7th Instance-Level Recognition and Generation Workshop @ ICCV2025

Call for Papers – ILR+G@ICCV2025

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We call for novel and unpublished work in the format of long papers (up to 8 pages) and short papers (up to 4 pages).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

CF PE-WASUN 2025

CfP: VisionDocs @ ICCV – Workshop on Computer Vision Systems for Document Analysis and Recognition

===================================

CALL FOR PAPERS and DEMOS: VisionDocs @ ICCV 2025

Website: https://sites.google.com/view/avml-lab-visiondocs-iccv2025/

===================================

 

We are glad to announce VisionDocs: 2nd Workshop on Computer Vision Systems for Document Analysis and Recognition, in conjunction with the IEEE/CVF International Conference on Computer Vision (ICCV) 2025, to be held in Honolulu, Hawaii, on October 19 or 20, 2025.

 

Workshop Overview:
Explore cutting-edge research at the intersection of computer vision and document analysis from ancient manuscripts to modern document understanding, multimodal learning, layout analysis, few-shot segmentation, and beyond!

 

Call for Papers and Demos:

We invite submissions on, but not limited to, the following topics:

  • Document image processing
  • Physical and logical layout analysis
  • Text and symbol recognition
  • Handwriting recognition
  • Document analysis systems
  • Document layout analysis
  • Document classification
  • Multimedia document analysis
  • Recognition of tables and formulas
  • Document forensics and provenance
  • Medical document analysis
  • Data-efficient document analysis
  • Indexing and retrieval of documents
  • Document synthesis
  • Document visual question answering
  • Extracting document semantics
  • Graphics recognition
  • Structured document generation
  • Historical document analysis
  • Document summarization and translation
  • Document analysis for social good
  • Multi-modal document analysis
  • Multi-modal document generation
  • Datasets and benchmarks for document analysis

Paper and Demo Submission Deadline: Coming Soon!

 

Website and Updates:
For the latest updates, deadlines, and submission details, please visit:
https://sites.google.com/view/avml-lab-visiondocs-iccv2025/


The VisionDocs Organizing Committee
visiondocs.organizers@gmail.com

 

18th International Conference on Similarity Search and Applications, SISAP 2025 – deadline extension


18th International Conference on Similarity Search and Applications,
SISAP 2025
Reykjavik, Iceland, October 1-3, 2025

https://www.sisap.org/2025/

Important Dates

Regular and Special Session Papers

  • Abstract submission deadline: May 11, 2025 (AoE) extended to May 25, 2025 (AoE)

  • Paper submission deadline: May 18, 2025 (AoE) extended to June 1, 2025 (AoE)

  • Acceptance notification: July 14, 2025 (AoE)

  • Camera-ready due: July 31, 2025 (AoE)

Demonstration and Doctoral Symposium Papers

  • Paper submission deadline: June 6, 2025 (AoE)

  • Acceptance notification: July 14, 2025 (AoE)

  • Camera-ready due: July 31, 2025 (AoE)

Scope

The 18th International Conference on Similarity Search and Applications (SISAP) is an annual forum for researchers and application developers in the area of similarity data management. It aims at the technological problems shared by numerous application domains, such as data mining, information retrieval, multimedia retrieval, computer vision, pattern recognition, computational biology, geography, biometrics, machine learning, and many others that make use of similarity search as a necessary supporting service. From its roots in metric indexing, SISAP has expanded to become the only international conference entirely devoted to all issues surrounding the theory, design, analysis, practice, and application of content-based and feature-based similarity search. Since 2021, SISAP has been a CORE Rank B conference.

The conference proceedings will be published by Springer as a volume in the Springer Lecture Notes in Computer Science (LNCS) series.

A small selection of the best papers presented at the conference will be invited for a post-conference special issue of Elsevier’s Information Systems journal. These extended versions will be subject to a second round of peer review at the journal.

Important Additional Scholarly Activities at SISAP

Submissions

SISAP 2025 allows for four forms of submissions: long research papers (from 9 to 14 pages), short research papers (of up to 8 pages), demonstration papers (of up to 8 pages), and doctoral symposium papers (up to 6 pages plus 2 pages of references). The submission itself, including references and appendices, should fit within these page limits. Papers must be written in English and formatted according to the LNCS guidelines.

Papers have to be submitted in PDF format through EasyChair: https://easychair.org/conferences/?conf=sisap2025 

Regular and Special Session Papers 

The organisers of SISAP 2025 call for novel and original research papers that address the various topics of interest related to the conference. We encourage contributions both to theoretical aspects and applications.

Full papers (from 9 to 14 pages) are expected to be descriptions of complete technical work, whereas short papers (of up to 8 pages) can describe innovative approaches or preliminary results which may nevertheless require more work to mature. Vision papers and other position papers should be submitted as short research papers.

Special session papers will supplement the regular research papers and be included in the proceedings of SISAP 2025, which will be published by Springer as a volume in the Lecture Notes in Computer Science (LNCS) series.

Regular and special session research papers will be peer-reviewed in a double-blind review process. Thus, the submissions must be properly anonymized.

The Best Paper will be recognized with a certificate and a monetary prize, thanks to Springer's sponsorship.

