Pedestrian Attribute Recognition (PAR) Contest 2025 – CAIP 2025

=== Call for submissions ===
Pedestrian Attribute Recognition (PAR) Contest 2025
International Conference on Computer Analysis of Images and Patterns CAIP 2025
Conference Website: https://caip2025.com/
Contest Website: https://mivia.unisa.it/par2025/
========================

=== Important dates ===
Method Submission Deadline: May 31, 2025
Contest Paper Deadline: June 15, 2025
========================

=== Contest ===
Following the success of the previous edition presented during CAIP 2023, the Pedestrian Attribute Recognition (PAR) 2025 Contest is an international competition aimed at assessing methods for recognizing pedestrian attributes from images. We provide the participants with the Mivia PAR KD Dataset 2025, featuring newly annotated images with labels such as clothing color, gender and the presence or absence of a bag or hat. After the contest, the dataset—expanded with additional samples and annotations contributed by participants—will be made publicly available to the scientific community, with the goal to build one of the largest datasets for PAR with the considered set of annotations. Competing methods will be evaluated based on accuracy using a distinct private test set, separate from the training data. Recently, a wide variety of methods have been proposed to tackle the challenge of PAR in both effective and efficient ways. In the 2023 edition, the winning method, which leveraged Visual Question Answering (VQA), achieved remarkable success by integrating Large Language Models. This approach reached an impressive 92% accuracy on the contest’s private test set, highlighting the immense potential of Vision-Language Models (VLMs) in addressing complex PAR challenges. Considering the rapid advancements in VLMs over the past two years, we expect many of the proposed methods to take advantage of these cutting-edge technologies. However, the competition is not limited to a specific approach and every innovative solution is not only welcomed but highly valued, contributing to the ongoing progression of this field.
========================

=== Rules ===
The deadline for method submission is May 31, 2025. Submissions must be made via email, in which participants must share (either directly or via external links) the trained model, the code and a technical report of the method. The participants can obtain the training set, validation set and their annotations by sending an email, specifying their team name. They are allowed to use these provided training and validation samples and annotations but they may incorporate additional samples. However, the additional samples and annotations used must be made publicly available. Each participant must train a neural network to predict all the required pedestrian attributes for each sample. Teams are free to design novel neural network architectures, define new training procedures or propose innovative loss functions. Participants are highly encouraged to submit their contest papers via email by the deadline of June 15, 2025. The top three papers will be featured in the proceedings of the CAIP 2025 main conference. When submitting a paper, participants are requested to cite the official contest paper, which can be downloaded from the bibtex file or as follows:

Greco A., Vento B., “PAR Contest 2025: Pedestrian Attributes Recognition with Advanced Neural Networks”, 21st International Conference Computer Analysis of Images and Patterns, CAIP 2025

The detailed instructions can be downloaded here: https://mivia.unisa.it/par2025/
========================

The organizers,
Antonio Greco, University of Salerno, Italy
Bruno Vento, University of Naples – Federico II, Italy

Workshops and Tutorials at IEEE BHI 2025 – “Precision Health: AI Tailored to Individuals”

CALL FOR WORKSHOPS AND TUTORIALS AT IEEE BHI 2025

“Precision Health: AI Tailored to Individuals”

 

https://bhi.embs.org/2025/call-for-workshops-and-tutorials/

 

The IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), sponsored by the IEEE Engineering in Medicine and Biology Society (IEEE EMBS), is EMBS’s primary technical conference on informatics and computing in healthcare and life sciences. BHI 2025 will take place in Atlanta, Georgia, USA from October 26 – 29, 2025. It will provide a unique forum to showcase basic and translational research on big data analytics and machine learning that address challenges in the acquisition, transmission, processing, security, visualization, and interpretation of vast volumes of multi-modal biomedical data, as well as related social, behavioral, environmental, and geographical data. It will also demonstrate the deployment of BHI informatics solutions that integrate key technologies including artificial intelligence, machine learning, mHealth, e-Health, human-computer interface, telemedicine, bioinformatics, sensors, imaging, and public health monitoring, to achieve patient-centric and outcome-driven effective health care.

 

The program for BHI 2025 will feature workshop/tutorials that serve to bring new and emerging areas of interest to the BHI community (i.e., digital biomarkers, devices and sensors, hardware and software systems, large language models for biomedical and clinical research, cutting edge advances in AI for health, digital health, and more). Each workshop/tutorial may be delivered by a group of leading researchers in their respective areas. The duration of a workshop is expected to be a half day (approximately 3 hours). A scientific committee will be established by the workshop organizers to ensure the quality of presentations and materials offered to the registrants.

