no code implementations • 18 Apr 2024 • Pushkar Shukla, Dhruv Srikanth, Lee Cohen, Matthew Turk
To address this issue, we propose using adversarial images, that is images that deceive a deep neural network but not humans, as counterfactuals for fair model training.
no code implementations • 3 Dec 2023 • Aditya Chinchure, Pushkar Shukla, Gaurav Bhatt, Kiri Salij, Kartik Hosanagar, Leonid Sigal, Matthew Turk
Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery.
no code implementations • 23 Nov 2021 • Yi Ding, Alex Rich, Mason Wang, Noah Stier, Matthew Turk, Pradeep Sen, Tobias Höllerer
Multimodal classification is a core task in human-centric machine learning.
no code implementations • 14 Sep 2021 • Jedrzej Kozerawski, Matthew Turk
Real-world classification tasks are frequently required to work in an open-set setting.
1 code implementation • ACCV 2020 • Jedrzej Kozerawski, Victor Fragoso, Nikolaos Karianakis, Gaurav Mittal, Matthew Turk, Mei Chen
Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes.
Ranked #53 on Long-tail Learning on ImageNet-LT
no code implementations • 28 Jul 2019 • Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang
In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective.
no code implementations • ACL 2019 • Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang
In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective.
no code implementations • CVPR 2018 • Jedrzej Kozerawski, Matthew Turk
This work addresses the novel problem of one-shot one-class classification.
no code implementations • 27 Sep 2017 • Victor Fragoso, Chris Sweeney, Pradeep Sen, Matthew Turk
While RANSAC-based methods are robust to incorrect image correspondences (outliers), their hypothesis generators are not robust to correct image correspondences (inliers) with positional error (noise).
no code implementations • 13 Feb 2017 • Michael S. Warren, Samuel W. Skillman, Rick Chartrand, Tim Kelton, Ryan Keisler, David Raleigh, Matthew Turk
We present our experiences using cloud computing to support data-intensive analytics on satellite imagery for commercial applications.
no code implementations • 2 Aug 2016 • Victor Fragoso, Walter Scheirer, Joao Hespanha, Matthew Turk
This work introduces the one-class slab SVM (OCSSVM), a one-class classifier that aims at improving the performance of the one-class SVM.
no code implementations • 13 Jul 2016 • Chris Sweeney, Victor Fragoso, Tobias Hollerer, Matthew Turk
We introduce the distributed camera model, a novel model for Structure-from-Motion (SfM).
no code implementations • ICCV 2015 • Chris Sweeney, Torsten Sattler, Tobias Hollerer, Matthew Turk, Marc Pollefeys
The viewing graph represents a set of views that are related by pairwise relative geometries.
no code implementations • CVPR 2015 • Chris Sweeney, Laurent Kneip, Tobias Hollerer, Matthew Turk
We propose a novel solution for computing the relative pose between two generalized cameras that includes reconciling the internal scale of the generalized cameras.
no code implementations • CVPR 2013 • Victor Fragoso, Matthew Turk
We present SWIGS, a Swift and efficient Guided Sampling method for robust model estimation from image feature correspondences.