Precognition: Seeing through the Future
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
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
Workshop paper submission deadline:
March 31st, 2019
Notification to authors:
April 15th, 2019
April 19th, 2019
June 17th, 2019
"Perception and Prediction for Autonomous Driving at Uber ATG"
"Google Health Research: Medical Imaging Insights"
"Multi-modal Perceptual Understanding at IBM Research"
1:30PM - Workshop kick-off
1:45PM - Invited talk: Carl Wellington, "Perception and Prediction for Autonomous Driving at Uber ATG"
2:25PM - Lightning talks (full papers)
"Leveraging the Present to Anticipate the Future in Videos", Antoine Miech (Inria), Ivan Laptev (INRIA Paris), Josef Sivic (Inria and Czech Technical University), Heng Wang (Facebook Research), Lorenzo Torresani (Facebook AI Research), Du Tran (Facebook Research) [paper] [slides] [poster]
"Multimodal 2D and 3D for In-the-wild Facial Expression Recognition", Son Thai Ly (Chonnam National University), Nhu-Tai Do (Chonnam National University, Gwangju, South Korea), Guee-Sang Lee (Chonnam National University), Soo-Hyung Kim (Chonnam National University), Hyung-Jeong Yang (Chonnam National University) [paper] [slides] [poster]
2:40PM - Invited talk: Sonia Phene, "Google Health Research: Medical Imaging Insights"
3:15PM - Coffee break and poster session, includes both extended abstracts (listed below) and full papers
"Predicting the What and How - A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling", Judith Butepage (KTH Royal Institute of Technology), Hedvig Kjellström (KTH Royal Institute of Technology), Danica Kragic (KTH Royal Institute of Technology) [paper] [poster]
"Anticipation of Human Actions with Pose-based Fine-grained Representations", Sebastian Agethen (National Taiwan University), Hu-Cheng Lee (National Taiwan University), Winston H. Hsu (National Taiwan University) [paper] [poster]
"Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Junwei Liang (Carnegie Mellon University), Lu Jiang (Google), Juan Carlos Niebles (Stanford University), Alexander Hauptmann (Carnegie Mellon University), Li Fei-Fei (Stanford University) [paper] [poster]
4:00PM - Invited talk: John R. Smith, "Multi-modal Perceptual Understanding at IBM Research"
4:40PM - Lightning talks (full papers)
"Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs", Javad Amirian (Inria, Rennes, France), Jean-Bernard Hayet (CIMAT), Julien Pettré (INRIA Rennes - Bretagne Atlantique) [paper] [slides] [poster]
4:55PM - Invited talk: Vivek Kumar Singh, "AI in medical imaging"
5:35PM - Lightning talks (full papers)
"Robust Aleatoric Modeling for Future Vehicle Localization", Max Hudnell (UNC Chapel Hill), True Price (UNC Chapel Hill), Jan-Michael Frahm (UNC-Chapel Hill) [best student paper] [paper] [slides] [poster]
"SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data", Baohua Sun (Gyrfalcon Technology Inc.), Lin Yang (Gyrfalcon Technology Inc.), Wenhan Zhang (Gyrfalcon Technology Inc.), Michael Lin (Gyrfalcon Technology Inc.), Patrick Z Dong (Gyrfalcon Technology Inc.), Charles J Young (Gyrfalcon Technology Inc.), Jason Z Dong (Gyrfalcon Technology Inc.) [paper] [slides] [poster]
5:50PM - Workshop wrap-up
6:00PM - End of workshop
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 a total of eight pages, including all content and references, must be in PDF format, and formatted according to the CVPR style (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/PRECOGNITION2019
Best paper awards
Uber ATG has generously agreed to reward an author of a best paper and a best student paper with valuable Uber ATG swag merchandise.
Program Committee members
Ankit Laddha, Uber ATG
Arun Ross, MSU
Carlos Vallespi-Gonzalez, Uber ATG
Chi Nhan Duong, PDActive, Inc.
David Ross, Google
De-An Huang, Stanford
Fang-Chieh Chou, Uber ATG
Henggang Cui, Uber ATG
Kha Gia Quach, PDActive, Inc.
Namhoon Lee, Oxford
Nick Rhinehart, CMU
Radu Timofte, ETH Zurich
Thi Hoang Ngan Le, CMU
Vladan Radosavljevic, OLX
Wei-Chiu Ma, MIT