VisionDocs
4th Workshop on
Computer Vision Systems for Document Analysis and Recognition
4th Workshop on
Computer Vision Systems for Document Analysis and Recognition
Overview
The rapid growth of foundation models and multimodal AI has transformed document understanding into a key research area with broad scientific and industrial relevance. While recent advances have significantly improved performance on individual tasks, many challenges remain, including robust reasoning over complex document collections, generalization across heterogeneous layouts, multilingual and low-resource settings, historical documents, and efficient adaptation to emerging document domains.
VisionDocs aims to bring together researchers working on computer vision, multimodal learning, language models, and document intelligence to discuss the next generation of AI systems for document understanding. Topics of interest include vision-language foundation models, agentic document AI, retrieval-augmented systems, generative models, self-supervised learning, efficient adaptation, and trustworthy evaluation. By fostering collaboration between the computer vision, document analysis, and broader AI communities, the workshop will highlight state-of-the-art advances, identify open challenges, and promote new research directions toward scalable, reliable, and practical document intelligence.
Call for Paper
Research papers are solicited in, but not limited to, the following topic areas:
Document image processing
Physical and logical layout analysis
Text and symbol recognition
Handwriting recognition
Document analysis systems
Document classification
Multimedia document analysis
Recognition of tables and formulas
Document forensics and provenance
Medical document analysis
Data-efficient Document Analysis
Document synthesis
Document vision question answering
Extracting document semantics
Graphics Recognition
Structured document generation
Historical document analysis
Document summarization and translation
Agentic systems for document understanding
Multi-modal document Analysis
Multi-modal document Generation
Datasets and benchmarks of document analysis
Keynote Speaker
Submission
We invite researchers to submit their original and unpublished work related to the workshop's theme. Authors can submit either regualr papers (max 8 pages + reference) or short papers (max 4 pages + reference), following the WACV 2027 formatting guidelines.
Accepted regular papers will be published in the WACV 2027 Workshop Proceedings. Accepted short papers will be published on this website only and will not be included in the conference proceedings.
All submissions should be compiled for double-blind review, adopt the standard main conference WACV 2027 template.
Accepted papers must be presented in person during the workshop, either as oral presentations or posters. If none of the authors presents the work in person, the paper will be removed from the WACV 2027 Workshop Proceedings.
Submission regular paper: OpenReview TBA
Submission short paper: google form
Important Dates
Regular Papers:
Paper submissions: October 13, 2026, at 11:59 PM Pacific Time
Author Notification: November 02, 2026, at 11:59 PM Pacific Time
Camera-ready: November 20, 2026, at 11:59 PM Pacific Time
Short Papers:
Paper submissions: November 12, 2026, at 11:59 PM Pacific Time
Author Notification: November 19, 2026, at 11:59 PM Pacific Time
Short paper Camera-ready: November 26, 2026, at 11:59 PM Pacific Time
Workshop date: January 04 or 05, 2027