The 4th IEEE/CVF CVPR Precognition Workshop

Precognition: Seeing through the Future

in conjunction with

The 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)

New Orleans, June 19th - 24th, 2022

Topics of the Workshop

Vision-based detection and recognition studies have been recently achieving highly accurate performance and were able to bridge the gap between research and real-world applications. Beyond these well-explored detection and recognition capabilities of modern algorithms, vision-based forecasting will likely be one of the next big research topics in the field of computer vision. Vision-based prediction is one of the critical capabilities of humans, and potential success of automatic vision-based forecasting will empower and unlock human-like capabilities in machines and robots.

One important application is in autonomous driving technologies, where vision-based understanding of a traffic scene and prediction of movement of traffic actors is a critical piece of the autonomous puzzle. Various sensors such as camera and lidar are used as "eyes" of a vehicle, and advanced vision-based algorithms are required to allow safe and effective driving. Another area where vision-based prediction is used is medical domain, allowing deep understanding and prediction of future medical conditions of patients. However, despite its potential and relevance for real-world applications, visual forecasting or precognition has not been in the focus of new theoretical studies and practical applications as much as detection and recognition problems.

Through organization of this workshop we aim to facilitate further discussion and interest within the research community regarding this nascent topic. This workshop will discuss recent approaches and research trends not only in anticipating human behavior from videos but also precognition in multiple other visual applications, such as: medical imaging, health-care, human face aging prediction, early even prediction, autonomous driving forecasting, etc.

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

  • Early event prediction

  • Activity and trajectory forecasting

  • Multi-agent forecasting

  • Human behavior and pose prediction

  • Human face aging prediction

  • Predicting frames and features in videos and other sensors in autonomous driving

  • Traffic congestion anomaly prediction

  • Automated Covid-19 prediction in medical imaging

  • Visual DeepFake prediction

  • Short- and long-term prediction and diagnoses in medical imaging

  • Prediction of agricultural parameters from satellite imagery

  • Databases, evaluation and benchmarking in precognition

This is the fourth Precognition workshop organized at CVPR. It follows very successful workshops organized since 2019, which all 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, and 2021 workshop websites.

Important Dates

  • Paper submission deadline: March 31st, 2022 (anywhere on Earth)

  • Notification to authors: April 15th, 2022

  • Camera-ready deadline: April 20th, 2022

  • Video presentation submission: June 12th, 2022

  • Workshop: June 19th, 2022

Invited Speakers

Sella Nevo

Lead of the Google Flood Forecasting Initiative
Adjunct Lecturer at Tel Aviv University
Co-founder and Head of Research at Probably Good

Alex Lang

Senior Manager
Perception at Cruise

Program (times are in CDT timezone)

  • 1:00PM - Workshop kick-off

  • 1:05PM - Invited talk: Sella Nevo, "Spatially Accurate Mapping & Forecasting of Disasters"

  • 1:40PM - Lightning talks (full papers)

      • Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction”, Luigi Filippo Chiara (University of Padua), Pasquale Coscia (University of Padova), Sourav Das (University of Padova), Simone Calderara (University of Modena and Reggio Emilia, Italy), Rita Cucchiara (Università di Modena e Reggio Emilia), Lamberto Ballan (University of Padova) [open access] [video] [slides]

      • HR-STAN: High-Resolution Spatio-Temporal Attention Network for 3D Human Motion Prediction”, Omar Medjaouri (University of Texas at San Antonio), Kevin Desai (University of Texas at San Antonio) [Best Paper Award] [open access] [video] [slides]

  • 2:00PM - Extended abstract session

      • Persistent-Transient Duality in Human Behavior Modeling”, Hung Tran (Deakin University), Vuong Le (Deakin University), Svetha Venkatesh (Deakin University), Truyen Tran (Deakin University) [pdf] [video] [slides]

      • Importance is in your attention: agent importance prediction for autonomous driving”, Christopher Hazard (Motional), Akshay Bhagat (Motional), Balarama Raju Buddharaju (Motional), Zhongtao Liu (Motional), Yunming Shao (Motional), Lu Lu (Motional), Sammy Omari (Motional), Henggang Cui (Motional) [pdf] [video] [slides]

