Special Session on AI in Surgery
February 12th, 2025 
Daniela Lopez de Luise - Curating high-fidelity, open-access surgical datasets for AI training and validation.
- Innovative methods for self-supervised and semi-supervised learning in surgical AI applications.
- Development and application of foundation models for surgery.
- Data augmentation techniques tailored for surgical scenarios.
- AI-powered decision support systems for preoperative planning and risk assessment.
- Real-time AI for intraoperative surgical guidance and navigation.
- AI in postoperative monitoring and outcome prediction.
- Surgical Patient Digital Twins for personalized simulation and planning.
- AI for robotic-assisted surgery, including teleoperated and autonomous systems.
- Multimodal data fusion for enhanced surgical decision-making.
- Advancements in AI-driven surgical simulation and training.
- Sustainable AI solutions for surgical video processing and annotation.
- AI for surgical skill assessment using video analytics.
- Real-time segmentation and object detection in surgical images.
- Human-AI collaboration in surgery to enhance collective intelligence.
- Strategies for engaging clinicians in co-creating AI applications.
- Challenges and solutions for integrating AI into clinical workflows.
- Secure and robust AI systems for surgical care.
- Addressing ethical considerations and building trust in AI for surgery.
- Ensuring regulatory compliance for AI-based surgical tools.
- Benchmarking AI performance in surgical environments.
- Clinical trials and real-world validation of AI tools.
- Metrics and methodologies for evaluating AI in surgery.
Second MetaFood Workshop at CVPR 2025
February 12th, 2025 Daniela Lopez de Luise The MetaFood Workshop is a premier venue for research that addresses the pressing challenges of applying state-of-the-art computer vision algorithms to food-related data. While modern computer vision models excel on well-curated datasets, they struggle when confronted with food data in natural, uncontrolled environments—often called “data in the wild”. This difficulty arises from the inherent complexities of food imagery, such as noisy, watermarked, and low-resolution data commonly found online.
The MetaFood Workshop aims to bridge this gap by showcasing groundbreaking research and fostering discussions on innovative methods for analyzing and digitizing food data. We invite the computer vision community to tackle these challenges and contribute solutions that can drive forward the fields of food computing and AI-driven food analysis.
Our program will feature technical paper presentations and invited talks from leading experts.
- Multi-modal food data analysis covering images, video, audio, structured and/or unstructured text data
- Reasoning, in-context learning, and retrieval-augmented generation with Large-Language Models (LLMs)/ Vision-Language Models (VLMs) for food
- Food ontologies and LLM-based models for food data analysis
- Visual question answering with VLMs for food
- Food data analysis and uncertainty modeling
- Learning with noisy food labels
- Continual, self-supervised, semi-supervised, and unsupervised learning for food
- Food classification/detection/segmentation with 2D/3D bias
- Food 3D model reconstruction, Novel View Synthesis for food objects
- Food portion/nutrition value estimation
- Food manipulation understanding, robotic perception systems for food manipulation
- Food image quality analysis/inspection
- Food image/video generation and Generative AI
- Food video analysis and action (eating, cooking, etc.) recognition
- Fine-grained dietary monitoring and nutrition assessment
Join us at the MetaFood Workshop to explore how computer vision can revolutionize food understanding and contribute to solving real-world challenges in food computing.
============================
Important Dates:
- Paper submission deadline: 4th March 2025 (11:59 pm AOE)
- Supplementary material deadline: 6th March 2025 (11:59 pm AOE)
- Notification to authors: 1st April 2025
- Camera-ready deadline: 7th April 2025 (11:59 pm AOE)
Website: https://sites.google.com/view/cvpr-metafood-2025/
We look forward to your contributions.
Regards,
Second MetaFood Workshop – Organizing Team
Call for Challenge Participants: International Workshop on Interactive Video Search and Exploration @ CVPR 2025
February 12th, 2025 Daniela Lopez de Luise We invite researchers and practitioners in computer vision, information retrieval, and human-computer interaction to participate in the 1st International Workshop on Interactive Video Search and Exploration (IViSE 2025), held in conjunction with CVPR 2025.
