NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:4701
Title:Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network


		
The paper shows that accurate wind speed measurements in real time can be done using a suitable deep net based on visual observations such as flapping of flags or swaying of trees. The deep net considered is a coupled CNN and RNN. The results illustrate the approach to be accurate and discussions are provided for the challenges in the high and the low wind speeds, respectively called the frame rate limited zone and the duration limited zone. The reviewers agreed that the paper presents an interesting dataset and proposes a creative approach using existing machine learning models. The reviewers felt that due to the novelty of the application domain, novel machine learning approaches are not a requirement. However, opinion was divided on the overall merit of the work. Some reviewers felt that the paper makes progress on a problem which can have impact in real world whereas others felt that the paper does not solve a real world problem with a novel approach and has not illustrated the method to work well on test sets and in related settings. The work was extensively discussed after the author response but the difference in opinion could not be resolved. Adding a clear motivation for real world applications and discussions of the state-of-the-art will strengthen the paper.