譚嘯

Xiao Tan

I have been working at the Dept. of Computer Vision, Baidu (Vis-Baidu) as a technical lead since 2018.

I Joined the Institute of Deep Learning (IDL) Baidu in Oct, 2016.

I Joined the Dept. of Computer Science the University of HongKong in Mar, 2015.

I received my PhD degree from the University of New South Wales in Nov, 2014.

I was sponsered by China Scholarship Council (CSC) for pursuing a PhD degree from 2010 to 2014.

I graduated from the FENG Bingquan Distinghuished Class, South China University of Technology in Sept, 2008.

Log

OCT 2021 We won the 1st place in video panoptic segmentation track of KITTI-STEP Challenge 2021 (joint with ICCV 2021).
July 2021 Two papers (about depth estimation / mono-3D object detection) are accepted to ICCV 2021.
July 2021 Our AGO-Net paper is accepted to TPAMI.
July 2021 Our CityScope, a vision system for AI-city, is announced.
July 2021 Three papers (two of which are about depth estimation and one of which is about video representation) are accepted to ACM-MM 2021.
June 2021 We won the 1st place in two tracks and the 2nd place in another two tracks in AI-city Challenge 2021 (joint with CVPR 2021).


Conferece Papers

2023

  • Zhe Liu, Xiaoqing Ye, Xiao Tan, Errui Ding, Xiang Bai. StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection in AAAI Conference on Artificial Intelligence (AAAI), 2023
  • Ruihang Chu, Zhengzhe Liu, Xiaoqing Ye, Xiao Tan , Xiaojuan Qi, Chi-Wing Fu, Jiaya Jia. Command-Driven Articulated Object Understanding and Manipulation in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  • Kaixin Xiong, Shi Gong, Xiaoqing Ye, Xiao Tan , Ji Wan, Errui Ding, Jingdong Wang, Xiang Bai. CAPE: Camera View Position Embedding for Multi-View 3D Object Detection in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  • Chang Chang, Weiming Zhang, Xiangru Lin, Wei Zhang, Xiao Tan , Junyu Han, Xiaomao Li, Errui Ding, Jingdong Wang. Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  • Jiacheng Zhang, Xiangru Lin, Wei Zhang, Kuo Wang, Xiao Tan , Junyu Han, Errui Ding, Jingdong Wang, Guanbin Li. Semi-DETR: Semi-Supervised Object Detection with Detection Transformers in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

    • 2022

  • Jianhui Liu, Yukang Chen, Xiaoqing Ye, Zhuotao Tian, Tan, Xiao , Xiaojuan Qi. Spatial Pruned Sparse Convolution for Efficient 3D Object Detection in Advances in Neural Information Processing Systems (NeurIPS), 2022
  • Yue He, Minyue Jiang, Xiaoqing Ye, Liang Du, Zhikang Zou, Wei Zhang, Xiao Tan , Errui Ding. Repainting and Imitating Learning for Lane Detection in ACM International Conference on Multimedia (ACMMM), 2022
  • Bo Ju, Zhikang Zou, Xiaoqing Ye, Minyue Jiang, Xiao Tan , Errui Ding, Jingdong Wang. Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network in ACM International Conference on Multimedia (ACMMM), 2022
  • Shi Gong, Xiaoqing Ye, Xiao Tan, Jingdong Wang, Errui Ding, Yu Zhou, Xiang Bai. GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation in European Conference on Computer Vision (ECCV), 2022
  • Linfeng Li, Minyue Jiang, Yue Yu, Wei Zhang, Xiangru Lin, Yingying Li, Xiao Tan, Jingdong Wang, Errui Ding. Diverse Learner: Exploring Diverse Supervision for Semi-supervised Object Detection in European Conference on Computer Vision (ECCV), 2022
  • Xiaoqing Ye, Mao Shu, Hanyu Li, Yifeng Shi，Yingying Li，GuangJie Wang, Xiao Tan，Errui Ding. Rope3D: Take A New Look from the 3D Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  • Ruihang Chu, Xiaoqing Ye, Zhengzhe Liu, Xiao Tan, Xiaojuan Qi, Chi-Wing Fu, Jiaya Jia. Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

