2nd workshop on Vision-based InduStrial InspectiON (VISION)

Tower Lounge W15 @ ECCV 2024, Milano, Italy

9:30- 13:00, Monday, Sept 30th

Overview

Aims and Scope

The VISION workshop will provide a platform for the exchange of scholarly innovations and emerging practical challenges in Vision-based Industrial Inspection. Through a series of keynote talks, technical presentations, and challenge competitions, this workshop aims to (i) bring together researchers from the interdisciplinary research communities related to computer vision-based inspection; and (ii) connect researchers and industry practitioners to synergize recent research progress and current needs in industrial practice.

Keynote Talks

Dr. Bianca Maria Colosimo

Professor at Politecnico di Milano

Dr. Fugee Tsung

Chair Professor, HKUST, HKUST(GZ)

Dr. Raviteja Vemulapalli

Machine Learning Researcher, Apple

Program

Agenda

Time(CEST)	Topic
9:00 - 9:15	Opening Shanhari Sivagnanasundaram
9:15 - 10:15	Keynotes Prof. Colosimo Prof. Tsung Dr. Vemulapalli
10:15 - 10:40	Paper presentations (4 minutes for each oral paper)
10:40 - 11:30	Coffee break and poster session
11:30 - 12:25	Panel discussion
12:25 - 13:00	Data challenge winner announcement & presentation

Call for Papers

Topics of Interest (not limited to)

From an industry point of view:

Opportunities for development in vision-based inspection technology, new problem formulation, data formats, and potential applications
Deployment practices and challenges of production vision-based inspection systems
Open source datasets for vision-based inspection research

From an academic point of view:

Meta-Learning, Transfer Learning, and Domain Adaptation
Foundation Models in Industry Inspection
Multi-Modality Data Fusion for Industry Inspection
Unsupervised, semi-supervised, and supervised anomaly detection algorithms under data and annotation limitations
Data generation techniques for real-world data challenges
Data-centric tools to simplify data collection, and increase quality & efficiency
Robust, explainable machine learning for high-stake applications
Vision-based modeling, diagnosis, control, and quality improvement of the manufacturing system

Submission Instructions

Research and industrial papers relevant to the topics are invited. Authors have two options:

Regular paper: max 14 pages (details), appear in the ECCV workshops proceedings
Extended Abstracts: 4 pages, will NOT appear in the proceedings

Important Dates

Submit paper

Regular paper submission deadline (AoE):


July 29th	Paper submission deadline
Aug 19th	Author notification
Aug 23rd	Camera-ready submission

Extended abstract submission deadline (AoE):


Aug 10th	Paper submission deadline
Aug 23rd	Author notification

Challenges

Track

One Shot Industrial Defect Segmentation

Important Notes:

Participants in the VISION 24 Data Challenge retain sole and exclusive copyright ownership of their respective submitted works. All Participants are obliged to prepare and have readily available reproducible inference code for audits upon requests from Organizers on their technical reports.

The top three Performing Teams shall be invited to present their work onsite at the VISION’24 ECCV workshop.

The Organizers encourage all Participants to submit formal reports or methodology papers to the workshop paper submission track. The papers shall undergo a rigorous and formal evaluation process.

Participation

The detailed instructions and the dataset for this Challenge can be found via the below link.

To offer participants hands-on experience with the entire submission pipeline, we are now launching a Beta-test phase of the challenge. Please visit the challenge website for more details.

Learn more

Important Dates

Submit technical report


June 1st	Dataset release and registration open
July 25th	Beta test release
Aug 1st	Registration close
Aug 21st	Test data release
Aug 28th	Result submission deadline
Aug 30th	Camera-ready submission
Sep 6th	Winners announced