Jian ZHAO 赵健

Leader of Evolutionary Vision+x Oriented Learning (EVOL) Lab & Principal Research Scientist @ The Institute of AI (TeleAI), China Telecom, Beijing, P.R. China
Researcher & Ph.D. Supervisor @ School of Artificial Intelligence, Optics and Electronics (iOPEN) | Northwestern Polytechnical University (NWPU), Xi'an Shanxi, P.R. China
Office: 11 Dongzhimen South Street, Dongcheng District, Beijing, China 100027
Phone: (86) 15313525501
Email: zhaoj90 (at) chinatelecom (dot) cn OR jian_zhao (at) nwpu (dot) edu (dot) cn OR zhaojian90 (at) u (dot) nus (dot) edu OR zhaoj08 (at) pcl (dot) ac (dot) cn
Prospective Students : Contact me.


Research Interests

My research interests include Multimedia Analytics, Vicinagearth Security, and AI Agent. In particular, I have recently worked in:

  • Multimedia Analytics: detection and tracking of small objects in complex scenarios, etc.
  • Vicinagearth Security: perception and understanding of visual targets under unconstrained conditions, etc.
  • AI Agent (AI for Good): Autonomous agent for Beauty, Food, Home, Tour, Clip, etc.

More details can be found here.

News

  • [ ACTIVITY ]
    01 Dec 2024, Will organize the Resource-Limited Infrared Small Target Detection (LimitIRSTD) Challenge with ICPR 2024.
  • [ ACTIVITY ]
    18 Oct 2024, Will organize the Wide Infrared Small Target Detection (WideIRSTD) Challenge with PRCV 2024.
  • [ PAPER ]
    26 Sep 2024, One paper is accepted to NeurIPS 2024, congrats to Yifan Duan!
  • [ PROJECT ]
    23 Sep 2024, Will release our recent achievements on AI for Tour (TeleTrip).
  • [ ACTIVITY ]
    07 Sep 2024, Will give a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on the 2024 Ningxia Youth Expert Academic Exchange Conference on Artificial Intelligence.
  • [ CODE ]
    06 Sep 2024, Tsinghua Jittor officially merged Anti-UAV to better facilitate more cutting-edge researches and applications on small object detection and tracking in complex scenes.
  • [ PAPER ]
    28 Aug 2024, One paper is accepted to T-IP, congrats to Jiaming Chu!
  • [ ACTIVITY ]
    29 Jul 2024, Will give a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on the Workshop of Red Teaming Multi-Modal Large Language Model Security Challenge with CCDM 2024.
  • [ ACTIVITY ]
    28 Jul 2024, Will organize the Evolutionary Vision+X Oriented Learning Workshop with CCDM 2024.
  • [ ACTIVITY ]
    26 Jul 2024, Will give a talk "AI4Beauty: Innovation and Empowerment in the Era of LLMs" on ChinaMM 2024.
  • [ ACTIVITY ]
    22 Jul 2024, officially interviewed by Committee for Elite Young Professionals, CSIG.
  • [ ACTIVITY ]
    18 Jul 2024, Will give a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on the 7th CSIG Outstanding PhD Forum 2024.
  • [ PAPER ]
    16 Jul 2024, One paper is accepted to ACM MM 2024, congrats to Xinpeng Li!
  • [ ACTIVITY ]
    08 Jul 2024, Will give a talk "Multi-Modal AI Agent" on the TeleAI & EE of Tsinghua Meet-Up 2024.
  • [ PAPER ]
    28 Jun 2024, Two papers are accepted to PRCV 2024, congrats to Xuechao Zou and Jun Wang!
  • [ AWARD ]
    17 Jun 2024, Achieved Winner Award on the 4th Physics based Vision Meets Deep Learning Workshop and Challenge on Low-Light Object Detection and Instance Segmentation (Detection Track) with CVPR 2024, congrats to Haiyang Xie, Shuai An, and Peng Cheng!
  • [ AWARD ]
    17 Jun 2024, Achieved 3rd Place Award on the 4th Physics based Vision Meets Deep Learning Workshop and Challenge on Low-Light Object Detection and Instance Segmentation (Segmentation Track) with CVPR 2024, congrats to Haiyang Xie, Shuai An, and Peng Cheng!
  • [ ACTIVITY ]
    15 Jun 2024, Will give a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on BAAI Conference 2024.
  • [ ACTIVITY ]
    28 May 2024, Will organize the SkatingVerse Workshop & Challenge with FG 2024.
  • [ PAPER ]
    17 Apr 2024, One paper is accepted to IJCAI 2024, congrats to Jianqiang Xia!
  • [ ACTIVITY ]
    14 Apr 2024, Will organize the LLM & AGI Workshop with CAIIAC 2024.
  • [ ACTIVITY ]
    10 Apr 2024, Will organize the VALSE Webinar on "Incomplete Multi-Modal Information Fusion for Perception and Understanding in Complex Scenarios".
  • [ ACTIVITY ]
    02 Apr 2024, officially interviewed by CSIG.
  • [ PAPER ]
    13 Mar 2024, One paper is accepted to ICME 2024, congrats to Ziliang Gan!
  • [ TEAM ]
    1 Mar 2024, I joined School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University (NWPU) as a Researcher.
  • [ PAPER ]
    27 Feb 2024, Two papers are accepted to CVPR 2024, congrats to Tao Wang and Chen Min!
  • [ TEAM ]
    26 Feb 2024, I joined China Telecom Institute of AI (TeleAI) as a Young Scientist.
  • [ PAPER ]
    17 Feb 2024, One paper is accepted to T-OMM, congrats to Zhihao Zhang!
  • [ AWARD ]
    25 Jan 2024, I received the 2023 CAAI WU WEN JUN AI Outstanding Youth Award!
  • [ PAPER ]
    23 Jan 2024, One paper is accepted to IJCV, congrats to Haoyu Xie!

