Robust Video Scene Understanding:
Tracking and Video Segmentation

A Workshop and Challenge at CVPR 2021

Virtual - Friday 25th June, 2021 - Whole day

Call for Workshop Paper Submissions

We invite researchers working on topics such as video and scene understanding, tracking, and video segmentation, to submit papers to be published at our workshop.

Summary:

We present a call for papers on topics related to video and scene understanding, tracking, and video segmentation.

Format: Short 4 page summary of recent work, or teaser of upcoming work. CVPR format. Single blind (non-anonymized).

 

Submission Deadline: Thursday, 4th of June.

Papers will be presented at our RVSU CVPR'21 Workshop.

 

Countdown to Deadline:

Detailed Information:

Workshop Overview:

 

Object tracking, and more generally understanding dynamic scenes in video, is one of the core research directions for the computer vision community. Every year there are many papers and workshops in this area. However, such research within the computer vision community is currently extremely fragmented, with a huge number of different benchmarks and tasks, each of which has its own sub-community of people only evaluating against their own benchmark. We aim to bring together these discrete sub-communities, to share knowledge and promote research into algorithms that work across a variety of different settings and scenarios.

 

 

Topics:

 

We invite papers from any of the following (or similar) topics:

 - Video Scene Understanding

 - Multi-Object Tracking

 - Video Segmentation

 - Single Object Tracking

 - 3D Tracking

 - Ethical and Safe Video Algorithms and Research

 - Video Domain Adaptation

 - Benchmarking and Evaluation for Video Scene Understanding

 - Analyzing Humans in Video

 - Future Trajectory Prediction

 - Vision for Self-Driving in Dynamic Scenes 

 - Self-Supervised and Unsupervised Video Representation Learning

 - Simulation for Dynamic Scene Understanding

 - Low-level Feature Tracking

 - Action Recognition and Video Classification

 - Video Detection

 - Architectures for Video

 - Optical Flow and Scene Flow

 - Video Object Discovery

 - Online / Real-Time Video Algorithms

 

 

Submission and Review format:

 

The workshop aims to be a venue to present only the most exciting recent and upcoming work. We expect submissions to be sufficiently interesting to merit future or concurrent publication in CVPR/ICCV/ECCV. Paper submissions are therefore limited to 4 pages (including references and acknowledgements) to ensure that this remains possible. This can be thought of as a condensed summary of recent work or a short teaser for upcoming work. We do not accept work that has already been published at the submission date (e.g., in conferences which have already taken place).

 

Thus, we allow short (4 page) versions of:

                     Accepted papers at CVPR'21, ICML'21, ICRA'21, RSS'21, etc.  

                     Papers under review at ICCV'21, IROS'21, NeuIPS'21, BMVC'21, etc.  
                     Papers planning to be submitted to CVPR'22, ECCV'22, NeuIPS'22, etc.  

We do not allow versions of:

                     Papers from ICLR'21, WACV'21, ECCV'20, CVPR'20, etc. because these conferences would have already passed.

Paper submissions should be in CVPR'21 format (but restricted to 4 pages including references).  

 

Reviewing will be single-blind. There will be no opportunity for rebuttal.

 

 

Paper presentation:

 

Accepted papers will be self-published on the website of this workshop (not in the official proceedings, although they have the same value).

 

All accepted papers will be asked to submit a 1-minute spotlight video, which will be played live during the workshop at a spotlight session.

 

All accepted papers will be asked to submit a static pdf poster. After the spotlight session, we will have an approximately 45 minute poster session live on gatherly.io, where participants can interact with presenters, who can refer to their posters.

 

All papers, posters and videos will be uploaded to the website of this workshop.

 

We will award a best paper award, and a best paper award runner up. Both will have the chance to present an approximately 10 minute live oral presentation during the workshop. 

 

 

Important dates: 

 

Paper submission:                                                                                            Friday, 4th of June.

Reviews and decisions to authors:                                                          Tuesday, 15th of June.

Camera-ready, Poster, and Video submission:                                  Monday, 21st of June.

Workshop                                                                                                             Friday, 25th of June.

 

All deadlines are the end of the day, Anywhere on Earth. There will be no extensions.

 

 

Submit now:

Workshop Sponsors

 

Main Organizer and

Contact Person:

 

 

Jonathon Luiten (RWTH Aachen University)

luiten@vision.rwth-aachen.de

 

Copyright © 2020 Jonathon Luiten