Timezone: »
The global trends of urbanization and increased personal mobility force us to rethink the way we live and use urban space. The Traffic4cast competition series tackle this problem in a data driven way, advancing the latest methods in modern machine learning for modelling complex spatial systems over time. This year, our dynamic road graph data combine information from road maps, 10^12 location probe data points, and car loop counters in three entire cities for two years. While loop counters are the most accurate way to capture the traffic volume they are only available in some locations. Traffic4cast 2022 explores models that have the ability to generalize loosely related temporal vertex data on just a few nodes to predict dynamic future traffic states on the edges of the entire road graph. Specifically, in our core challenge we invite participants to predict for three cities the congestion classes known from the red, yellow, or green colouring of roads on a common traffic map for the entire road graph 15min into the future. We provide car count data from spatially sparse loop counters in these three cities in 15min aggregated time bins for one hour prior to the prediction time slot. For our extended challenge participants are asked to predict the actual average speeds on each road segment in the graph 15min into the future.
|
Tue 3:00 a.m. - 3:10 a.m.
|
Competition Intro
(Opening Remarks)
|
Sepp Hochreiter · Moritz Neun · Christian Eichenberger 🔗 |
|
Tue 3:10 a.m. - 3:20 a.m.
|
Data and Tasks
(Presentation)
|
Moritz Neun · Christian Eichenberger 🔗 |
|
Tue 3:20 a.m. - 3:30 a.m.
|
Leaderboard and Awards
(Presentation)
|
Michael Kopp · David Kreil · Christian Eichenberger · Moritz Neun 🔗 |
|
Tue 3:30 a.m. - 4:30 a.m.
|
Solutions Part 1
(Presentations by Participants)
|
🔗 |
|
Tue 4:30 a.m. - 4:50 a.m.
|
Break
|
🔗 |
|
Tue 4:50 a.m. - 6:10 a.m.
|
Solutions Part 2
(Presentations by Participants)
|
🔗 |
|
Tue 6:10 a.m. - 6:30 a.m.
|
Outlook and Discussion
(Q&A and Discussion)
|
🔗 |
|
-
|
Fifteen-minute Competition Overview Video
(Overview)
SlidesLive Video » |
Moritz Neun · Sepp Hochreiter · Michael Kopp · David Kreil · Christian Eichenberger 🔗 |
|
-
|
Competition Workshop Full Session Recording
(Video)
link »
Passcode: NR6D!iiz |
🔗 |
Author Information
Moritz Neun (IARAI)
Christian Eichenberger (IARAI)
Michael Kopp (Institute of Advanced Research in Artificial Intelligence (IARAI) GmbH)
David Kreil (Institute of Advanced Research in Artificial Intelligence (IARAI) GmbH)
Sepp Hochreiter (Institute of Advanced Research in Artificial Intelligence (IARAI) GmbH)
More from the Same Authors
-
2022 : Boosting Multi-modal Contrastive Learning with Modern Hopfield Networks and InfoLOOB »
Andreas Fürst · Elisabeth Rumetshofer · Johannes Lehner · Viet T. Tran · Fei Tang · Hubert Ramsauer · David Kreil · Michael Kopp · Günter Klambauer · Angela Bitto · Sepp Hochreiter -
2022 : Fifteen-minute Competition Overview Video »
Moritz Neun · Sepp Hochreiter · Michael Kopp · David Kreil · Christian Eichenberger -
2022 : Informative rewards and generalization in curriculum learning »
Rahul Siripurapu · Vihang Patil · Kajetan Schweighofer · Marius-Constantin Dinu · Markus Holzleitner · Hamid Eghbalzadeh · Luis Ferro · Thomas Schmied · Michael Kopp · Sepp Hochreiter -
2022 Competition: Weather4cast - Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts »
Aleksandra Gruca · Pedro Herruzo · Pilar Rípodas · Xavier Calbet · Llorenç Lliso Valverde · Federico Serva · Bertrand Le Saux · Michael Kopp · David Kreil · Sepp Hochreiter -
2022 : Fifteen-minute Competition Overview Video »
Pilar Rípodas · Federico Serva · Aleksandra Gruca · Xavier Calbet · Sepp Hochreiter · Pedro Herruzo · Michael Kopp · Llorenç Lliso Valverde · David Kreil · Bertrand Le Saux -
2022 : Leaderboard and Awards »
Michael Kopp · David Kreil · Christian Eichenberger · Moritz Neun -
2022 : Data and Tasks »
Moritz Neun · Christian Eichenberger -
2022 : Competition Intro »
Sepp Hochreiter · Moritz Neun · Christian Eichenberger -
2022 Poster: CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP »
Andreas Fürst · Elisabeth Rumetshofer · Johannes Lehner · Viet T. Tran · Fei Tang · Hubert Ramsauer · David Kreil · Michael Kopp · Günter Klambauer · Angela Bitto · Sepp Hochreiter -
2021 : Traffic4cast 2021 – Temporal and Spatial Few-Shot Transfer Learning in Traffic Map Movie Forecasting + Q&A »
Moritz Neun · Christian Eichenberger · Henry Martin · Pedro Herruzo · David Jonietz · Fei Tang · Daniel Springer · Markus Spanring · Avi Avidan · Luis Ferro · Ali Soleymani · Rohit Gupta · Bo Xu · Kevin Malm · Aleksandra Gruca · Johannes Brandstetter · Michael Kopp · David Kreil · Sepp Hochreiter