622 citations · 1.4k across the 32 of their papers we have counts for
6 papers · 1 filter
American Sign Language fingerspelling recognition in the wild
Bowen Shi, Aurora Martinez Del Rio, Jonathan Keane +4
We address the problem of American Sign Language fingerspelling recognition in the wild, using videos collected from websites. We introduce the largest data set available so far fo…
Regularizing Deep Networks by Modeling and Predicting Label Structure
Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich
We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit int…
Confidence from Invariance to Image Transformations
Yuval Bahat, Gregory Shakhnarovich
We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier. Our method is agnostic to the form of the classifier, requiring acc…
Task-Driven Super Resolution: Object Detection in Low-resolution Images
Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images. Intuitively, SR gives a positive impact on the object detection tas…
Deep Back-Projection Networks For Super-Resolution
Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-res…
Discriminability objective for training descriptive captions
Ruotian Luo, Brian Price, Scott Cohen +1
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We…