no code implementations • LREC 2020 • Bao Thai, Robert Jimerson, Raymond Ptucha, Emily Prud{'}hommeaux
The application of deep learning to automatic speech recognition (ASR) has yielded dramatic accuracy increases for languages with abundant training data, but languages with limited training resources have yet to see accuracy improvements on this scale.
1 code implementation • IEEE Western New York Image and Signal Processing Workshop (WNYISPW) 2019 • Miguel Dominguez, Rohan Dhamdhere, Naga Durga Harish Kanamarlapudi, Sunand Raghupathi, Raymond Ptucha
Our evolution mutates a population of neural networks to search the architecture and hyperparameter space.
Ranked #1 on Graph Classification on MUTAG
no code implementations • 10 Jul 2019 • Felipe Petroski Such, Dheeraj Peri, Frank Brockler, Paul Hutkowski, Raymond Ptucha
Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message.
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 • 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 • 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 • NAACL 2018 • McKenna Tornblad, Luke Lapresi, Christopher Homan, Raymond Ptucha, Cecilia Ovesdotter Alm
While labor issues and quality assurance in crowdwork are increasingly studied, how annotators make sense of texts and how they are personally impacted by doing so are not.
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)
no code implementations • WS 2017 • Alex Calderwood, er, Elizabeth A. Pruett, Raymond Ptucha, Christopher Homan, Cecilia Ovesdotter Alm
Interpersonal violence (IPV) is a prominent sociological problem that affects people of all demographic backgrounds.
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.
no code implementations • 12 Dec 2016 • Arjun Raj Rajanna, Kamelia Aryafar, Rajeev Ramchandran, Christye Sisson, Ali Shokoufandeh, Raymond Ptucha
Our experimental results show that neural networks in combination with preprocessing on the images can boost the classification accuracy on this dataset.