2020<\/a> Video Interpolation Challenge<\/li>\n\n\n\n<li>1 paper accepted to TIP 2020<\/li>\n\n\n\n<li>1 paper accepted to ICML 2020<\/li>\n\n\n\n<li>2 papers accepted to CVPR 202020<\/li>\n\n\n\n<li>No. 1 in ICCV <a href=\"http:\/\/www.vision.ee.ethz.ch\/aim19\/\">AIM 2019<\/a> Video Interpolation Challenge<\/li>\n\n\n\n<li>1 paper accepted as spotlight to NeurIPS 2019<\/li>\n\n\n\n<li>2 papers accepted to ICCV 2019<\/li>\n\n\n\n<li>3 papers accepted to CVPR 2019<br><\/li>\n<\/ul>\n\n\n\n<div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<h3 class=\"wp-block-heading\"><strong>Press<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>2019.12.11 <a href=\"https:\/\/mp.weixin.qq.com\/s\/7IMTVYu7Z3XJpyv4SLKPmA\">GiveMeFive\u4e28\u5546\u6c64\u4e94\u5e74\uff0c\u4ece0\u5230N\u7684\u5feb\u901f\u8fdb\u51fb <\/a><\/li>\n\n\n\n<li>2023.09.26 contributed in Video Frame Interpolation <a href=\"https:\/\/www.sohu.com\/a\/723683383_99963310\">\u300a\u5b64\u6ce8\u4e00\u63b7\u300b\u706b\u7206\u6709\u539f\u56e0\uff0c\u9664\u4e86\u5267\u60c5\u597d\uff0c\u8fd8\u6709\u795e\u79d8AI\u529b\u91cf<\/a><\/li>\n\n\n\n<li>2023.10.31 contributed in RGB-D Fusion <a href=\"https:\/\/news.mydrivers.com\/1\/942\/942873.htm\">\u9a81\u9f998 Gen 3 \u6b63\u5f0f\u53d1\u5e03, \u6167\u9ca4\u643a\u624b\u9ad8\u901a\u4e3a\u624b\u673a\u6ce8\u5165AI \u8d85\u80fd\u529b <\/a><\/li>\n\n\n\n<li>2023.11.08 contributed in Video Frame Interpolation <a href=\"https:\/\/www.xiaoyuzhoufm.com\/episode\/654bbb2063f913837c8c5ebc\">\u7f16\u7801\u4eba\u58f0\uff1a\u4ece\u9ed1\u767d\u7535\u89c6\u5230\u300a\u5b64\u6ce8\u4e00\u63b7\u300b\uff0c\u804a\u804a\u51b0\u5c71\u4e0b\u7684\u9ad8\u6e05\u6280\u672f <\/a><\/li>\n\n\n\n<li>2023.11.10 contributed in Video Frame Interpolation <a href=\"https:\/\/mp.weixin.qq.com\/s\/rkH5XzwpXv8UQtkF4ZUzdg\">\u300a\u6d41\u6d6a\u5730\u7403\u300b3\u5b9a\u6863\uff0c\u7535\u5f71\u5de5\u4e1a\u53163.0\u65f6\u4ee3\uff0c\u5546\u6c64AI\u6709\u66f4\u591a\u201c\u620f\u4efd\u201d<\/a><\/li>\n\n\n\n<li>2024.09.23 China Daily Interview &#8220;Making the most of AI: Insights from Wenxiu&#8221; <a href=\"https:\/\/www.youtube.com\/watch?v=LjQXS4ry8_Q\" data-type=\"link\" data-id=\"https:\/\/www.youtube.com\/watch?v=LjQXS4ry8_Q\">Youtube Link<\/a> \/ <a href=\"https:\/\/www.chinadailyhk.com\/hk\/video?code=girl_city&amp;play_id=593638\">China Daily Link<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Selected Publications<\/strong><\/h3>\n\n\n\n<p><a href=\"https:\/\/openaccess.thecvf.com\/content\/ICCV2021\/papers\/Wang_Dual-Camera_Super-Resolution_With_Aligned_Attention_Modules_ICCV_2021_paper.pdf\">Dual-Camera Super-Resolution with Aligned Attention Modules<br><\/a>Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan, Qifeng Chen<br>International Conference on Computer Vision,&nbsp; (<strong>ICCV 2021<\/strong>) &#8211; <strong>Oral<\/strong><br>[<a href=\"https:\/\/github.com\/Tengfei-Wang\/DCSR\">code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2109.02974.pdf\">FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting<\/a><br>Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li<br>International Conference on Computer Vision,&nbsp; (<strong>ICCV 2021<\/strong>)<br><a href=\"https:\/\/github.com\/ruiliu-ai\/FuseFormer\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/papers\/Siyao_Deep_Animation_Video_Interpolation_in_the_Wild_CVPR_2021_paper.pdf\">Deep Animation Video Interpolation in the