      • S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction”, Yu-Wen Chen (National Tsing Hua University), Hsuan-Kung Yang (National Tsing Hua University), Chu-Chi Chiu (National Tsin-Hua University), Chun-Yi Lee (National Tsing Hua University) [pdf] [video] [slides]

  • 2:20PM - Invited talk: cancelled

  • 2:55PM - Lunch break

  • 3:30PM - Lightning talks (full papers)

      • Information Elevation Network for Online Action Detection and Anticipation”, Sunah Min (Electronics and Telecommunications Research Institute), Jinyoung Moon (Electronics and Telecommunications Research Institute) [open access] [video] [slides]

      • Joint Forecasting of Panoptic Segmentations with Difference Attention”, Colin Graber (UIUC), Cyril Jazra (University of Illinois at Urbana-Champaign), Wenjie Luo (Waymo LLC), Liangyan Gui (University of Illinois Urbana-Champaign), Alexander Schwing (UIUC) [open access] [video] [slides]

      • Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles”, Pha Nguyen (University of Arkansas), Kha Gia Quach (PDActive Inc.), Chi Nhan Duong (Concordia University), Ngan Le (University of Arkansas), Xuan-Bac Nguyen (University of Arkansas), Khoa Luu (University of Arkansas) [open access] [video] [slides]

  • 4:00PM - Invited talk: Alex Lang, "Learning to Track"

      • Abstract: The machine learning revolution has overturned classical perception and replaced it with neural networks. One of the last holdouts has been tracking where Kalman filters and other classical tracking algorithms have remained difficult to beat with neural networks in real time systems. In this talk, I will discuss our approach to ML-based tracking and demonstrate we can learn to track and use these neural networks in an autonomous vehicle.

  • 4:35PM - Lightning talks (full papers)

      • Sea Situational Awareness (SeaSAW) Dataset”, Parneet Kaur (Sea Machines Robotics), Arslan Aziz (Sea Machines Robotics), Darshan Jain (Sea Machines), Harshil Patel (Sea Machines Robotics), Jonathan Hirokawa (Sea Machines), Lachlan G M Townsend (Sea Machines), Christoph Reimers (Sea Machines), Fiona Hua (Sea Machines) [open access] [video] [slides]

      • Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization”, Changjie Lu (Wenzhou Kean University), Shen Zheng (Wenzhou Kean University), Gaurav Gupta (Wenzhou Kean University) [open access] [video] [slides]

  • 4:55PM - Workshop wrap-up

  • 5:00PM - End of workshop

Submission Instructions

All submitted work will be assessed based on their novelty, technical quality, potential impact, insightfulness, 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 abstract submissions are limited to a total of four pages (including references). Extended abstracts of already published works can also be submitted. Accepted abstracts 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 CVPR style. Additional pages containing only cited references are allowed (additional information about formatting and style files is available here). Accepted papers will be presented in an oral session. All accepted papers will be published by the CVPR in the workshop proceedings.

Submission website:


For questions please contact the organizers at

Khoa Luu
University of Arkansas,

Nemanja Djuric

Aurora Innovation Inc.

Kris Kitani

Carnegie Mellon University

Utsav Prabhu

Google Research

Hien Van Nguyen

University of Houston

Program Committee

  • Ankit Laddha (Cruise)

  • Chen Sun (Google)

  • Chi Nhan Duong (Concordia University)

  • Fang-Chieh Chou (Aurora)

  • Henggang Cui (Motional)

  • Joshua Manela (Waymo)

  • Kaushik Roy (North Carolina A&T State University)

  • Kha Gia Quach (PDActive)

  • Meng Fan (Aurora)

  • Nicholas Rhinehart (UC Berkeley)

  • Rowan McAllister (Toyota Research Institute)

  • Shangxuan Wu (Waymo)

  • Shivam Gautam (Aurora)

  • Shreyash Pandey (Aurora)

  • Slobodan Vucetic (Temple University)

  • Xinshuo Weng (Carnegie Mellon University)

  • Yu Kong (Rochester Institute of Technology)

Thanh Dat Truong

University of Arkansas

(Workshop Website Organizer)

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

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.

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.