 

We are inviting proposals for the following two categories:

 

  • Workshops will cover current and future trends in multi-disciplinary and cross-disciplinary areas of BHI, including but not limited to emerging trends in enabling technologies of devices and sensors, hardware and software systems, digital biomarkers, predictive models, databases, and big data analytics that optimize the acquisition, transmission, processing, monitoring, storage, retrieval, analysis, visualization and interpretation of vast volumes of multi-modal biomedical data, as well as related social, behavior, environmental, and geographical data. Workshop organizers will select a panel of reviewers for reviewing the presentations and materials offered to workshop registrants.

 

  • Tutorials will provide reviews of a specific area related to health informatics, behavioral informatics, health data analytics, and health informatics education, including current research directions, challenges, and state-of-the-art practices, but may also involve registrants through hands-on experience or demonstrations. Tutorials can be organized by a company, a group of companies, or a group of leading researchers featuring presentations/papers/ panels.

 

The proposals can be submitted through the conference Web page or the following link: https://docs.google.com/forms/d/e/1FAIpQLSfi0Z3j7cKjTQq_BlBu9BQCeB5zjhdpP1W8EYI_-Cq4oTjpQQ/viewform

 

Paper Submission and Review

Presentations/papers/panels featured in workshops will not undergo review by the BHI 2025 TPC and will not appear in IEEE-Xplore Proceedings. Presentations and materials offered to workshop registrants will be reviewed by the reviewer panel selected by the workshop organizers. The organizers are fully responsible for ensuring the quality of the workshop content.

 

Workshop Promotion and Material for the Registrants

Workshop information (call for papers, program/speakers, etc.) will be provided on a dedicated page of the web site and will be updated accordingly. Workshop registrants will be able to download any material provided by the workshop organizer(s) from the workshop website. Workshop organizer(s) may provide additional materials such as handouts to the participants during the workshop.

 

CfP Fast Continuum 2025 Workshop (Co-located with IEEE SERVICES

in conjunction with IEEE QSW Conference, IEEE Cloud, IEEE Edge, part of
IEEE SERVICES 2025

July 7-12 2025, Helsinki, Finland

https://services.conferences.computer.org/2025/fastcontinuum-2025/

INTRODUCTION

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

As industries increasingly adopt distributed intelligence, new
challenges emerge in managing heterogeneous resources, ensuring
performance guarantees, and securing end-to-end application execution.
The computing continuum —a seamless integration of cloud, edge, IoT and,
in the very near future, quantum computers— aims at addressing these
challenges and has revolutionized the way we design, deploy, and
optimize modern applications.
********Fast Continuum 2025 Workshop Call for Papers********

in conjunction with IEEE QSW Conference, IEEE Cloud, IEEE Edge, part of
IEEE SERVICES 2025

July 7-12 2025, Helsinki, Finland

https://services.conferences.computer.org/2025/fastcontinuum-2025/

INTRODUCTION

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

As industries increasingly adopt distributed intelligence, new
challenges emerge in managing heterogeneous resources, ensuring
performance guarantees, and securing end-to-end application execution.
The computing continuum —a seamless integration of cloud, edge, IoT and,
in the very near future, quantum computers— aims at addressing these
challenges and has revolutionized the way we design, deploy, and
optimize modern applications.

The FastContinuum workshop invites researchers, industry experts, and
practitioners to contribute innovative solutions, share experiences, and
engage in discussions on the future of computing beyond conventional
cloud models. This workshop serves as a way for exploring emerging
trends, methodologies, and frameworks that facilitate intelligent,
adaptive, and high-performance computing across the continuum.

TOPICS OF INTEREST

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

* Computing Continuum Foundations

* Design principles and architecture of continuum systems

* Application scheduling and orchestration strategies

* Energy-efficient continuum computing

* Quantum computing and HPC as computing continuum components

* Performance & Optimization

* Modeling, evaluation, and performance optimization

* AI-driven optimizations

* Large Language Models requirements for the computing continuum

* Artificial Intelligence & Emerging Technologies

* Generative AI for designing and managing continuum software

* Machine Learning and AI applications in the continuum

* Augmented Reality and immersive computing

* Software & Infrastructure Innovations

* Microservices, Function as a Service (FaaS), and serverless computing

* Cyber-physical systems, IoT, digital twins, and industrial internet

* Data-intensive and real-time stream processing systems

* Security, Automation, & Resilience

* Infrastructure as Code and automation in the continuum

* DevSecOps for distributed applications

* Autonomous, resilient, and adaptive systems

IMPORTANT DATES

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

Workshop paper submissions: April 26, 2025

Notification of acceptance: May 16, 2025

Camera-ready copies and registration: May 30, 2025

Workshop date: TBD

SUBMISSION GUIDELINES

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

Authors are invited to submit original, unpublished papers that are not
being considered in another forum. We solicit full papers (max. 6 pages)
as well as short and demo papers (max. 4 pages). Short papers can
include reports about research activities not mature enough for a full
paper as well as new ideas and vision papers. All submissions must
conform to the standard IEEE template for conference proceedings:
https://www.ieee.org/conferences/publishing/templates.html. More
specifically, the double-column formats have to be used for all paper
submissions. Each paper submission will be reviewed by at least three
members of the program committee. Papers can be submitted via EasyChair:
https://easychair.org/my/conference?conf=2025ieeeservices,
“[FastContinuum] Workshop on Fast Continuum” track.

