What is Motion for?

About the Workshop

Motion is an important cue for many perception tasks from navigation to scene understanding. This workshop will explore various ways of representing and extracting motion information, and provide a venue to exchange ideas about the use of motion in Computer Vision.

We invite paper contributions discussing temporal and motion representations, their applications, evaluation metrics, and benchmarks that will help understand and shape the future of temporal and motion representations and its role in the field of computer vision and other related areas.

The workshop will focus on topics including (but not limited to):

Motion representations (optical flow, stereo, scene flow, and alternatives)
Benchmarks involving motion estimation or motion understanding
Multi-frame and long term motion representations
Applications of motion estimation and representations and the impact on other computer vision problems (e.g. tracking, action classification, video captioning, etc)
Motion representations in other applications, such as graphics, autonomous driving, robotics, medical imaging, animal tracking etc
Event cameras and applications of event-based representations

Instructions for Authors

Speakers

Andrew Owens

Assistant Professor, University of Michigan

Angjoo Kanazawa

Assistant Professor, University of California, Berkeley

Ce Liu

Chief Architect for Computer Vision, Microsoft Azure AI

Deva Ramanan

Professor, Carnegie Mellon University

Jia Deng

Assistant Professor, Princeton University

Tali Dekel

Assistant Professor, Weizmann Institute & Research Scientist, Google

Weidi Xie

Assistant Professor, Shanghai Jiao Tong University

Instructions for Authors

We will accept submissions in two formats:

Previously published papers (up to 12 pages in ECCV submission format) representing work that is relevant to the workshop and has been published in a peer-reviewed venue before. These submissions will be checked for relevance to the workshop, but will not undergo a complete review, and will not be published in the workshop proceedings.
Novel works and ideas in the form of full papers (up to 12 pages in ECCV submission format) or extended abstracts (up to 4 pages, no format will be given preference over the other) representing novel work that has not been previously published or accepted for publication in a peer-reviewed venue. These submissions will undergo double-blind review, and authors of accepted works will have the option to have their work included in the ECCV workshop proceedings. Note that if you want to re-submit your paper to a future Computer Vision conference, the length should not exceed 4 pages including citations.

Accepted papers will be presented as posters/short online presentations, and the authors of the best paper will be invited to give an oral presentation. The workshop website will provide links to the accepted papers. Authors of novel and previously unpublished papers will have the option to have their papers included in the ECCV workshop proceedings.

Papers should be submitted via CMT, at the following URL: https://cmt3.research.microsoft.com/WIMF2022

Dual submission policy: Please do not submit work for peer review to two workshops/conferences simultaneously.

Important Dates

Paper submission deadline extended to: September 2, 2022 11:59:59 AM PST.
Notification to authors: September 26th, 2022.
Finalized workshop program: October 10th, 2022.
Workshop: Monday, October 24, 2022

Hybrid workshop, with both in-person and virtual attendance option.

Workshop Program

Monday, October 24, 2022. A full-day hybrid workshop.

Location: Royal Ballroom H, Intercontinental David Hotel, Tel Aviv, Israel.

IDT	CST	EDT	Duration	Description	Speaker
09:00	14:00	02:00	5 mins	Opening Remarks	Organizers
09:05	14:05	02:05	30 mins	Invited Speaker 1	Andrew Owens
09:35	14:35	02:35	30 mins	Invited Speaker 2	Jia Deng
10:05	15:05	03:05	55 mins	Poster Session + Coffee Break
11:00	16:00	04:00	30 mins	Invited Speaker 3	Angjoo Kanawaza
11:30	16:30	04:30	30 mins	Invited Speaker 4	Weidi Xie
12:00	15:00	05:00	15 mins	Spotlight Talks (5 mins each) Tonderski et al. Amir et al. Tchenegnon et al.
12:00	15:00	05:00	1 hr	Lunch
13:00	16:00	06:00	30 mins	Invited Speaker 5	Tali Dekel
13:30	16:30	06:30	1 hr	Poster Session + Break
14:30	17:30	07:30	30 mins	Invited Speaker 6	Dava Ramanan
15:00	18:00	08:00	30 mins	Invited Speaker 7	Ce Liu
15:30	18:30	08:30	1 hr	Panel Discussion	Ce Liu, Weidi Xie, Andrew Owens

Awards

Best Spotlight: Shir Amir, Tali Dekel, Shai Bagon, Yossi Gandelsman, "On the Effectiveness of ViT Features as Local Semantic Descriptors".

Best Poster: Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Jae Won Cho, In So Kweon, "Optical Flow Estimation from a Single Motion-blurred Image".