Selected Honors & Awards

Academic Services & Activities

Academic Services

Co-Ph.D. Supervisor
  • Department of Automation, Tsinghua University
  • Department of Computer Science and Technology, Fudan University
  • Department of Computer Science and Technology, Zhejiang University
  • Department of Computer Science and Technology, University of Science and Technology of China
Member of the Board of Directors
  • Beijing Society of Image and Graphics (BSIG)
Editorial Board Member
  • Pattern Recognition
  • Electronics and Signal Processing [Certificate]
  • Artificial Intelligence Advances [Certificate]
  • IET Computer Vision [Certificate]
  • Guest Editor
  • Pattern Recognition Letters special issue on Recent Advances in Deep Learning Model Security [WeChat News1 News2 News3]
  • Electronics special issue on Multimedia Content Analysis, Management and Retrieval: Trends and Challenges [CFP]
  • Senior Area Chair
  • Vision and Learning Seminar (VALSE)
  • Session Chair
  • ACM MM 2021
  • ECCV 2020 China Pre-Conference
  • Area Chair
  • The Chinese Association for Artificial Intelligence (CAAI) International Conference on Artificial Intelligence (CICAI) 2023
  • The Chinese Association for Artificial Intelligence (CAAI) International Conference on Artificial Intelligence (CICAI) 2022
  • Presentation Chair
  • The Chinese Association for Artificial Intelligence (CAAI) International Conference on Artificial Intelligence (CICAI) 2021
  • Workshop Chair
  • The Chinese Conference on Biometric Recognition (CCBR) 2024 [Official Notification]
  • Member of Expert Arbitration
  • The "Challenge Cup" National Undergraduate Curricular Academic Science and Technology Works by Race [2024]
  • The "Challenge Cup" National Undergraduate Curricular Academic Science and Technology Works by Race [2023]
  • China Artificial Intelligence Competition
  • Science and Technology Award, Chinese Institute of Electronic (CIE)
  • Science and Technology Award, China Telecom
  • Senior Member
  • China Computer Federation (CCF)
  • Chinese Association for Artificial Intelligence (CAAI)
  • China Society of Image and Graphics (CSIG)
  • Technical Consultant
  • Synced (2022-Now)
  • Baidu Institute of AI (2020-2022)
  • OPPO Institute (2021-2022)
  • PENSEES (2020-2021)
  • Committee Member
  • Technical Committee on Computer Vision, China Computer Federation (CCF-CV)
  • Technical Committee on Big Visual Data, China Society of Image and Graphics (CSIG-BVD)
  • Technical Committee on Multimedia Division, China Society of Image and Graphics (CSIG-MM)
  • Committee for Elite Young Professionals, China Society of Image and Graphics (CSIG)
  • Committee for Elite Young Professionals, Beijing Society of Image and Graphics (BSIG)
  • Developer Expert
  • PaddlePaddle, Baidu
  • Member
  • IEEE, CCF, CAAI, CSIG, CSIG-BVD, CSIG-MM, BSIG

