MORE ’24

ICMR 2024 Workshop Multimedia Object Re-ID

Workshop topic and goals

Object re-identification , commonly known as object re-id, has become a focal point of research and development due to the escalating demand for sophisticated video analysis and safety systems. In our daily life, an object (e.g., a vehicle, person, or fashion item) is encountered in a certain scenario, and re-identifying the same object means recognising it in an another context of a different time, location or viewpoint. Here, we usually refer to object instances instead of object categories. In the computer vision community, commonlystudied objects include persons, animals, vehicles, and landmarks, which are captured by cameras. Specifically, given an image of an object instance (or query) captured by a certain camera, we aim to match it against a database of previously captured object images to find those containing the same instance. In object re-identification, a query can be of different modalities, such as an image, a video, point cloud or natural language, containing or describing the object of interest. As one of the fundamental research problems, object re-identification can be applied to many real-world applications, including recognizing persons and vehicles for public safety, tracking multiple objects in a camera network, smart husbandry by re-identifying animals, geo-localization and product re-identification for cargo management.

This workshop is designed to unite researchers, practitioners, and enthusiasts passionate about object re-identification, providing a platform to delve into the latest advancements, challenges, and opportunities within this dynamic field. Encompassing a wide array of topics, the workshop covers aspects such as new datasets and benchmarks, deep metric learning, multi-view data generation, video-based object re-identification, cross-domain object reidentification, and real-world applications. For researchers, it is an opportunity to highlight their work, while practitioners can stay informed about the most recent developments in object reidentification technology. Beyond a mere gathering, this workshop establishes a unique space for exploring the swiftly evolving field of object re-identification. Its profound impact is not limited to the advancement of multimedia analysis and retrieval capabilities but extends to addressing the pressing challenges posed by the increasing complexity of safety systems.


Topics covered in this workshop (but not limited to) is as follows:

  • New Datasets and Benchmarks
  • Deep Metric Learning
  • Multi-view Data Generation
  • Video-based Object Re-identification
  • Cross-domain Object Re-identification
  • Object Re-identification Domain Adaptation / Generalization
  • Single/ Multiple Object Tracking
  • Object Geo-localization
  • Multimedia Re-ranking


Important Dates

  • Paper Submission: April 15, 2024
  • Paper Notification: April 22, 2024
  • Camera-Ready Submission: April 25, 2024

Submission Types

  • Original papers (up to 4 pages in length, plus unlimited pages for references): original solution to the tasks in the scope of workshop topics and themes.
  • Position or perspective papers (up to 4 pages in length, plus unlimited pages for references): original ideas, perspectives, research vision, and open challenges in the area of evaluation approaches for explainable multimedia systems;
  • Survey papers (up to 4 pages in length, plus unlimited pages for references): papers summarizing existing publications in leading conferences and high-impact journals that are relevant for the topic of the workshop;
Page limits include diagrams and appendices. Submissions should be single-blind, written in English, and formatted according to the current ACM two-column conference format. Suitable LaTeX, Word, and Overleaf templates are available from the ACM Website (use “sigconf” proceedings template for LaTeX and the Interim Template for Word).

Workshop organizers

  • Zhedong Zheng ( is a tenure-track Assistant Professor at University of Macua.
  • Yaxiong Wang ( is an Associate Professor in Hefei University of Technology (HFUT), China
  • Xuelin Qian ( is a Postdoctoral Researcher in the School of Data Science, Fudan University.
  • Zhun Zhong ( is an Assistant Professor at the University of Nottingham.
  • Zheng Wang ( is a Professor with the National Engineering Research Center for Multimedia Software, Wuhan University, China.
  • Liang Zheng ( is an Associate Professor (with Tenure) in the School of Computing, Australian National University (ANU).

Submission Instructions

See the Paper Submission section.