    • 2021

  • Zhi Chen, Xiaoqing Ye, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang. Revealing the Reciprocal Relations between Self-Supervised Stereo and Monocular Depth Estimation in International Conference on Computer Vision (ICCV), 2021
  • Zhikang Zou, Xiaoqing Ye, Liang Du, Xianhui Chen, Xiao Tan, Li Zhang, Jianfeng Feng, Xiangyang Xue, Errui Ding. The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection in International Conference on Computer Vision (ICCV), 2021
  • Zhi Chen, Xiaoqing Ye, Liang Du, Wei Yang, Liusheng Huang, Xiao Tan, Zhenbo Shi, Fumin Shen, Errui Ding. AggNet for Self-supervised Monocular Depth Estimation: Go An Aggressive Step Further in ACM International Conference on Multimedia (ACMMM), 2021
  • Tianhao Fu, Yingying Li, Xiaoqing Ye, Xiao Tan, Hao Sun, Fumin Shen, Errui Ding. Lifting the Veil of Frequency in Joint Segmentation and Depth Estimation in ACM International Conference on Multimedia (ACMMM), 2021
  • Wenhao Wu, Yuxiang Zhao, Yanwu Xu, Xiao Tan, Dongliang He, Zhikang Zou, Jin Ye, Yingying Li, Mingde Yao, Zichao Dong, Yifeng Shi. DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning in ACM International Conference on Multimedia (ACMMM), 2021
  • Feng He, Qi Wang, Zhifan Feng, Wenbin Jiang, Yajuan Lü, Yong Zhu, Xiao Tan. Improving Video Retrieval by Adaptive Margin in ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021: 1359-1368
  • Minyue Jiang, Xuanmeng Zhang, Yue Yu, Zechen Bai, Zhedong Zheng, Zhigang Wang, Jian Wang, Xiao Tan, Hao Sun, Errui Ding, Yi Yang. Good practices and a strong baseline for traffic anomaly detection in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2021: 4026-4033
  • Jincheng Lu, Meng Xia, Xu Gao, Xipeng Yang, Tianran Tao, Hao Meng, Wei Zhang, Xiao Tan, Yifeng Shi, Guanbin Li, Errui Ding. Good practices and a strong baseline for traffic anomaly detection in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2021: 4002-4008
  • Yuxiang Zhao, Wenhao Wu, Yue He, Yingying Li, Xiao Tan, Shifeng Chen. Good practices and a strong baseline for traffic anomaly detection in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2021: 3993-4001
  • Jin Ye, Xipeng Yang, Shuai Kang, Yue He, Weiming Zhang, Leping Huang, Minyue Jiang, Wei Zhang, Yifeng Shi, Meng Xia, Xiao Tan. Good practices and a strong baseline for traffic anomaly detection in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2021: 4044-4053

    • 2020

  • Jie Wu, Yingying Li, Wei Zhang, Yi Wu, Xiao Tan, Hongwu Zhang, Shilei Wen, Errui Ding, Guanbin Li. Modularized Framework with Category-Sensitive Abnormal Filter for City Anomaly Detection in ACM International Conference on Multimedia (ACMMM), 2020: 4669-4673
  • Jinhui Liu, Zhikang Zou, Xiaoqing Ye, Xiao Tan, Errui Ding, Feng Xu, Xin Yu. Leaping from 2D detection to efficient 6DoF object pose estimation in European Conference on Computer Vision (ECCV), 2020: 707-714
  • Zhenbo Xu, Wei Zhang, Xiao Tan, Wei Yang, Huan Huang, Shilei Wen, Errui Ding, Liusheng Huang. Segment as points for efficient online multi-object tracking and segmentation in European Conference on Computer Vision (ECCV), 2020: 264-281
  • Zhenbo Xu, Wei Zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang. Zoomnet: Part-aware adaptive zooming neural network for 3d object detection in AAAI Conference on Artificial Intelligence (AAAI), 2020: 12557-12564
  • Xiaoqing Ye, Liang Du, Yifeng Shi, Yingying Li, Xiao Tan, Jianfeng Feng, Errui Ding, Shilei Wen. Monocular 3d object detection via feature domain adaptation in European Conference on Computer Vision (ECCV), 2020: 17--34
  • Yingying Li, Jie Wu, Xue Bai, Xipeng Yang, Xiao Tan, Guanbin Li, Shilei Wen, Hongwu Zhang, Errui Ding. Going beyond real data: A robust visual representation for vehicle re-identification in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2020: 586-587
  • Zhedong Zheng, Minyue Jiang, Zhigang Wang, Jian Wang, Zechen Bai, Xuanmeng Zhang, Xin Yu, Xiao Tan, Yi Yang, Shilei Wen, Errui Ding. Multi-granularity tracking with modularlized components for unsupervised vehicles anomaly detection in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2020: 598-599
  • Zhongji Liu, Wei Zhang, Xu Gao, Hao Meng, Xiao Tan, Xiaoxing Zhu, Zhan Xue, Xiaoqing Ye, Hongwu Zhang, Shilei Wen, Errui Ding. Robust movement-specific vehicle counting at crowded intersections in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2020: 614-615
  • Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Yi Yang, Shilei Wen. Dynamic inference: A new approach toward efficient video action recognition in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2020: 676-677