📅 Date: June 11 – June 15
📍 Location: CVPR 2025 @ Nashville TN
🌐 Website: https://sites.google.com/view/ivise2025
Workshop Overview
The field of video understanding and retrieval has made significant strides in recent years, but current AI-driven methods struggle with long-form video content. IViSE 2025 aims to address this challenge by exploring human-machine teaming approaches for video search and question answering (QA).
This workshop will serve as a venue to compare “fully automated” approaches with “interactive, human-in-the-loop” systems for video retrieval. The focus will be on real-world scenarios involving large-scale video archives, bridging gaps between machine learning, computer vision, and user-centered interactive search strategies.
IViSE 2025 Challenge: Text-Based Video Retrieval and Question Answering
The IViSE 2025 challenge will use the Vimeo Creative Commons Collection (V3C) dataset—comprising 7,475 videos with a total duration of 1,000 hours—to evaluate state-of-the-art methods in:
1️⃣ Fully-Automated Track
Queries are provided in advance.
Participants develop end-to-end AI-based video retrieval and QA systems.
Solutions are evaluated on accuracy and retrieval effectiveness.
2️⃣ Interactive Track
Queries are presented during the workshop.
Teams must solve tasks in real-time within five minutes, leveraging human-machine collaboration.
Inspired by the Video Browser Showdown and Lifelog Search Challenge:
🔹 Known-Item Search (KIS): Given a textual description, retrieve the correct video segment and time interval.
🔹 Question Answering (QA): Answer a question based on a textual description of a video.
Both tracks will use standardized evaluation metrics and build upon existing benchmarks such as TRECVID & DVU for automated search, and Video Browser Showdown for interactive retrieval.
Why Participate?
Advance the field of long-form video retrieval and exploration.
Benchmark your methods against cutting-edge AI and interactive systems.
Engage with leading researchers in computer vision, video retrieval, and interactive search.
Compete in a structured challenge format with an emphasis on both fully automated & interactive approaches and also in a high-impact challenge at CVPR 2025.
Important Dates
📅 Feb 3, 2025 – Fully-Automated Track queries released
📅 Mar 24, 2025 – Submission deadline for Fully-Automated Track results & workshop papers
📅 Apr 3, 2025 – Reviews and challenge scores released
📅 Apr 7, 2025 – Camera-ready deadline
We look forward to your participation in IViSE 2025 as we explore the next frontier in interactive video search and long-form video understanding
Call for Participation: PBVS 2025 Multi-modal Aerial View Image Challenge – C
February 12th, 2025 Daniela Lopez de Luise The PBVS 2025 Multi-modal Aerial View Image Challenge – C invites researchers and practitioners to advance automated target recognition (ATR) by leveraging multi-modal aerial imagery. This competition focuses on the classification of synthetic aperture radar (SAR) data, utilizing both SAR and electro-optical (EO) inputs to explore how multi-modal information can enhance performance in challenging conditions.
Challenge Overview
Participants will develop a classification system to predict the class label of SAR imagery, distinguishing between 10 target classes and detecting out-of-distribution (OOD) targets. Innovative approaches such as domain adaptation, transfer learning, and fusion techniques are encouraged. Submissions will be evaluated on accuracy, novelty, and creativity, with top solutions invited for further recognition.
Key Dates
- 2025.01.19: Release of training data (inputs/outputs) and validation data (inputs only).
- 2025.01.21: Validation server opens.
- 2025.02.21: Final test data release (inputs only).
- 2025.03.02: Deadline for test results, fact sheets, and code submissions.
- 2025.03.04: Preliminary results and paper submission deadline.
- 2025.06.11: PBVS Workshop at CVPR 2025, results, and award ceremony.
Awards and Opportunities
Prizes will be awarded to the top three participants, and winners will be invited to submit their solutions as papers for presentation at the 21st IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS), held in conjunction with CVPR 2025.
Submission Guidelines
Participants are required to submit a description of their methodology alongside their results. Submissions will be reviewed for accuracy, reproducibility, and adherence to guidelines. Code and fact sheets must also be submitted for transparency and evaluation.
Resources
- Scripts for reproducibility and performance evaluation will be provided.
- A forum and direct email support (Justice Wheelwright: mavoc.pbvs@gmail.com) are available for queries.
For additional details, visit the competition page: PBVS 2025 Challenge.
This is an excellent opportunity to contribute to cutting-edge research in multi-modal ATR systems while gaining global recognition. We look forward to your participation.