Please find below a preliminary program for our events in Vancouver. Talk titles and times subject to change.

Everyone is welcome to attend the full-day IARAI Traffic4cast Symposion 15 Dec Sunday. Symposium Registration is now open until Saturday 14 Dec 17h, or earlier as soon as capacity is reached. Space is limited so please register now.

Every NeurIPS delegate is welcome to attend the Traffic4cast Competition Track session on 14 Dec Saturday 15h.

Traffic4cast Competition Track at NeurIPS 2019, 14 Dec, 3pm
  • Introduction – David Kreil, IARAI
  • Real-world Data Shaping the Algorithms of modern AI – Sepp Hochreiter, IARAI & JKU
  • Traffic Map Movies vs Real Movies – the Art of Predicting Moving Images – Leonid Sigal, University of British Columbia
  • Traffic4Cast – Aligning short-term traffic state forecasting and video frame prediction – David Jonietz, Here Technologies
  • Traffic map movie prediction using U-Net with Densenet – Sungbin Choi, Seoul Download abstract
  • Augmenting the Traffic4cast Challenge 2019 with Spatio-temporal Context – Henry Martin, ETH Zurich Download abstract
  • CrevNet: Conditionally Reversible Video Prediction – Wei Yu, University of Toronto Download abstract
  • Building an Effective Large-Scale Traffic State Prediction System – Zhichen Liu, Southeast University, China Download abstract
  • Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction – Tu Nguyen, Daimler Autonomous Services Download abstract
  • Recurrent Autoencoder with Skip Connections and Exogenous Variables for Traffic Forecasting – Pedro Herruzo Sánchez, Polytechnic University of Catalonia, Barcelona Download abstract
  • The Making Of — Compiling the large-scale real-world data for Traffic4cast – Moritz Neun, Here Technologies
  • Significance and Relevance of Leaderboard Ranks – Aleksandra Gruca, Silesian University of Technology
  • The Traffic4cast competition in numbers – Shia Shi, Here Technologies
  • Picking the right loss – choice of an appropriate metric – Michael Kopp, IARAI & Here Technologies
  • Awards ceremony – David Kreil, IARAI

75 mins total session time. Session chair Michael Kopp, IARAI & Here Technologies.

IARAI Traffic4cast Full-Day Symposion, 15 Dec, 9am – 5pm
  • 09:00 – Introduction – David Kreil, IARAI
  • 09:05 – Optimal Delayed Reward Redistribution – Sepp Hochreiter, IARAI & JKU
  • 09:45 – Early Activity Detection and Semantic Understanding in Videos – Leonid Sigal, University of British Columbia
  • 10:15 – The Making Of – Compiling the large-scale real-world data for Traffic4cast – Moritz Neun, Here Technologies
  • 10:45 – Coffee Break (catered)
  • 11:00 – Traffic map movie prediction using U-Net with Densenet – Sungbin Choi, Seoul Download abstract
  • 11:30 – Augmenting the Traffic4cast Challenge 2019 with Spatio-temporal Context – Henry Martin, ETH Zurich Download abstract
  • 12:00 – CrevNet: Conditionally Reversible Video Prediction – Wei Yu, University of Toronto Download abstract
  • 12:30 – Building an Effective Large-Scale Traffic State Prediction System – Qiming Zhang, University of Sydney Download abstract
  • 13:00 – Recurrent Autoencoder with Skip Connections and Exogenous Variables for Traffic Forecasting – Pedro Herruzo Sánchez, Polytechnic University of Catalonia, Barcelona Download abstract
  • 13:30 – Lunch Break (catered)
  • 14:30 – Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction – Tu Nguyen, Daimler Autonomous Services Download abstract
  • 15:00 – Traffic4Cast – Aligning short-term traffic state forecasting and video frame prediction – David Jonietz, Here Technologies
  • 15:30 – Coffee Break
  • 15:50 – Significance and Relevance of Leaderboard Ranks – Aleksandra Gruca, Silesian University of Technology
  • 16:20 – Picking the right loss – choice of an appropriate metric – Michael Kopp, IARAI & Here Technologies
  • 16:50 – Outlook to 2020 – David Kreil, IARAI
  • 17:00 – Closing

Session Chairs: David Kreil (IARAI), Moritz Neun (Here), Michael Kopp (IARAI & Here), Shia Shi (Here).

The meeting will be held in the Salt Spring Island Room on ‘Floor 1’ of the hotel, with expansive windows overlooking the historic Vancouver Art Gallery. Please note that this is not the first floor – just press “1” in the lift.

Please note that the whole meeting start and the exact schedule are still subject to changes!

Venue: Fairmount Vancouver hotel (5 mins walking from NeurIPS, down Burrard street):

©2020 IARAI - INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE

Imprint | Terms and conditions

Log in with your credentials

or    

Forgot your details?

Create Account