activity
20182020
collaborators

7 papers

cs.LG2020

Adaptive Hierarchical Decomposition of Large Deep Networks

Sumanth Chennupati, Sai Nooka, Shagan Sah +1

Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep le…

cs.CV2019

Fully Convolutional Networks for Handwriting Recognition

Felipe Petroski Such, Dheeraj Peri, Frank Brockler +2

Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwrit…

cs.CV2019

Show, Translate and Tell

Dheeraj Peri, Shagan Sah, Raymond Ptucha

Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has en…

cs.LG2018

Vector Learning for Cross Domain Representations

Shagan Sah, Chi Zhang, Thang Nguyen +3

Recently, generative adversarial networks have gained a lot of popularity for image generation tasks. However, such models are associated with complex learning mechanisms and deman…

cs.LG2018

Semantically Invariant Text-to-Image Generation

Shagan Sah, Dheeraj Peri, Ameya Shringi +4

Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant…

cs.LG2018

Batch-normalized Recurrent Highway Networks

Chi Zhang, Thang Nguyen, Shagan Sah +3

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the pro…