CVPR 2023

Vancouver, CANADA

June, 2023

You can find a list of accepted papers later. 

TBWorkshop Overview

Computer Vision has a long history of academic research, and recent advances in deep learning have provided significant improvements in the ability to understand visual content. As a result of these research advances on problems such as object classification, object detection, and image segmentation, there has been a rapid increase in the adoption of Computer Vision in industry; however, mainstream Computer vision research has given little consideration to speed or computation time, and even less to constraints such as power/energy, memory footprint and model size, or carbon emission. Nevertheless, addressing all of these metrics is essential if advances in Computer Vision are going to be widely available on mobile and AR/VR devices. In this year’s ECV workshop, our topics include but are not limited to the following:

Particular topics that will be covered:

• Efficient Neural Architecture, Compression, Quantization and Hardware Acceleration

  • Compact and efficient neural network architecture (CNN, Transformer, or mixed) for mobile and AR/VR devices

  • Efficient architecture search algorithm for different vision tasks (detection, segmentation, generative models, etc.)

  • Model compression (sparsification, binarization, quantization, pruning, thresholding and coding etc.) for efficient inference with deep networks and other ML models

  • Investigations into the processor architectures (CPU vs GPU vs DSP) that best support mobile applications.

  • Hardware accelerators to support Computer Vision on mobile and AR/VR platforms.

• Data-Efficient Learning

  • Methods, algorithms, systems that improves data efficiency of deep learning

  • Semi-, weakly-, self-supervised learning for computer vision tasks

  • Zero-shot, few-shots learning, language-supervised learning

  • Open-set recognition, detection, and segmentation 

• Efficient Generative Models

  • Compact and efficient architectures for generative models, such as Generative Adversarial Networks (GANs), Autoregressive models, Denoising Diffusion Probabilistic Models (DDPMs)

  • Model-pruning and optimization algorithm for running generative models on mobile and AR/VR devices

  • Efficient Generative architecture search algorithm for generative model tasks (domain adaptation, style transfer, deep fake faces)

  • Latency-aware loss design for efficient generative models training

• Efficient 3D models

  • Efficient 3D understanding models, including point-cloud, voxel, multi-view image based models.

  • Efficient neural rendering: efficient methods, models, and systems for reconstructing and rendering 3D scenes and objects. Efficient NeRF for on-device reconstruction training and rendering.

• Low Power Computer Vision Challenge

  • On-device Disaster Scene Parsing Competition: Perform semantic segmentation on Nvidia Jestson Nano with disaster images captured by unmanned aerial vehicles (UAV).

• Mobile and AR/VR Applications 

  • Novel mobile and AR/VR applications using Computer Vision such as image processing (e.g. style transfer, body tracking, face tracking, depth estimation) and augmented reality

  • Multi-task learning and efficient multi-task models

  • On-device training, federated learning on devices

Program Summary

This workshop will feature invited talks, selected paper publication, and panel discussion. See the program section for details.

Call for papers

Important dates

Workshop paper submission deadline: TBD

Notification to authors: TBD

Camera ready deadline: TBD -- this is a firm deadline per CVPR workshop program.

Submission instructions

We are following the CVPR paper format: https://cvpr.thecvf.com/Conferences/2024/AuthorGuidelines

LaTeX/Word Templates: CVPR 2024 Author Kit.

We accept two forms of papers:

• Long paper: Long papers should not exceed 8 pages. All the requirements are the same as the CVPR paper style guide. Long papers are for presenting mature works. A long paper should not only describe novel ideas but also have full experiments and analyses to support the proposed ideas.

• Short paper: short papers should not exceed 4 pages. All other requirements are the same as the CVPR paper style guide. Short papers are for sharing early stage ideas. A short paper should describe novel ideas and have basic experiments to support the ideas. Comprehensive experiments and analyses, however, are not necessary.

Note the page limit includes figures and tables, in the CVPR style. Additional pages containing only cited references are allowed. Papers with more than 4 pages  (excluding references) will be reviewed as long papers, and papers with more than 8 pages (excluding references) will be rejected without review.

A paper should be submitted using the above templates.  The length should match that intended for final publication.

Blind review: we adopt double-blind review for this workshop. Submitted papers and supplementary materials should not reveal any information about the author.

Dual submission: We do not accept paper submissions that have been published (including at the CVPR main conference) or are under review for other conferences or workshops. Accepted papers are expected to be published at CVPR proceedings. 

Submission website

TBD