255 citations · 255 across the 1 of their papers we have counts for
3 papers
Attention-Based Multimodal Fusion for Video Description
Chiori Hori, Takaaki Hori, Teng-Yok Lee +3
Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of…
Full-Capacity Unitary Recurrent Neural Networks
Scott Wisdom, Thomas Powers, John R. Hershey +2
Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural…
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
John R. Hershey, Jonathan Le Roux, Felix Weninger
Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built int…