Search

Your search keyword '"Kopp, Michael K."' showing total 3 results
Start Over Author "Kopp, Michael K."
3 results on '"Kopp, Michael K."'

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

Author

Kreil, David P., Kopp, Michael K., Jonietz, David, Neun, Moritz, Gruca, Aleksandra, Herruzo Sánchez, Pedro, Martin, Henry, Soleymani, Ali, Hochreiter, Sepp, and Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors

Subjects
Traffic estimation--Mathematical models, Informàtica::Intel·ligència artificial::Aprenentatge automàtic [Àrees temàtiques de la UPC], Enginyeria civil::Infraestructures i modelització dels transports::Trànsit [Àrees temàtiques de la UPC], Circulació urbana -- Models matemàtics
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.

Published
2020

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

Author

Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors, Kreil, David P., Kopp, Michael K., Jonietz, David, Neun, Moritz, Gruca, Aleksandra, Herruzo Sánchez, Pedro, Martin, Henry, Soleymani, Ali, Hochreiter, Sepp, Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors, Kreil, David P., Kopp, Michael K., Jonietz, David, Neun, Moritz, Gruca, Aleksandra, Herruzo Sánchez, Pedro, Martin, Henry, Soleymani, Ali, and Hochreiter, Sepp

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., Postprint (published version)

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results