Wild<\/a><br>Li Siyao, Shiyu Zhao, Weijiang Yu, Wenxiu Sun, Dimitris Metaxas, Chen Change Loy, Ziwei Liu<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2021<\/strong>)<br><a href=\"https:\/\/github.com\/lisiyao21\/AnimeInterp\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2021\/papers\/Xie_Efficient_Regional_Memory_Network_for_Video_Object_Segmentation_CVPR_2021_paper.pdf\">Efficient Regional Memory Network for Video Object Segmentation<\/a><br>Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2021<\/strong>)<br>[<a href=\"https:\/\/github.com\/hzxie\/RMNet\">code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/openaccess.thecvf.com\/content\/CVPR2021W\/WAD\/papers\/He_Semi-Synthesis_A_Fast_Way_To_Produce_Effective_Datasets_for_Stereo_CVPRW_2021_paper.pdf\">Semi-synthesis: A fast way to produce effective datasets for stereo matching<br><\/a>Ju He, Enyu Zhou, Liusheng Sun, Fei Lei, Chenyang Liu, Wenxiu Sun<br>IEEE Conference on Computer Vision and Pattern Recognition &#8211; Workshop (<strong>CVPRW 2021<\/strong>)<\/p>\n\n\n\n<p>Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch<br>Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li<br>International Conference on Learning Representations (<strong>ICLR 2021<\/strong>)<br><a href=\"https:\/\/openreview.net\/forum?id=K9bw7vqp_s\">[open review]<\/a> <a href=\"https:\/\/iclr.cc\/virtual\/2021\/poster\/3174\">[presentation]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2102.01579.pdf\">Exploiting Raw Images for Real-Scene Super-Resolution<\/a><br>Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang<br>IEEE Transactions on Pattern Analysis and Machine Intelligence (<strong>T-PAMI, 2020<\/strong>)<br><\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2006.03761.pdf\">GRNet: Gridding Residual Network for Dense Point Cloud Completion<br><\/a>Haozhe Xie,&nbsp;Hongxun Yao,&nbsp;Shangchen Zhou,&nbsp;Jiageng Mao,&nbsp;Shengping Zhang,&nbsp;Wenxiu Sun<br>European Conference on Computer Vision,&nbsp; (<strong>ECCV 2020<\/strong>)<br><a href=\"https:\/\/github.com\/hzxie\/GRNet\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/www.ecva.net\/papers\/eccv_2020\/papers_ECCV\/papers\/123690715.pdf\">Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention<\/a><br>Quewei&nbsp;Li, Jie&nbsp;Guo, Yang&nbsp;Fei, Qinyu&nbsp;Tang, Wenxiu&nbsp;Sun, Jin&nbsp;Zeng, Yanwen&nbsp;Guo<br>European Conference on Computer Vision,&nbsp; (<strong>ECCV 2020<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/Yihao Liu, Liangbin Xie, Li Siyao, Wenxiu Sun, Yu Qiao, Chao Dong\">Enhanced Quadratic Video Interpolation<\/a><br>Yihao Liu,&nbsp;Liangbin Xie,&nbsp;Li Siyao,&nbsp;Wenxiu Sun,&nbsp;Yu Qiao,&nbsp;Chao Dong<br>European Conference on Computer Vision &#8211; AIM2020 Workshop,&nbsp; (<strong>ECCV 2020<\/strong>)<br>No. 1 in <a href=\"https:\/\/data.vision.ee.ethz.ch\/cvl\/aim20\/\">AIM2020<\/a> VTSR Challenge<br><a href=\"https:\/\/github.com\/lyh-18\/EQVI\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=9110760&amp;casa_token=Zgpvx_hHU1AAAAAA:Ji4px5PgUxlGEz7SMrjM2fAOPtGF_dhVgZNxDkQsmOSacHtZOCnCdr_ff4FYZyhiYUgNJgKW&amp;tag=1\">Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising<\/a><br>Xiangyu Xu, Muchen Li, Wenxiu Sun, Ming-Hsuan Yang<br>IEEE Transactions on Image Processing, VOL. 29, 2020,&nbsp; (<strong>TIP 2020<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/proceedings.mlr.press\/v119\/xu20f\/xu20f.pdf\">Learning