    • 2019

  • Xiao Tan, Zhigang Wang, Minyue Jiang, etc.,. Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features. in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw), 2019: 275-284
  • Yaming Wang, Xiao Tan, Yi Yang, Ziyu Li, Xiao Liu, Feng Zhou, Larry S Davis. A Refined 3D Pose Dataset for Fine-Grained Object Categories. in International Conference on Computer Vision Workshops (ICCVw), 2019
  • Zhaoyi Yan, Yuchen Yuan, Wangmeng Zuo, Xiao Tan, Yezhen Wang, Shilei Wen, Errui Ding. Perspective-guided convolution networks for crowd counting in International Conference on Computer Vision (ICCV), 2019: 952-961
  • Xiangyun Zhao, Yi Yang, Feng Zhou, Xiao Tan, Yuchen Yuan, Yingze Bao, Ying Wu. Recognizing part attributes with insufficient data in International Conference on Computer Vision (ICCV), 2019: 350-360
  • Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Shilei Wen. Multi-agent reinforcement learning based frame sampling for effective untrimmed video recognition in International Conference on Computer Vision (ICCV), 2019: 6222-6231

    • 2018

  • Chaofeng Chen, Wei Liu, Xiao Tan, Kwan-Yee K Wong. Semi-supervised learning for face sketch synthesis in the wild in Asian Conference on Computer Vision (ACCV), 2018: 216-231
  • Chaofeng Chen; Xiao Tan; Kwan-Yee K. Wong. Face Sketch Synthesis with Style Transfer using Pyramid Column Feature in IEEE Winter Conference on Applications of Computer Vision (WACV), 2018: 485-493
  • Zhu Chen, Tan Xiao, Zhou Feng, Liu Xiao, Yue Kaiyu, Ding Errui, Ma Yi. Fine-grained Video Categorization with Redundancy Reduction Attention in European Conference on Computer Vision (ECCV), 2018: 136-152
  • Yaming Wang, Xiao Tan, Yi Yang, Xiao Liu, Errui Ding, Feng Zhou, Larry S Davis. 3d pose estimation for fine-grained object categories in European Conference on Computer Vision Workshops (ECCVw), 2018

    • Before 2018

  • Xiao Tan, Changming Sun, Tuan D. Pham Soft Cost Aggregation with Multi-Resolution Fusion in European Conference on Computer Vision (ECCV), 2014: 17-32
  • Xiao Tan, Changming Sun, Tuan D. Pham Multipoint Filtering with Local Polynomial Approximation and Range Guidance in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014: 2941-2948
  • Xiao Tan, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham Cross Image Inference Scheme for Stereo Matching in Asian Conference on Computer Vision (ACCV), 2014: 17-32
  • Xiao Tan, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham Feature Correspondence with Even Distribution in International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2012: 1-7
  • Xiao Tan, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham Tree structural watershed for stereo matching in Image and Vision Computing New Zealand (IVCNZ), 2012: 340-345
  • Xiao Tan, Changming Sun, Tuan D. Pham Membrane extraction using two-step classifier and post-processing in Workshop on Segmentation of Neuronal Structures in EM Stacks Challenge in conjunction with International Symposium on Biomedical Imaging (ISBI), 2012