Papers will be published in the IEEE Services 2025 Companion Proceedings
volume (To be confirmed).

At least one author of each accepted paper is required to attend the
workshop and present the paper.

WORKSHOP GENERAL CHAIRS

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

Danilo Ardagna, Elisabetta Di Nitto (Politecnico di Milano, Italy)

WORKSHOP PROGRAM COMMITTEE CHAIRS

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

Juncal Alonso Ibarra (Tecnalia, Spain), Federica Filippini (University
of Milano-Bicocca, Italy)

PUBLICITY CHAIR

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

Marco Garlini (Politecnico di Milano, Italy)

PC COMMITTEE

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

* Vasilios Andrikopoulos, University of Groningen, The Netherlands

* Matija Cankar, COMSENSUS/JSI, Slovenia

* Marco Casiero, Microsoft, Italy

* Michele Chiari, Technischen Universität Wien, Austria

* Jean-Christophe Deprez, Centre d'Excellence en Technologies de
l'Information et de la Communication (CETIC), Belgium

* Karim Djemame, University of Leeds, UK

* Maria Fazio, University of Messina, Italy

* Francesc Lordan, Barcelona Supercomputing Center (BSC-CNS), Spain

* Fabrizio Magugliani, E4 Computer Engineering, Italy

* Dana Petcu, University of West Timisoara, Romania

* Alessandro Raganato, University of Milano-Bicocca, Italy

* Domenico Siracusa, University of Trento, Italy

* Jacopo Soldani, University of Pisa, Italy,

* Ettore Trevisiol, AWS, Italy

* Alessandro Tundo, Technische Universität Wien, Austria

* Indika Kumara, JADS, The Netherlands

* Alireza Furutanpey, Technischen Universität Wien, Austria (quantum)

* Radosław Piliszek, 7Bulls, Poland

* Josu Diaz de Arcaya, Tecnalia

The FastContinuum workshop invites researchers, industry experts, and
practitioners to contribute innovative solutions, share experiences, and
engage in discussions on the future of computing beyond conventional
cloud models. This workshop serves as a way for exploring emerging
trends, methodologies, and frameworks that facilitate intelligent,
adaptive, and high-performance computing across the continuum.

TOPICS OF INTEREST

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

* Computing Continuum Foundations

* Design principles and architecture of continuum systems

* Application scheduling and orchestration strategies

* Energy-efficient continuum computing

* Quantum computing and HPC as computing continuum components

* Performance & Optimization

* Modeling, evaluation, and performance optimization

* AI-driven optimizations

* Large Language Models requirements for the computing continuum

* Artificial Intelligence & Emerging Technologies

* Generative AI for designing and managing continuum software

* Machine Learning and AI applications in the continuum

* Augmented Reality and immersive computing

* Software & Infrastructure Innovations

* Microservices, Function as a Service (FaaS), and serverless computing

* Cyber-physical systems, IoT, digital twins, and industrial internet

* Data-intensive and real-time stream processing systems

* Security, Automation, & Resilience

* Infrastructure as Code and automation in the continuum

* DevSecOps for distributed applications

* Autonomous, resilient, and adaptive systems

IMPORTANT DATES

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

Workshop paper submissions: April 7, 2025

Notification of acceptance: May 16, 2025

Camera-ready copies and registration: May 30, 2025

Workshop date: TBD

SUBMISSION GUIDELINES

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

Authors are invited to submit original, unpublished papers that are not
being considered in another forum. We solicit full papers (max. 6 pages)
as well as short and demo papers (max. 4 pages). Short papers can
include reports about research activities not mature enough for a full
paper as well as new ideas and vision papers. All submissions must
conform to the standard IEEE template for conference proceedings:
https://www.ieee.org/conferences/publishing/templates.html. More
specifically, the double-column formats have to be used for all paper
submissions. Each paper submission will be reviewed by at least three
members of the program committee. Papers can be submitted via EasyChair:
https://easychair.org/my/conference?conf=2025ieeeservices,
“[FastContinuum] Workshop on Fast Continuum” track.

Papers will be published in the IEEE Services 2025 Companion Proceedings
volume (To be confirmed).

At least one author of each accepted paper is required to attend the
workshop and present the paper.

