Collection

Open-World Visual Object Detection and Tracking

Submission status
Closed
Visual object detection and tracking algorithms have traditionally been developed within a closed-world paradigm, making assumptions about a predefined set of object categories. However, the real-world visual environment is distinguished by its openness, dynamism, and unpredictability, posing challenges that exceed the capabilities of closed-world systems. Open-world visual object detection and tracking necessitate algorithms capable of adapting and continuously learning with novel objects, handling domain shifts, and operating robustly in diverse and ever-changing scenarios. This special issue aims to delve into the challenges and advancements associated with open-world visual object detection and tracking. It seeks to gather innovative research contributions that not only address the limitations of closed-world approaches but also propose novel methodologies for achieving robust detection and tracking in open-world settings.

Editors

  • Yi Jin Yi Jin , 

    Yi Jin

    Dr. Yi Jin is a Professor at the School of Computer Science, Beijing Jiaotong University. Her research interests include the semantic understanding of traffic videos, video behavior analysis, facial anti-counterfeiting and recognition, pedestrian recognition, etc. To date, she has authored or coauthored over 70 academic papers on these research topics, including articles published in esteemed journals such as IEEE/ACM and presentations at CCF Class A conferences including CVPR, AAAI, ICCV, IJCAI, ACM MM, among others.

  • Shuqiang Jiang Shuqiang Jiang , 

    Shuqiang Jiang

    Dr. Shuqiang Jiang (Senior Member, IEEE) is currently a Professor with the Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China, and a Professor with the University of CAS. He is also with the Key Laboratory of Intelligent Information Processing, CAS. He was supported by the New-Star Program of Science and Technology of Beijing Metropolis in 2008, the NSFC Excellent Young Scientists Fund in 2013, and the Young Top-Notch Talent of Ten Thousand Talent Program in 2014. His research interests include multimedia processing and semantic understanding, pattern recognition, and computer vision.

  • An-An Liu An-An Liu  &

    An-An Liu

    Dr. An-An Liu is currently a professor in the School of Electronic Information Engineering, Tianjin University, China. He used to be a visiting professor in the School of Computing, National University of Singapore, working with Prof. Mohan Kankanhalli, and the visiting scholar in the Robotics Institute, Carnegie Mellon University, working with Prof. Takeo Kanade. He respectively received his B.E. and Ph.D. degrees from Tianjin University, China, in 2005 and 2010. His research interests include multimedia analysis and retrieval. Various parts of his work have been published in first-tier venues including TPAMI, TMI, TIP, TCYB, CVPR, ACM MM.

  • Xiangyang Li Xiangyang Li

    Xiangyang Li

    Dr. Xiangyang Li is currently an assistant researcher at the Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China. In 2020, he received his Ph.D. degree from the Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, CAS. His research interests include embodied AI, large-scale image classification, vision and language understanding. He has been serving/served as a reviewer of IEEE TPAMI, IEEE TIP, IEEE TMM, IEEE TNNLS, IEEE TBD, and ACM TOMM.

Articles (3 in this collection)