Special Sessions 

Special sessions are mini-venues, each focusing on one state-of-the-art research direction within the field of similarity search and applications. For SISAP 2025, we call for contributions for the following two special sessions:

  • IRMC: Interactive Retrieval for Multimedia Collections. This session focuses on innovative methods and systems that enhance user interaction and experience in multimedia retrieval, covering areas such as user-centric interfaces, relevance feedback mechanisms, and interactive search paradigms.
    Learn more: IRMC Special Session

  • BRIDGES: Bridging Past and Present: Similarity Search for Digital Cultural Heritage and GLAM Content. This session focuses on advances in similarity search and retrieval techniques for digital cultural heritage and GLAM (Galleries, Libraries, Archives, and Museums) content, addressing both technical innovations and real‐world applications. The session aims to bring together researchers, practitioners, and GLAM professionals to explore novel methodologies, discuss challenges, and showcase successful implementations of similarity‐based retrieval in cultural heritage contexts.
    Learn more: BRIDGES Special Session

Demonstration Papers

SISAP 2025 invites novel, impactful demonstrations aligned with its topics of interest. Submissions (up to 8 pages, including references) must include a mandatory 1-page PDF appendix describing how the demo will be conducted on-site. Demonstrations will be evaluated on novelty, technical challenges, and on-site impact in a single-blind review process.

Please see https://www.sisap.org/2025/demonstrations.html  for more details.

Doctoral Symposium Papers

SISAP 2025 Doctoral Symposium provides a forum for PhD students to present their research ideas and receive feedback from senior members of the research community. The Symposium fosters a collaborative environment, encouraging constructive discussions and sharing of ideas.

The doctoral symposium papers will be peer-reviewed in a single-blind review process.

Please see https://www.sisap.org/2025/doctoralsymposium.html  for more details.

SISAP Indexing Challenge

The SISAP Indexing Challenge is an event for researchers and practitioners to test new and/or well-tuned and optimised indexing approaches for shared tasks in laboratory and practical conditions. The Indexing Challenge results provide valuable comparisons of competing approaches and their implementations from given viewpoints and environments.

The Indexing Challenge papers will be peer-reviewed in a single-blind review process.

Please see https://sisap-challenges.github.io/2025/index.html  for more details.

Topics of interest

Topics of interest to the SISAP community include (but are not limited to) the following:

  • Similarity

    • Similarity queries (k-NN, range, reverse NN, top-k, Approximate and/or precise solutions, etc.)

    • Similarity measures (for vectors, graphs, structures, time series, complex data, tensors, secondary similarity, etc.)

    • Similarity operations (joins, ranking, classification, categorization, filtering, etc.)

  • Scalability

    • Indexing and access methods for similarity-based processing

    • High-performance/large-scale similarity search (distributed, parallel, etc.)

    • Data management (transaction support, dynamic maintenance, etc.)

  • Theory

    • Models of similarity

    • Intrinsic dimensionality and Curse of dimensionality

    • Discriminability and contrast

    • Languages for similarity databases

    • Manifolds and subspaces

  • Analytics, Learning, Artificial Intelligence

    • Feature selection and extraction for similarity search

    • Representations learning for feature extraction

    • Visual analytics for similarity-based operations

    • Learning/adaptive similarity measures

    • Similarity in learning and mining

    • Merging/combining multiple similarity modalities

  • Evaluation

    • Evaluation techniques for similarity queries and operations

    • Cost models and analysis for similarity data processing

    • Performance studies and comparisons

    • Test collections and benchmarks

  • Applications

    • Multimedia retrieval systems

    • Dense retrieval

    • Vector databases

    • Similarity search in emerging data domains

    • Applications of similarity-based operations

    • Industrial applications and case studies

    • Similarity search cloud services

    • Security and privacy of in similarity search

    • Similarity for forensics and security

Organization

Steering Committee

  • Giuseppe Amato, CNR-ISTI, Italy

  • Edgar Chávez, CICESE, México

  • Stéphane Marchand-Maillet, University of Geneva, Switzerland

  • Marco Patella, University of Bologna, Italy

  • Benjamin Kimia, Brown Unversity, USA

  • Oscar Pedreira, University of A Coruña, Spain

General Co-Chairs

  • Björn Þór Jónsson, Reykjavik University, Iceland

  • Lucia Vadicamo, CNR-ISTI, Italy

Program Committee Co-Chairs

  • Giuseppe Amato, CNR-ISTI, Italy

  • Vladimir Mic, Aarhus University, Denmark

  • Agma J. M. Traina, University of São Paulo, Brazil

Demonstration Chair

  • Gylfi Þór Guðmundsson, Reykjavik University, Iceland

Doctoral Symposium Chair

  • Laurent Amsaleg, IRISA-CNRS, France

Publications Chair

  • Nicola Messina, CNR-ISTI, Italy

Publicity Chair

  • Luca Ciampi, CNR-ISTI, Italy

  • Conrado Martinez, Universitat Politècnica de Catalunya, Spain

SISAP Indexing Challenge Chairs

  • Eric S. Tellez, CICESE-INFOTEC-CONACyT, Mexico

  • Martin Aumüller, ITU Copenhagen, Denmark

  • Vladimir Mic, Aarhus University, Denmark

  • Edgar Chávez, CICESE, México


Stephen Raudenbush’s “Causal Inference for Multilevel Data” Seminar

Hello everyone,

Join renowned scholar Stephen Raudenbush, on Wednesday, May 28th, for a livestream seminar on estimating causal effects in complex, multilevel settings—contexts where interventions are implemented by diverse agents such as teachers, doctors, or police across varied environments. You'll learn practical tools for analyzing data from randomized trials, observational studies, and natural experiments, while exploring innovative alternatives to conventional modeling approaches.

Raudenbush is the Lewis-Sebring Distinguished Service Professor at the University of Chicago and co-author of the landmark book Hierarchical Linear Models, which has been cited more than 35,000 times. He has received major awards in both education and sociology in recognition of his groundbreaking methodological work.

Causal Inference for Multilevel Data” will be held via Zoom from 1pm-4pm ET, but you can also join asynchronously by viewing the recorded video.

Please share this information with anyone who may be interested. Email kaity@statisticalhorizons.com with any questions.

Thanks,
Kaity

Design by 2b Consult