WORKSHOP GENERAL CHAIRS

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

Danilo Ardagna, Elisabetta Di Nitto (Politecnico di Milano, Italy)

WORKSHOP PROGRAM COMMITTEE CHAIRS

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

Juncal Alonso Ibarra (Tecnalia, Spain), Federica Filippini (University
of Milano-Bicocca, Italy)

PUBLICITY CHAIR

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

Marco Garlini (Politecnico di Milano, Italy)

PC COMMITTEE

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

* Vasilios Andrikopoulos, University of Groningen, The Netherlands

* Matija Cankar, COMSENSUS/JSI, Slovenia

* Marco Casiero, Microsoft, Italy

* Michele Chiari, Technischen Universität Wien, Austria

* Jean-Christophe Deprez, Centre d'Excellence en Technologies de
l'Information et de la Communication (CETIC), Belgium

* Karim Djemame, University of Leeds, UK

* Maria Fazio, University of Messina, Italy

* Francesc Lordan, Barcelona Supercomputing Center (BSC-CNS), Spain

* Fabrizio Magugliani, E4 Computer Engineering, Italy

* Dana Petcu, University of West Timisoara, Romania

* Alessandro Raganato, University of Milano-Bicocca, Italy

* Domenico Siracusa, University of Trento, Italy

* Jacopo Soldani, University of Pisa, Italy,

* Ettore Trevisiol, AWS, Italy

* Alessandro Tundo, Technische Universität Wien, Austria

* Indika Kumara, JADS, The Netherlands

* Alireza Furutanpey, Technischen Universität Wien, Austria (quantum)

* Radosław Piliszek, 7Bulls, Poland

* Josu Diaz de Arcaya, Tecnalia

ICL-GNSS WIPHAL workshop DL extension

Dear colleagues,
The Work-in-Progress branch of the International Conference on Localization
and GNSS (ICL-GNSS), the WIPHAL workshop, has its submission deadline
extended to April 22 (midnight CET).
The conference will take place in Rome, Italy on June 10-12, 2025.
Regards,
Jari Nurmi
ICL-GNSS General Chair

 

— From bench to the wild: Recent Advances in Computer Vision methods

 From bench to the wild: Recent Advances in Computer Vision methods
(WILD-VISION)
Pattern Recognition
Website:
https://www.sciencedirect.com/journal/pattern-recognition/about/call-for-papers#from-bench-to-the-wild-recent-advances-in-computer-vision-methods-wild-vision

Submission Portal Open: October 27, 2024
Extended Submission Deadline: April 30, 2025

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

=== Call for papers ===

The rapid advancement of visual pattern recognition systems has led to
their transition from laboratory settings to real-world applications,
where they face the challenges of distribution shifts and adversarial
samples. This special issue focuses on innovative methodologies that
enhance the robustness and generalization capabilities of visual
classifiers on unknown data in diverse, uncontrolled environments,
addressing key issues such as dataset imbalance, adversarial attacks,
and the exploitation of multi-modal systems. Submissions are encouraged
from researchers exploring neural network architectures, data
augmentation, multi-task learning, and multi-sensor fusion techniques to
improve performance in real-world conditions.

This special issue seeks to collect cutting-edge research that advances
the generalization capabilities of visual classifiers under real-world
conditions. The scope includes, but is not limited to, the development
of robust neural network architectures, transformers, and machine
learning models that address challenges such as distribution shift,
adversarial attacks, and dataset imbalance. Contributions leveraging
multi-task neural networks, multimodal approaches (e.g., vision-language
models, multi-sensor fusion), and efficient, lightweight models for edge
devices are highly encouraged. Papers should align with the broader
topics of computer vision, image processing, multimedia systems, and
biometrics, with a focus on improving real-world performance across
various applications, including autonomous driving, cognitive robotics,
and security-critical environments.

Topics of interest are but not limited to:

1) Novel Neural Networks or other Architectures (e.g. Transformers) for
Dealing with Distribution Shifts in the Wild
2) Data Augmentation Strategies, Generative and Degradation models for
Enhancing Generalization on Unseen Data
3) Robustness against Adversarial Attacks
4) Bias Mitigation in Unbalanced Datasets
5) Multi-task vs Single-task Learning in Real-world Scenarios
6) Resource-efficient Architectures for Edge Computing and (near)
Real-time Processing
7) Vision-Language Models and other Multi-modal Approaches
8) Multi-sensor Fusion for Enhanced Performance
9) New Datasets and Benchmarks for Computer Vision Systems in the Wild
10) Novel Applications and Case Studies

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

=== Guest editors ===

George Azzopardi, PhD
University of Groningen, Groningen, The Netherlands
E-mail: g.azzopardi@rug.nl

Laura Fernández Robles, PhD
University of León, Leon, Spain
E-mail: l.fernandez@unileon.es

Antonio Greco, PhD
University of Salerno, Fisciano, Italy
E-mail: agreco@unisa.it

Bruno Vento, PhD Student
University of Naples Federico II, Napoli, Italy
E-mail: bruno.vento@unina.it

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

Design by 2b Consult