Search Results for author: Raymond Ptucha

Found 14 papers, 5 papers with code

Fully Convolutional ASR for Less-Resourced Endangered Languages

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.

Acoustic Modelling Automatic Speech Recognition +2

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

Sensing and Learning Human Annotators Engaged in Narrative Sensemaking

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.

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

Neural Networks with Manifold Learning for Diabetic Retinopathy Detection

no code implementations12 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.

Diabetic Retinopathy Detection General Classification

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