Vision4Neuro · Track call for papers

Neural Decoding and Computer Vision for Behavioral and Clinical Neuroscience

First edition. A half-day track of the combined WACV 2027 workshop Vision for Biomedical Discovery, running in the afternoon. Vision4Neuro keeps its own call for papers, program committee and reviewing process.

Scope and motivation

Vision4Neuro is about computer vision for neural decoding, behaviour and clinical neuroscience. Reconstructing what someone saw from EEG, MEG, fMRI, fNIRS or ECoG; aligning the representations of vision-language models with cortical responses; reading behaviour from video through eye tracking and markerless pose estimation; and turning any of this into interfaces and clinical measures that work outside a controlled lab.

The recurring obstacle is the same one WACV cares about: models that work on the subjects, sessions and devices they were fitted on, and degrade elsewhere. Cross-subject and cross-session transfer, domain shift, calibration and open-set recognition are therefore first-class topics of the track, not afterthoughts.

Shared with CVPath. The joint panel after lunch asks what counts as evidence that a model is ready for clinical use — a question with the same shape in neural decoding as in whole-slide imaging. Posters from both tracks are presented together in one combined session.
Call for papers

Topics of interest

We invite original research contributions in, but not limited to, the following areas.

  • Decoding and reconstruction of visual experience from neural signals (EEG, MEG, fMRI, fNIRS, ECoG)
  • Brain-to-image and brain-to-video generation
  • Encoding models and representational alignment between vision-language models and cortex
  • Multimodal neuroimaging and fusion
  • Brain-computer interfaces, gaze-driven interfaces and assistive communication
  • Vision-based behavioural phenotyping: eye tracking and markerless pose analysis
  • Clinical and translational applications in neurodevelopmental and neurodegenerative conditions
  • Robustness in the wild: cross-subject and cross-session transfer, domain shift, calibration, open-set recognition
  • Self-supervised and foundation models for neural time series
  • Datasets, benchmarks and reproducibility for neural and behavioural data
  • Interpretability, privacy and ethics of neural and behavioural data
Submission types

Three ways to contribute

All submissions use the WACV 2027 paper format. Page limits exclude references.

Submission typeLengthProceedingsPresentation
Regular paper8 pages (excluding references)Archival — published in the WACV 2027 Workshop Proceedings (IEEE Xplore and CVF Open Access)Oral or poster
Short paper4 pages (excluding references)Non-archival — not published in the proceedingsPoster, possibly lightning talk
Extended abstract2 pages (excluding references)Non-archival — not published in the proceedingsPoster, possibly lightning talk
Proceedings. Accepted regular papers are archival and appear in the WACV 2027 Workshop Proceedings (IEEE Xplore and CVF Open Access). Short papers and extended abstracts are non-archival and are not published in the proceedings.
Submission instructions

How to submit to Vision4Neuro

  1. Prepare your paper in the WACV 2027 format

    Use the official WACV 2027 author kit (LaTeX or Word), the same template as the main conference. Page limits above exclude references; supplementary material is optional and is not counted in the page limit.

  2. Anonymise the submission

    Reviewing is double-blind for all submission types. Remove author names and affiliations, and avoid identifying acknowledgements or self-references in the first person.

  3. Submit through OpenReview, choosing the Vision4Neuro track

    Both tracks share one submission site with a track selector, so that authors of either half of the day use the same entry point.

  4. Present in person

    WACV 2027 does not accommodate virtual workshops or remote presentations. At least one author of every accepted contribution must register for the conference and present on site at Disney Springs.

Questions on submission to this track: mpetrov@uccs.edu.

Important dates

Vision4Neuro timeline

Both tracks of the combined workshop follow the same timeline.

DateMilestone
October 9, 2026Regular papers (8 pages, archival) — submission deadline (23:59 AoE)
October 30, 2026Notification to authors, regular papers
November 6, 2026Short papers (4 pages) and extended abstracts (2 pages) — submission deadline (23:59 AoE)
November 20, 2026Notification, short papers and extended abstracts
November 20, 2026Camera-ready deadline, archival papers (23:59 PT)
January 4–5, 2027Workshop day at WACV 2027

All deadlines are 23:59 Anywhere on Earth unless stated otherwise. The OWL challenge follows its own timeline, on the challenge page.

Who reviews your paper

Vision4Neuro organizers and program committee

Reviewing is handled by the Vision4Neuro program committee, independently of the CVPath track.

Marios Petrov

University of Colorado Colorado Springs, USA

Primary contact, Vision4Neuro

Adham Atyabi

University of Colorado Colorado Springs, USA

Terrance E. Boult

University of Colorado Colorado Springs, USA

Frederick Shic

Seattle Children's Research Institute and University of Washington, USA

Contact

For questions about the Vision4Neuro track, write to the primary contact, Marios Petrov, at mpetrov@uccs.edu. Questions about the day as a whole can go to either track contact; see the contact page.