  • Invited Reviewer

    Journal

  • T-PAMI, IJCV, T-MM, T-IFS, T-CSVT, Neurocomputing, T-CDS, T-AFFC, T-HMS, KNOSYS, IET Computer Vision, CSSP, JVCI, GVC, IMAVIS, ESWA, INFFUS, CVIU, ITS

    Conference

  • NeurIPS (one of the top 30% highest-scoring reviewers of NeurIPS 2018), CVPR, ICCV, ACM MM, AAAI, ICLR, ICML, ICME, ACCV, UAI, FG, CICAI, ICASSP
  • Chair
  • The Evolutionary Vision+X Oriented Learning Workshop with CCDM 2024 [Official News] [Certificate]
  • The 1st SkatingVerse Workshop & Challenge with FG 2024 [BSIG News] [Synced News]
  • The 3rd Anti-UAV Workshop & Challenge with CVPR 2023 [Poster] [WeChat News1 News2] [ModelScope News] [CSDN News]
  • The 2nd Anti-UAV Workshop & Challenge with ICCV 2021
  • The "Knowledge and Semantic Hybrid Driven Visual Understanding" Workshop with VALSE 2021
  • The 1st Anti-UAV Workshop & Challenge with CVPR 2020
  • The Challenge on Unconstrained Face Recognition, Suspicious Object Recognition, and Special Behavior Recognition
  • Co-Chair
  • The Resource-Limited Infrared Small Target Detection (LimitIRSTD) Challenge with ICPR 2024 [BSIG News]
  • The Wide Infrared Small Target Detection (WideIRSTD) Challenge with PRCV 2024 [BSIG News]
  • The LLM & AGI Workshop with CAIIAC 2024 [Official Summary]
  • The Visual Target Perception: Present and Future Workshop with CAIIAM 2023
  • The Explainable Deep Learning Algorithms and Vision Applications Workshop with VALSE 2022
  • The Knowledge and Semantics Driven Visual Understanding Workshop with VALSE 2021
  • The RLQ-TOD Workshop and Challenge with ECCV 2020
  • The L.I.P Workshop and MHP Challenge with CVPR 2018