Factorized Weight Matrix for Joint Filtering<\/a><br>Xiangyu Xu, Yongrui Ma, Wenxiu Sun<br>Proceedings of the 37th International Conference on Machine Learning,&nbsp; (<strong>ICML 2020<\/strong>)<\/p>\n\n\n\n<p><a href=\"javascript:void(0)\">Pix2Vox++: multi-scale context-aware 3D object reconstruction from single and multiple images<\/a><br>Haozhe Xie, Hongxun Yao, Shengping Zhang, Shangchen Zhou, Wenxiu Sun<br>International Journal of Computer Vision (<strong>IJCV2020<\/strong>)<br><a href=\"https:\/\/github.com\/hzxie\/Pix2Vox\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2008.05157.pdf\">Towards Geometry Guided Neural Relighting with Flash Photography<br><\/a>Di Qiu, Jin Zeng, Zhanghan Ke, Wenxiu Sun, Chengxi Yang<br>International Conference on 3D Vision (<strong>3DV 2020<\/strong>)<\/p>\n\n\n\n<p><a href=\"https:\/\/openaccess.thecvf.com\/content_CVPR_2020\/papers\/Liu_StereoGAN_Bridging_Synthetic-to-Real_Domain_Gap_by_Joint_Optimization_of_Domain_CVPR_2020_paper.pdf\">StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching<\/a><br>Rui Liu, Chengxi Yang, Wenxiu Sun, Xiaogang Wang, Hongsheng Li<br>Advances in Neural Information Processing Systems (<strong>CVPR 2020<\/strong>)<\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2003.12789.pdf\">Polarized Reflection Removal with Perfect Alignment in the Wild<\/a><br>Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan, Wenxiu Sun, Qifeng Chen<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2020<\/strong>)<br><a href=\"https:\/\/github.com\/ChenyangLEI\/polarization-reflection-removal\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"http:\/\/wenxiusun.com\">Quadratic Video Interpolation<\/a><br>Xiangyu Xu, Li Si-Yao, Wenxiu Sun, Qian Yin, Ming-Hsuan Yang<br>Advances in Neural Information Processing Systems (<strong>NeurIPS 2019<\/strong>) &#8211; <strong>Spotlight<\/strong><\/p>\n\n\n\n<p><a href=\"http:\/\/www.wenxiusun.com\">Quadratic Video Interpolation for VTSR Challenge<\/a><br>Li Si-Yao, Ze Pan, Xiangyu Xu, Wenxiu Sun<br>International Conference on Computer Vision &#8211; Workshop on Advances in Image Manipulation (<strong>ICCVW 2019<\/strong><em>)<\/em> <br><strong>No. 1<\/strong> in ICCV <a href=\"http:\/\/www.vision.ee.ethz.ch\/aim19\/\">AIM 2019<\/a> Video Interpolation Challenge<\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/1909.07623.pdf\">Dee<\/a><a rel=\"noreferrer noopener\" aria-label=\"p End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module  (opens in a new tab)\" href=\"http:\/\/openaccess.thecvf.com\/content_ICCV_2019\/papers\/Qiu_Deep_End-to-End_Alignment_and_Refinement_for_Time-of-Flight_RGB-D_Module_ICCV_2019_paper.pdf\" target=\"_blank\">p End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module <\/a><br>Di Qiu, Jiahao Pang, Wenxiu Sun, and Chengxi Yang<br>International Conference on Computer Vision (<strong>ICCV 2019<\/strong><em>)<\/em><br><a rel=\"noreferrer noopener\" aria-label=\" (opens in a new tab)\" href=\"https:\/\/github.com\/sylqiu\/tof_rgbd_processing\" target=\"_blank\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"http:\/\/wenxiusun.com\/wordpress\/wp-content\/uploads\/2019\/10\/Xu_Towards_Real_Scene_Super-Resolution_With_Raw_Images_CVPR_2019_paper.pdf\">Towards Real Scene Super-Resolution with Raw Images <\/a><br>Xiangyu Xu, Yongrui Ma, and Wenxiu