Visual Detection, Recognition and Prediction at Altitude and Range

in conjunction with

The IEEE/CVF International Conference on Computer Vision
(ICCV 2021)

Virtual Conference, Oct. 11th - 17th, 2021

Topics of the Workshop

Vision-based detection, recognition and prediction studies have recently achieved highly accurate performances, which have narrowed the gap between research and real-world applications. Beyond these well-explored detection, recognition and prediction capabilities of modern algorithms, vision-based understanding at altitude and range will likely be one of the next big research topics in the field of computer vision. Vision-based understanding at altitude and range is a very challenging problem, even for humans, and successful automatic solutions will unlock, empower and extend human-like capabilities in self-driving cars, robots and surveillance cameras. In autonomous driving, vision-based understanding at distance of a traffic scene, objects and lanes is a critical piece of the autonomous puzzle that can help to provide a better solution for planning and control. Various sensors such as cameras and lidar are used as “eyes” of a vehicle, and advanced vision-based algorithms are required to allow safe and effective driving. In medical domains, vision-based understanding can be used for automated Covid-19 and flu prediction at distance. In agriculture and forestry, vision-based understanding can be combined with drones and colour/hyperspectral cameras to access biological threats.

In this workshop, the topics of interest include, but are not limited to:

• Tiny and blurry Object Detection

• Object Recognition at distance

• Long range face recognition

• Human gait recognition at distance

• Long range object tracking

• Early event prediction at distance

• Human Re-ID at distance

• Multi-agent forecasting at distance

• Activity and trajectory forecasting at distance

• Human behavior and pose prediction at distance

• Visual DeepFake Prediction at distance

• Prediction of agricultural parameters from satellite imagery

• Databases, evaluation and benchmarking in long range visual detection and recognition

>> need discussion >> This ICCV'21 Workshop Vision at Distance shares the same interests with further extensions in Altitude and Range. It follows a very successful CVPR Precognition Workshops organized in 2019, 2020 and 2021, which featured talks from researchers across a number of industries, insightful presentations, and large attendance. For full programs, slides, posters, and other resources, please visit the 2019, 2020, 2021 workshop websites.

Important Dates

Paper submission deadline: 15/07/2021

Notification to acceptance: 02/08/2021

Camera-ready deadline: 16/08/2021

Invited Speakers (TBA)

Program (TBA)

Submission Instructions

All submitted papers will be assessed based on their novelty, technical quality, potential impacts, insights, depth, clarity, and reproducibility. For each accepted submission, at least one author must attend the workshop and present the paper. There are two ways to contribute submissions to the workshop:

• Extended abstracts submissions are single-blind peer-reviewed, and author names and affiliations should be listed. Extended abstracts are limited to a total of four pages (including references). Extended abstracts of already published works can also be submitted. Accepted abstracts will be presented at the poster session, and will not be included in the printed proceedings of the workshop.

• Full paper submissions are double-blind peer-reviewed. The submissions are limited to eight pages, including figures and tables, in the ICCV style. Additional pages containing only cited references are allowed. Further information about formatting and style files is available here. Accepted papers will be presented at the poster session, with selected papers also being presented in an oral session. All accepted papers will be published by the ICCV in the workshop proceedings.

Submission website: TBD

Organizers

• Khoa Luu (University of Arkansas)

• Kris Kitani (Carnegie Mellon University)

• Son Lam Phung (University of Wollongong)

• Hien Van Nguyen (University of Houston)

• Nemanja Djuric (Aurora Innovation)

• Ngan Le (University of Arkansas)

For questions please contact the organizers at: khoaluu@uark.edu.

Workshop Sponsors (TBD)

Program Committee Members

• TBA

The Second Precognition CVPR Workshop - 2020

It was a virtual workshop for the paper presentations, the posters and the talks. Uber ATG generously sponsored to reward the authors of the best paper and the best student paper.

The First Precognition CVPR Workshop - 2019

There were about 300 attendants for the paper presentations, the posters and the talks. Uber ATG generously sponsored to reward the authors of the best paper and the best student paper.