    Academic Activities

    • We released our recent achievements on AI for Tour (TeleTrip) on 23rd Sep 2024. [CSIG News] [BSIG News] [Synced News] [Jiangmen News] [Sichuan Observation News] [People's Daily News]
    • Tsinghua Jittor officially merged Anti-UAV to better facilitate more cutting-edge researches and applications on small object detection and tracking in complex scenes. [BSIG News]
    • I was invited by the 2024 Ningxia Youth Expert Academic Exchange Conference on Artificial Intelligence to deliver a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on 07th Sep 2024.
    • I was invited by the Workshop of Red Teaming Multi-Modal Large Language Model Security Challenge with CCDM 2024 to deliver a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on 29th Jul 2024.
    • Officially interviewed by Committee for Elite Young Professionals, CSIG on 22 Jul 2024.
    • I was invited by ChinaMM 2024 AI Art & Design Workshop to deliver a talk "AI4Beauty: Innovation and Empowerment in the Era of LLMs" on 26th Jul 2024.
    • I was invited by the 7th CSIG Outstanding PhD Forum to deliver a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on 18th Jul 2024.
    • I delivered a talk "Multi-Modal AI Agent" on the TeleAI & EE of Tsinghua Meet-Up on 08th Jul 2024.
    • I was invited by BAAI Conference 2024 to deliver a talk "Unconstrained Perception and Understanding: From Visual Vertical Domain Modeling to Multimodal Unification and Multi-Task Collaboration" on 15th Jun 2024.
    • Officially interviewed by CSIG on 02 Apr 2024.
    • I was invited by Ningxia "Data from the East Computed by the West" Young Scientist Workshop on Artificial Intelligence Science and Technology Breakthroughs to deliver a talk "Towards Unconstrained Intelligent Perception and Deep Understanding on Images/Videos" on 28th Oct 2023.
    • I was invited by CAAI to deliver a talk "Towards Unconstrained Human-centric Intelligent Perception and Deep Understanding" on 29th Oct 2022.
    • I was invited by BSIG to deliver a talk "Towards Unconstrained Human-centric Intelligent Perception and Deep Understanding" on 9th Sep 2022.
    • I was invited by Tsinghua AIR Webinar to deliver a talk "Towards Unconstrained Image/Video Deep Understanding" on 19th Jul 2022.
    • I was invited by CSIG Webinar to deliver a talk "Towards Unconstrained Image/Video Deep Understanding" on 28th Jun 2022.
    • Officially interviewed by CSIG on 24 May 2022.
    • Officially interviewed by Beijing Association for Science and Technology, due to a series of contributions on "Unconstrained Image/Video Deep Understanding". [BAST Official Interview1 Interview2 Interview3]
    • Baidu PaddlePaddle officially merged face.evoLVe to better facilitate more cutting-edge researches and applications on facial analytics and human-centric multi-media understanding.
    • I have co-organized a VALSE Tutorial with Assoc. Prof. Xingxing Wei on the topic of "Deep Synthesis and Identification in Adversarial Environments" on 8th Sep 2021.
    • I have co-organized a VALSE Webinar with Dr. Wenguan Wang and Prof. Zheng Wang on the topic of "Human-Centric Vision Techniques" on 13th Jan 2021.
    • I was invited by Qihoo 360 to attend the "2020 Shanghai Digital Innovation Conference" on 5th Dec 2020 as a panel guest of "Opportunities and Challenges Brought by Artificial Intelligence to Cyberspace" session.
    • I have co-organized a VALSE Webinar with Prof. Chang Xu on the topic of "Visual Generation and Synthesis" on 23th Sep 2020.
    • I was invited by Jiang Men to attend the "将门ECCV 2020鲜声夺人云际会" on 30th Aug 2020 as a panel guest of "奔涌吧后浪:从PhD到助理教授身份转变" session.
    • I was invited by Prof. Jimin Xiao at Xi'an Jiaotong-Liverpool University, Xi'an China to deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing" on 31st Jul 2020.
    • I have co-organized a VALSE Webinar with Prof. Shiguang Shan on the topic of "Face-based Human Understanding: beyond Face Recognition" on 25th Mar 2020.
    • I was invited by Prof. Congyan Lang at Beijing Jiaotong University, Beijing China to deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing" on 24th Oct 2019.
    • I was invited by Dr. Jingtuo Liu at Baidu, Beijing China to deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing" on 5th Sep 2019.
    • I was invited by Prof. Ran He at Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing China to deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing" on 29th Aug 2019.
    • I was invited by Huawei Noah's Ark Lab to deliver a talk "Understanding Humans in Visual Scenes" on 13th Jun 2019.
    • I was invited by Peng Cheng Laboratory (PCL) to attend the 2019 Overseas Young Scientist Workshop at Shenzhen China during 30th Mar 2019 to 1st Apr 2019 and deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing".
    • I delivered a spotlight talk "Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing" on VALSE 2019.
    • I was invited by CoLab, School of Computer, Beihang University to deliver a talk "Deep Learning for Human-Centric Image Analysis: From Face Recognition to Human Parsing" on 23rd Mar 2019.
    • I was invited by Tencent Deep Sea AI Lab to deliver a talk "Margin-based Representation Learning, Residual Knowledge Distillation and Prior-Aided Super Resolution" on 1st Mar 2019.
    • I was invited by UBTECH to deliver a talk "Deep Learning for Human-Centric Image Understanding" on 8th Jan 2019.
    • I was invited by OmniVision to deliver a talk "Facial Analytics" on 16th Nov 2018.
    • I was invited by Jiang Men to deliver a talk "Deep Learning for Human-Centric Image Understanding" on 30th Aug 2018. [Poster] [Summary]
    • I was invited by VALSE Webinar to deliver a talk "Deep Learning for Human-Centric Image Understanding" on 22nd Aug 2018. [Summary]
    • I represented the Learning & Vision (LV) Group of NUS to "Launch of NUS new Vision, Mission and Values" at University Culture Center on 15th Aug 2018, and presented the recent achievements on Facial Analytics to NUS President Prof. Tan Eng Chye. [NUS Instagram] [NUS News] [Gallery]