no code implementations • 17 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.
1 code implementation • 14 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.
no code implementations • 27 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.
no code implementations • 27 Sep 2018 • Shagan Sah, Dheeraj Peri, Ameya Shringi, Chi Zhang, Miguel Dominguez, Andreas Savakis, Ray Ptucha
Along with MMVR, we propose two improvements to the text conditioned image generation.
1 code implementation • 26 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.
no code implementations • 26 Sep 2018 • Chi Zhang, Shagan Sah, Thang Nguyen, Dheeraj Peri, Alexander Loui, Carl Salvaggio, Raymond Ptucha
This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing.
1 code implementation • IEEE Winter Conference on Applications of Computer Vision (WACV) 2018 • Miguel Dominguez, Rohan Dhamdhere, Atir Petkar, Saloni Jain, Shagan Sah, Raymond Ptucha
We adopt these graph based methods to 3D point clouds to introduce a generic vector representation of 3D graphs, we call graph 3D (G3D).
Ranked #2 on 3D Object Classification on ModelNet40 (using extra training data)
1 code implementation • 2 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.