    • Journal Papers

  • Peizhe Jiang, Wei Yang, Xiaoqing Ye, Xiao Tan, Meng Wu. Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation IEEE Robotics and Automation Letters, vol.7 ,pp.12094--12101, 2022
  • Liang Du, Xiaoqing Ye, Xiao Tan, Edward Johns, Bo Chen, Errui Ding, Xiangyang Xue, Jianfeng Feng AGO-Net: Association-Guided 3D Point Cloud Object Detection Network , IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol.44, pp.8097-8109
  • Zhenbo Xu,Wei Yang, Wei Zhang, Xiao Tan, Huan Huang, and Liusheng Huang Segment as Points for Efficient and Effective Online Multi-Object Tracking and Segmentation , IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol.44, pp.6424--6437
  • Xu, Yan and Shen, Fumin and Xu, Xing and Gao, Lianli and Wang, Yuan Xiao Tan, Huan Huang, and Liusheng Huang Large-scale image retrieval with supervised sparse hashing , Neurocomputing, vol.229, pp.45-53, 2017
  • Xiao Tan, Changming Sun, Fumin Shen, Kwan-Yee K Wong Efficient Message Passing Methods With Fully Connected Models for Early Vision , IEEE Transactions on Image Processing (TIP), vol.26, pp.5994-6005, 2017
  • Xiao Tan, Changming Sun, Tuan D. Pham Stereo Matching based on Multi-Direction Polynomial Model , Signal Processing: Image Communication, vol.44, pp.44-56, 2016
  • Yutong Jiang, Changming Sun, Xiao Tan, Li Yang Orientation-Guided Geodesic Weighting for PatchMatch-based Stereo Matching Information Sciences, vol 334, pp.293-306, 2016
  • Xiao Tan, Changming Sun, Kwan-Yee K. Wong, Tuan D. Pham Guided Image Completion by Confidence Propagation Pattern Recognition (PR), vol.50, pp.210-222, 2016
  • Xiao Tan, Changming Sun, Tuan D. Pham Edge-aware Filtering with Local Polynomial Approximation and Rectangle based Weighting IEEE Transactions on Cybernetics (TCYB), vol.46, pp.2693-2705, 2015
  • Ignacio Arganda-Carreras, Srinivas C Turaga, Daniel R Berger, Dan Ciresan, Alessandro Giusti, Luca Maria Gambardella, Jurgen Schmidhuber, Dmitry Laptev, Sarvesh Dwivedi, Joachim M Buhmann, Ting Liu, Mojtaba Seyedhosseini, Tolga Tasdizen, Lee Kamentsky, Radim Burget, Vaclav Uher, Xiao Tan, Changming Sun, Tuan Pham, Erhan Bas, Mustafa Gokhan Uzunbas, Albert Cardona, Johannes Schindelin, H. Sebastian Seung Crowdsourcing the creation of image segmentation algorithms for connectomics Frontiers in Neuroanatomy 9:142. doi: 10.3389/fnana.2015.00142
  • Xiao Tan, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham Feature Matching in Stereo Images Encouraging Uniform Distribution Pattern Recognition (PR), vol.48, no.8, pp.2530-2542, 2015
  • Xiao Tan, Changming Sun, Xavier Sirault, Robert Furbank, Tuan D. Pham Stereo Matching Using Cost Volume Watershed and Region Merging Signal Processing: Image Communication, vol.29 no.10 pp.1232-1244, 2014




    • Challenge Awards

  • 2019 AI-city Challenge Track2 1st place
  • 2020 AI-city Challenge Track1 1st place
  • 2020 AI-city Challenge Track2 1st place
  • 2020 AI-city Challenge Track4 1st place
  • 2020 BMTT MOTChallenge Track2 1st place
  • 2021 AI-city Challenge Track1 1st place
  • 2021 AI-city Challenge Track2 2nd place
  • 2021 AI-city Challenge Track3 2nd place
  • 2021 AI-city Challenge Track4 1st place
  • 2021 ROD Challenge 1st place
  • 2021 KITTI-STEP Challenge 1st place
  • 2022 AI-city Challenge Track1 1st place
  • 2022 AI-city Challenge Track2 1st place
  • 2022 SoccerNet Challenge Camera Calibration 1st place
  • 2022 SoccerNet Challenge Pitch Localization 1st place


    • Professional Activities

      Reviewer:
      IEEE Transactions on Image Processing (TIP)
      IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
      Image and Vision Computing (IVC)
      CVPR 2019, 2020
      ECCV 2020
      ICCV 2019, 2021
      AAAI 2020, 2021
      NeurIPS 2021
      ICML 2021


    We are hiring

    Our team is dedicated to the research of algorithms in computer vision. The main research areas include computer vision and maching learning, covering object detection, recognition, segmentation, vision geometry, 3D machine vision, life-long learning and other fields, providing technical support for AI city, intelligent transportation, AR&VR, motion capture, 3D human body animation and etc. You are welcomed to join us if you are passionate about computer vision research or about algorithmic implementations.


    You can reach me at

    Wechat：yongyegang0420

    Email: tanxchong@gmail.com