Precognition: Seeing through the Future

in conjunction with

The 33rd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)

Seattle, WA, USA, June 14th-19th, 2020

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 forecasting

• Multi-agent forecasting

• Human behavior prediction

• Human face aging prediction

• Anticipation of trajectories

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

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

• Databases, evaluation and benchmarking in precognition

This is the second Precognition workshop organized at CVPR. It follows a very successful workshop organized in 2019, 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 website of Precognition 2019.

Important dates

Workshop paper submission deadline: March 28th, 2020 (anywhere on Earth)

Notification to authors: April 14th, 2020

Camera-ready deadline: April 22nd, 2020

Workshop: June 19th, 2020

Invited speakers

• Raquel Urtasun (Chief Scientist at Uber ATG) [video]

  • "Joint Detection and Motion Forecasting"

• Chen Sun (Staff Research Scientist at Google Research) [slides] [video]

  • "Action Recognition in Videos and Action Forecasting"

  • Note: Joint work with Cordelia Schmid (Research Director at INRIA, Research Scientist at Google Research)

• Nick Rhinehart (Postdoc at UC Berkeley Artificial Intelligence Research (BAIR)) [video]

  • "Jointly Forecasting and Controlling Behavior with High-Dimensional Observations"

Program (all times in PDT)

• 1:55 - 2:00 PM - Workshop kick-off

• 2:00 - 2:30 PM - Invited talk: Chen Sun, "Action Recognition in Videos and Action Forecasting"

• 2:30 - 3:30 PM - Q&A session with the authors of accepted papers, pre-recorded talks available at CVPR website

  • "Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras", Olly Styles (Univ. of Warwick), Tanaya Guha (Univ. of Warwick), Victor Sanchez (Univ. of Warwick), Alex Kot (Nanyang Technological Univ.) [Best Student Paper Award] [open access] [slides] [video]

  • "Dynamic Neural Relational Inference for Forecasting Trajectories", Colin Graber (UIUC), Alexander Schwing (UIUC) [Best Paper Award] [open access] [slides] [video]

  • "Glaucoma Precognition: Recognizing Preclinical Visual Functional Signs of Glaucoma", Krati Gupta (Indian Institute of Techn. Mandi), Anshul Thakur (Univ. of Tennessee Health Science Center), Michael Goldbaum (UCSD), Siamak Yousefi (Univ. of Tennessee Health Science Center) [open access] [slides] [video]

  • "A Multimodal Predictive Agent Model for Human Interaction Generation", Murchana Baruah (Univ. of Memphis), Bonny Banerjee (Univ. of Memphis) [open access] [slides] [video]

  • "SILA: An Incremental Learning Approach for Pedestrian Trajectory Prediction", Golnaz Habibi (MIT), Nikita Jaipuria (Ford Motor Company), Jonathan How (MIT) [open access] [slides] [video]

• 3:30 - 4:15 PM - Invited talk: Raquel Urtasun, "Joint Perception and Motion Forecasting"

• 4:15 - 4:45 PM - Invited talk: Nick Rhinehart, "Jointly Forecasting and Controlling Behavior with High-Dimensional Observations"

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. 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 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 at the poster session, with selected papers also being presented in an oral session. All accepted papers will be published by the CVPR in the workshop proceedings.

Submission website: https://cmt3.research.microsoft.com/precognition2020

Best paper awards

Uber ATG has generously agreed to reward first authors of a best paper and a best student paper with valuable Uber ATG swag merchandise.

Organizers

• Khoa Luu (University of Arkansas)

• Kris Kitani (Carnegie Mellon University)

• Minh Hoai Nguyen (Stony Brook University)

• Hien Van Nguyen (University of Houston)

• Nemanja Djuric (Uber ATG)

• Utsav Prabhu (Google Research)

For questions please contact the organizers at precognition.organizers@gmail.com.

Program Committee members

• Radu Timofte, ETH Zurich

• Arun Ross, MSU

• Marios Savvides, CMU

• Ankit Laddha, Uber ATG

• Carlos Vallespi-Gonzalez, Uber ATG

• Chen Sun, Google

• Chi Nhan Duong, PDActive, Inc.

• David Ross, Google

• De-An Huang, Stanford

• Fang-Chieh Chou, Uber ATG

• Minh Triet Tran, University of Science, HCM

• Henggang Cui, Uber ATG

• Thi Hoang Ngan Le, UA

• Kaushik Roy, NCAT

• Kha Gia Quach, PDActive, Inc.

• Namhoon Lee, Oxford

• Nick Rhinehart, UC Berkeley

• Rowan McAllister, UC Berkeley

• Slobodan Vucetic, Temple University

• Vladan Radosavljevic, Spotify

• Wei-Chiu Ma, MIT

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.