FASTER Recurrent Networks for Efficient Video Classification

Tensor-Train Recurrent Neural Networks for Video Classification

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very high-dimensional inputs due to the large input-to-hidden weight matrix. This may have prevented RNNs’ large-scale application in tasks that involve very hig...

Efficient Short-Term Electricity Load Forecasting Using Recurrent Neural Networks

Short term load forecasting (STLF) plays an important role in the economic and reliable operation ofpower systems. Electric load demand has a complex profile with many multivariable and nonlineardependencies. In this study, recurrent neural network (RNN) architecture is presented for STLF. Theproposed model is capable of forecasting next 24-hour load profile. The main feature in this networkis ...

Efficient Pixel Decimation Pattern For Faster Video Encoders

Today’s trend in multimedia is towards providing real time voice and video services over a diverse range of channels without compromising their quality. As the network switching capability has dramatically increased over the last decade, the concentration is now on the improvement of encoders. So much so that many video coding standard such as MPEG and so forth, attracted much attention for fur...

Efficient and Effective Solutions for Video Classification

Video captioning with recurrent networks based on frame- and video-level features and visual content classification

In this paper, we describe the system for generating textual descriptions of short video clips using recurrent neural networks, which we used while participating in the Large Scale Movie Description Challenge 2015 in ICCV 2015. Our work builds on static image captioning system proposed in [22] and implemented in [8] and extends this framework to videos utilizing both static image features and v...