Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.

#5 best model for Traffic Prediction on PeMS-M

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis.

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels.

We introduce a method to learn a hierarchy of successively more abstract representations of complex data based on optimizing an information-theoretic objective.

It is well-known that neural networks are computationally hard to train.

Predicting depth is an essential component in understanding the 3D geometry of a scene.

Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.

#4 best model for Action Recognition In Videos on VIVA Hand Gestures Dataset

ACTION CLASSIFICATION ACTION RECOGNITION IN VIDEOS MULTI-TASK LEARNING OPTICAL FLOW ESTIMATION

We develop collaborative topic Poisson factorization (CTPF), a generative model of articles and reader preferences.

In this paper we explore how machine learning techniques can be applied to the discovery of efficient mathematical identities.

A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories.