on June 12, 2025

The 4th Workshop on Transformers for Vision (T4V)

at CVPR 2025

Workshop location: TBD
Poster session location: TBD

A half-day summit to bring together the latest ideas in using Transformers for image, video, 3D and multi-modal visual processing

Overview

Transformers have recently emerged as promising and versatile deep neural architecture in various domains. Since the introduction of Vision Transformers (ViT) in 2020, the vision community has witnessed an explosion of transformer-based computer vision models with applications ranging from image classification to dense prediction (e.g., object detection, segmentation), video, self-supervised learning, 3D and multi-modal learning. This workshop presents a timely opportunity to bring together researchers across computer vision and machine learning communities to discuss the opportunities and open challenges in designing transformer models for vision tasks.

Invited Speakers

University of Waterloo

UC Berkeley

We accept abstract submissions to our workshop. All submissions shall have maximally 4 pages (excluding references) following the CVPR 2025 author guidelines.

Submission Portal:

CMT: https://cmt3.research.microsoft.com/T4V2025

Important Dates:

Submission Deadline: April 18th, 2025 (11:59pm PST)

Notification of Acceptance: May 25th, 2025

Camera-Ready Submission Deadline: June 8th, 2025

Workshop Date: June 12th, 2025

Organizers

Tyler ZhuPrinceton University
Shilong LiuTsinghua University
Fuxiao LiuUMD College Park

Program Committee

TBD