Search Results for author: Shagan Sah

Found 8 papers, 4 papers with code

Adaptive Hierarchical Decomposition of Large Deep Networks

no code implementations17 Jul 2020 Sumanth Chennupati, Sai Nooka, Shagan Sah, Raymond W Ptucha

As datasets get larger, a natural question to ask is if existing deep learning architectures can be extended to handle the 50+K classes thought to be perceptible by a typical human.

Object Recognition

Show, Translate and Tell

1 code implementation14 Mar 2019 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.

Cross-Modal Retrieval Image Captioning +2

Vector Learning for Cross Domain Representations

no code implementations27 Sep 2018 Shagan Sah, Chi Zhang, Thang Nguyen, Dheeraj Kumar Peri, Ameya Shringi, Raymond Ptucha

We leverage a sequence-to-sequence model to generate synthetic captions that have the same meaning for having a robust image generation.

Image Captioning Image Generation +2

Batch-normalized Recurrent Highway Networks

1 code implementation26 Sep 2018 Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks.

Image Captioning

Robust Spatial Filtering with Graph Convolutional Neural Networks

1 code implementation2 Mar 2017 Felipe Petroski Such, Shagan Sah, Miguel Dominguez, Suhas Pillai, Chao Zhang, Andrew Michael, Nathan Cahill, Raymond Ptucha

Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.