The main focus of our workshop is on computer vision tasks that operate at instance-level, including both recognition (instance-level recognition - ILR) and generation (instance-level generation - ILG), denoted as ILR+G. More precisely, ILR+G is the task of identifying, comparing, and generating images of specific objects, scenes, or events. This year, we expand the scope of our workshop to ILG and the potential synergy between ILG and ILR. We will organize a call for papers, and host keynote talks by renowned speakers and invited paper talks from the main conference. The 2025 Instance-Level Recognition and Generation (ILR+G) Workshop is a follow-up of six successful editions of our previous workshops — the first two having focused only on landmark recognition (, ), the following ones expanding to the domains of artworks and products (, ), introducing the universal image embedding problem (), and the latest one introducing a call for papers ().
We call for novel and unpublished work in the format of long papers (up to 8 pages) and short papers (up to 4 pages). Papers should follow the and will be reviewed in a double-blind fashion. Submissions may be made to either of two tracks: (1) in-proceedings papers – long papers that will be published in the conference proceedings, and (2) out-of-proceedings papers – long or short papers that will not be included in the proceedings. Note that according to the , papers longer than four pages are considered published, even if they do not appear in the proceedings. Selected long papers from both tracks will be invited for oral presentations; all accepted papers will be presented as posters.
Topics of interest include
The task of person re-identification clearly falls within our definition of ILR. Nevertheless, because of its social implications, we intentionally omit it from the list of topics.
Important Dates
In-proceedings papers
Out-of-proceedings papers
Questions? Please reach out to us at ilr-workshop@googlegroups.com
Google DeepMind
Google DeepMind
Google DeepMind
Czech Technical University
Osaka University
Google DeepMind
Czech Technical University (Primary Contact)
Czech Technical University
Amazon
Czech Technical University
Amazon
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
© 2025 ILR+G 2025
We thank Jalpc for the jekyll template