185 citations · 208 across the 10 of their papers we have counts for
5 papers · 1 filter
Learning to Compose Domain-Specific Transformations for Data Augmentation
Alexander J. Ratner, Henry R. Ehrenberg, Zeshan Hussain +2
Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it i…
Bidirectional American Sign Language to English Translation
Hardie Cate, Zeshan Hussain
We outline a bidirectional translation system that converts sentences from American Sign Language (ASL) to English, and vice versa. To perform machine translation between ASL and E…
Group Visual Sentiment Analysis
Zeshan Hussain, Tariq Patanam, Hardie Cate
In this paper, we introduce a framework for classifying images according to high-level sentiment. We subdivide the task into three primary problems: emotion classification on faces…
DeepFace: Face Generation using Deep Learning
Hardie Cate, Fahim Dalvi, Zeshan Hussain
We use CNNs to build a system that both classifies images of faces based on a variety of different facial attributes and generates new faces given a set of desired facial character…
Sign Language Recognition Using Temporal Classification
Hardie Cate, Fahim Dalvi, Zeshan Hussain
Devices like the Myo armband available in the market today enable us to collect data about the position of a user's hands and fingers over time. We can use these technologies for s…