7th Instance-Level Recognition and Generation Workshop
International Conference on Computer Vision, ICCV 2025
Honolulu, Hawaii, October 19-20 2025
https://ilr-workshop.github.io/ICCVW2025/

The Instance-Level Recognition and Generation (ILR+G) Workshop aims to explore computer vision tasks focusing on specific instances rather than broad categories, covering both recognition (instance-level recognition – ILR) and generation (instance-level generation – ILG). Unlike category-level recognition, which assigns broad class labels based on semantics (e.g., “a painting”), ILR focuses on distinguishing specific instances, assigning class labels that refer to particular objects or events (e.g., “Blue Poles” by Jackson Pollock), enabling recognition, retrieval, and tracking at the finest granularity. This year, the workshop also covers ILG, also known as personalized generation, which involves synthesizing new media that preserve the visual identity of a particular instance while varying context or appearance, often guided by text.  We encourage the exploration of synergies between ILR and ILG, such as using recognition as a foundation for instance-conditioned generation, or leveraging generative models to boost ILR in low-data or open-set scenarios.

Relevant topics include (but are not limited to):

• instance-level object classification, detection, segmentation, and pose estimation
• particular object (instance-level) and event retrieval
• personalized (instance-level) image and video generation
• cross-modal/multi-modal recognition at instance-level
• other ILR tasks such as image matching, place recognition, video tracking, moment retrieval
• other ILR+G applications or challenges
• ILR+G datasets and benchmarking

Submission details
We call for novel and unpublished work in the format of long papers (up to 8 pages) and short papers (up to 4 pages).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 ICCV proceedings style 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 ICCV guidelines, 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.

Important dates
in-proceedings papers

• submission deadline: June 7, 2025
• notification of acceptance: June 21, 2025
• camera-ready papers due: June 27, 2025

out-of-proceedings papers

• submission deadline: June 30, 2025
• notification of acceptance: July 18, 2025
• camera-ready papers due: July 25, 2025

Organizing committee
Andre Araujo, Google DeepMind
Bingyi Cao, Google DeepMind
Kaifeng Chen, Google DeepMind
Ondrej Chum, Czech Technical University in Prague
Noa Garcia, Osaka University
Guangxing Han, Google DeepMind
Giorgos Kordopatis-Zilos, Czech Technical University in Prague
Giorgos Tolias, Czech Technical University in Prague
Hao Yang, Amazon
Nikolaos-Antonios Ypsilantis, Czech Technical University in Prague
Xu Zhang, Amazon