Sun<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2019<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/wenxiusun.com\/wordpress\/wp-content\/uploads\/2019\/10\/Zeng_Deep_Surface_Normal_Estimation_With_Hierarchical_RGB-D_Fusion_CVPR_2019_paper.pdf\">Deep Surface Normal Estimation with Hierarchical RGB-D Fusion<\/a> <br>Jin Zeng, Yanfeng Tong, Yunmu Huang, Qiong Yan, Wenxiu Sun, Jing Chen, and Yongtian Wan<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2019<\/strong>)<br><a href=\"https:\/\/github.com\/jzengust\/RGBD2Normal\">[code]<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/1904.06903.pdf\">Learning Deformable Kernels for Image and Video Denoising<\/a><br>Xiangyu Xu, Muchen Li, and Wenxiu Sun<br><em>arXiv preprint arXiv:1904.06903<\/em>&nbsp;(2019).<\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/1809.09763.pdf\">DSR: Direct Self-rectification for Uncalibrated Dual-lens Cameras<\/a><br>Ruichao Xiao, Wenxiu Sun, Jiahao Pang, Qiong Yan, and Jimmy Ren<br>International Conference on 3D Vision (<strong>3DV 2018<\/strong>)<br>[<a href=\"https:\/\/github.com\/garroud\/self-rectification\">code<\/a>]\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_CVPRW_2019\/papers\/NTIRE\/Zeng_Deep_Graph_Laplacian_Regularization_for_Robust_Denoising_of_Real_Images_CVPRW_2019_paper.pdf\">Deep graph Laplacian regularization for robust denoising of real images<\/a><br>Jin Zeng, Jiahao Pang, Wenxiu Sun, and Gene Cheung<br> IEEE Conference on Computer Vision and Pattern Recognition &#8211; Workshop (<strong>CVPRW 2019<\/strong>)<\/p>\n\n\n\n<p><a href=\"https:\/\/www.ijcai.org\/proceedings\/2018\/0387.pdf\">Convolutional Memory Blocks for Depth Data Representation Learning<\/a><br>Keze Wang, Liang Lin, Chuangjie Ren, Wei Zhang, and Wenxiu Sun<br>The 27th International Joint Conference on Artificial Intelligence  (<strong>IJCAI 2018<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_ECCV_2018\/papers\/YuKang_Gan_Monocular_Depth_Estimation_ECCV_2018_paper.pdf\">Monocular depth estimation with affinity, vertical pooling, and label enhancement<\/a><br>Yukang Gan, Xiangyu Xu, Wenxiu Sun, and Liang Lin<br> European Conference on Computer Vision  (<strong>ECCV 2018<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Pang_Zoom_and_Learn_CVPR_2018_paper.pdf\">Zoom and learn: Generalizing deep stereo matching to novel domains<\/a><br>Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, and Liang Lin<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2018<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_ICCV_2017_workshops\/papers\/w17\/Pang_Cascade_Residual_Learning_ICCV_2017_paper.pdf\">Cascade residual learning: A two-stage convolutional neural network for stereo matching<\/a><br>Jiahao Pang, Wenxiu Sun, Jimmy SJ Ren, Chengxi Yang, and Qiong Yan<br>International Conference on Computer Vision (<strong>ICCV 2017<\/strong>)<br><strong>No. 1<\/strong> in <a href=\"http:\/\/www.cvlibs.net\/datasets\/kitti\/eval_scene_flow.php?benchmark=stereo\">KITTI2015<\/a> from Mar 2016 &#8211; Sep 2016<br> <a href=\"https:\/\/github.com\/Artifineuro\/crl\">[code]<\/a> <\/p>\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Luo_Single_View_Stereo_CVPR_2018_paper.pdf\">Single View Stereo Matching<\/a><br>Yue Luo, Jimmy S. Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2018<\/strong>) &#8211; <strong>spotlight<\/strong>.