The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task – Insights from the IARAI Traffic4cast Competition at NeurIPS 2019

David P Kreil, Michael K Kopp, David Jonietz, Moritz Neun, Aleksandra Gruca, Pedro Herruzo, Henry Martin, Ali Soleymani, Sepp Hochreiter
Proceedings of the NeurIPS 2019 Competition and Demonstration Track, PMLR 123:232-241, 2020.

Abstract

Deep Neural Networks models are state-of-the-art solutions in accurately forecasting future video frames in a movie. A successful video prediction model needs to extract and encode semantic features that describe the complex spatio-temporal correlations within image sequences of the real world. The IARAI Traffic4cast Challenge of the NeurIPS Competition Track 2019 for the first time introduced the novel argument that this is also highly relevant for urban traffic. By framing traffic prediction as a movie completion task, the challenge requires models to take advantage of complex geo-spatial and temporal patterns of the underlying process. We here report on the success and insights obtained in a first Traffic Map Movie forecasting challenge. Although short-term traffic prediction is considered hard, this novel approach allowed several research groups to successfully predict future traffic states in a purely data-driven manner from pixel space. We here expand on the original rationale, summarize key findings, and discuss promising future directions of the t4c competition at NeurIPS.

Cite this Paper

BibTeX
@InProceedings{pmlr-v123-kreil20a, title = {The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task – Insights from the IARAI \t4c Competition at NeurIPS 2019}, author = {Kreil, David P and Kopp, Michael K and Jonietz, David and Neun, Moritz and Gruca, Aleksandra and Herruzo, Pedro and Martin, Henry and Soleymani, Ali and Hochreiter, Sepp}, booktitle = {Proceedings of the NeurIPS 2019 Competition and Demonstration Track}, pages = {232--241}, year = {2020}, editor = {Escalante, Hugo Jair and Hadsell, Raia}, volume = {123}, series = {Proceedings of Machine Learning Research}, month = {08--14 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v123/kreil20a/kreil20a.pdf}, url = {https://proceedings.mlr.press/v123/kreil20a.html}, abstract = {Deep Neural Networks models are state-of-the-art solutions in accurately forecasting future video frames in a movie. A successful video prediction model needs to extract and encode semantic features that describe the complex spatio-temporal correlations within image sequences of the real world. The IARAI Traffic4cast Challenge of the NeurIPS Competition Track 2019 for the first time introduced the novel argument that this is also highly relevant for urban traffic. By framing traffic prediction as a movie completion task, the challenge requires models to take advantage of complex geo-spatial and temporal patterns of the underlying process. We here report on the success and insights obtained in a first Traffic Map Movie forecasting challenge. Although short-term traffic prediction is considered hard, this novel approach allowed several research groups to successfully predict future traffic states in a purely data-driven manner from pixel space. We here expand on the original rationale, summarize key findings, and discuss promising future directions of the t4c competition at NeurIPS.} }
Endnote
%0 Conference Paper %T The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task – Insights from the IARAI Traffic4cast Competition at NeurIPS 2019 %A David P Kreil %A Michael K Kopp %A David Jonietz %A Moritz Neun %A Aleksandra Gruca %A Pedro Herruzo %A Henry Martin %A Ali Soleymani %A Sepp Hochreiter %B Proceedings of the NeurIPS 2019 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2020 %E Hugo Jair Escalante %E Raia Hadsell %F pmlr-v123-kreil20a %I PMLR %P 232--241 %U https://proceedings.mlr.press/v123/kreil20a.html %V 123 %X Deep Neural Networks models are state-of-the-art solutions in accurately forecasting future video frames in a movie. A successful video prediction model needs to extract and encode semantic features that describe the complex spatio-temporal correlations within image sequences of the real world. The IARAI Traffic4cast Challenge of the NeurIPS Competition Track 2019 for the first time introduced the novel argument that this is also highly relevant for urban traffic. By framing traffic prediction as a movie completion task, the challenge requires models to take advantage of complex geo-spatial and temporal patterns of the underlying process. We here report on the success and insights obtained in a first Traffic Map Movie forecasting challenge. Although short-term traffic prediction is considered hard, this novel approach allowed several research groups to successfully predict future traffic states in a purely data-driven manner from pixel space. We here expand on the original rationale, summarize key findings, and discuss promising future directions of the t4c competition at NeurIPS.
APA
Kreil, D.P., Kopp, M.K., Jonietz, D., Neun, M., Gruca, A., Herruzo, P., Martin, H., Soleymani, A. & Hochreiter, S.. (2020). The surprising efficiency of framing geo-spatial time series forecasting as a video prediction task – Insights from the IARAI Traffic4cast Competition at NeurIPS 2019. Proceedings of the NeurIPS 2019 Competition and Demonstration Track, in Proceedings of Machine Learning Research 123:232-241 Available from https://proceedings.mlr.press/v123/kreil20a.html.

Related Material