Workshop 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. 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. This workshop will focus on efficient deep learning algorithms, models, and systems for computer vision. Particular topics include:

• 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) and augmented reality

  • Learning efficient deep neural networks under memory and computation constraints for on-device applications

• Efficient Neural Network and Architecture Search

  • Compact and efficient neural network architecture for mobile and AR/VR devices

  • Hardware (latency, energy) aware neural network architectures search, targeted for mobile and AR/VR devices

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

  • Optimization for latency, accuracy and memory usage, as motivated by embedded devices.

• Neural Network Compression

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

  • Scalable compression techniques that can cope with large amounts of data and/or large neural networks (e.g., not requiring access to complete datasets for hyperparameter tuning and/or retraining)

  • Hashing (Binary) Codes Learning

• Low-bit Quantization Network and Hardware Accelerators

  • 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.

  • Low-precision training/inference & acceleration of deep neural networks on mobile devices

• Efficient Generative Models

  • Compact and efficient style-transfer neural networks for 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 (for embedded devices)

  • Model-pruning and optimization algorithm for generative models running on mobile / embedded 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

Please note that in order to adjust to the CVPR publicaiton timeline, we set the camera-ready paper deadline the same as the paper submission deadline. This means that when you submit your paper, please make sure it is camera-ready -- it should be properly formatted and contains all the information such as author names, institutions, emails, etc. There will not be a chance to submit another camera-ready version. If the paper is accepted, the inital submission will be used as the camera-ready paper.

Workshop paper submission deadline: April 16, 2021

Camera ready deadline: April 16, 2021

Notification to authors: April 20, 2021

Submission instructions

We are following the CVPR paper format: http://cvpr2021.thecvf.com/node/33#call-for-paper

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.

Example submission paper with detailed instructions: egpaper_for_review.pdf

LaTeX/Word Templates: cvpr2021AuthorKit_2.zip

A paper should be submitted using the above templates. The length should match that intended for final publication. Please make sure the paper submission is camera-ready, and contains information such as author names, institutions, emails, etc. There will not be another chance to submit a camera-ready version.

Submission website

Please submit your papers through https://cmt3.research.microsoft.com/ECV2021.