<\/p>\n\n\n\n<p><a href=\"http:\/\/openaccess.thecvf.com\/content_cvpr_2018\/papers\/Luo_LSTM_Pose_Machines_CVPR_2018_paper.pdf\">LSTM Pose Machines <\/a><br>Yue Luo, Jimmy S. Ren, Zhouxia Wang, Wenxiu Sun, Jinshan Pan, Jianbo Liu, Jiahao Pang, Liang Lin<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2018<\/strong>).<br>[<a href=\"https:\/\/github.com\/lawy623\/LSTM_Pose_Machines\">code<\/a>]\n\n\n\n<p><a href=\"https:\/\/zpascal.net\/cvpr2017\/Ren_Accurate_Single_Stage_CVPR_2017_paper.pdf\">Accurate Single Stage Detector Using Recurrent Rolling Convolution<\/a><br>Jimmy S. Ren, Xiaohao Chen, Jianbo Liu, Wenxiu Sun, Jiahao Pang, Qiong Yan, Yu-Wing Tai, Li Xu<br>IEEE Conference on Computer Vision and Pattern Recognition (<strong>CVPR 2017<\/strong>)<\/p>\n\n\n\n<p><a href=\"https:\/\/arxiv.org\/pdf\/1602.04364.pdf\">Look, Listen and Learn &#8211; A Multimodal LSTM for Speaker Identification<\/a><br>Jimmy S. Ren, Yongtao Hu, Yu-Wing Tai, Chuan Wang, Li Xu, Wenxiu Sun, Qiong Yan<br>The 30th AAAI Conference on Artificial Intelligence (<strong>AAAI 2016<\/strong>) &#8211;<strong> oral<\/strong><\/p>\n\n\n\n<p><a href=\"https:\/\/papers.nips.cc\/paper\/5774-shepard-convolutional-neural-networks.pdf\">Shepard Convolutional Neural Networks<\/a><br>Jimmy S. Ren, Li Xu, Qiong Yan, Wenxiu Sun<br>Advances in Neural Information Processing Systems (<strong>NeurIPS 2015<\/strong>)<\/p>\n\n\n\n<p><a href=\"http:\/\/wenxiusun.com\/wordpress\/wp-content\/uploads\/2019\/10\/sun_tip14.pdf\">Seamless View Synthesis through Texture Optimization<\/a><br>Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu<br>IEEE Trans. Image Processing, vol 23, no. 1, 2014.&nbsp;(<strong>TIP 2014<\/strong>)<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Awards<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>SenseTime Award, 2019<\/li>\n\n\n\n<li>No. 1 in <a href=\"https:\/\/data.vision.ee.ethz.ch\/cvl\/aim20\/\">AIM 2020<\/a> Video Interpolation Challenge<\/li>\n\n\n\n<li>No. 1 in <a href=\"http:\/\/www.vision.ee.ethz.ch\/aim19\/\">AIM 2019<\/a> Video Interpolation Challenge<\/li>\n\n\n\n<li>No. 1 in <a href=\"http:\/\/www.cvlibs.net\/datasets\/kitti\/eval_scene_flow.php?benchmark=stereo\">KITTI2015<\/a> from Mar 2016 &#8211; Sep 2016<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<p style=\"font-size:10px\"><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-cyan-bluish-gray-color\">UPDATED ON Oct 08, 2024<\/mark><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Wenxiu Sun (\u5b6b\u6587\u79c0, Ph.D.) Research Director at SenseTime Group LimitedEmail: sunwx at sensetime dot com Biography I received the Ph.D. degree from the Electronic and Computer Engineering,\u00a0The Hong Kong University of Science and Technology (HKUST)\u00a0in 2014, and B.Eng. degree from the School of Electronic &amp; Electrical Engineering,\u00a0Nanjing University\u00a0in 2009. During my Ph.D. study from Sep. [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-24","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/pages\/24"}],"collection":[{"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/wenxiusun.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=24"}],"version-history":[{"count":98,"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/pages\/24\/revisions"}],"predecessor-version":[{"id":221,"href":"http:\/\/wenxiusun.com\/index.php?rest_route=\/wp\/v2\/pages\/24\/revisions\/221"}],"wp:attachment":[{"href":"http:\/\/wenxiusun.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=24"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}