no code implementations • 10 Jun 2022 • Fanqing Lin, Tony Martinez
The proposed composition-based data generation technique can create two-hand instances with quality, quantity and diversity that generalize well to unseen domains.
no code implementations • CVPR 2022 • Fanqing Lin, Brian Price, Tony Martinez
Recently, feature backpropagating refinement scheme (f-BRS) has been proposed for the task of interactive segmentation, which enables efficient optimization of a small set of auxiliary variables inserted into the pretrained network to produce object segmentation that better aligns with user inputs.
no code implementations • 24 May 2021 • Taylor Archibald, Mason Poggemann, Aaron Chan, Tony Martinez
We demonstrate that temporal stroke information recovered by TRACE from offline data can be used for handwriting synthesis and establish the first benchmarks for a stroke trajectory recovery system trained on the IAM online handwriting dataset.
1 code implementation • 14 Nov 2020 • Fanqing Lin, Tony Martinez
Hand segmentation and detection in truly unconstrained RGB-based settings is important for many applications.
no code implementations • 1 Jun 2020 • Fanqing Lin, Connor Wilhelm, Tony Martinez
We tackle the challenging task of estimating global 3D joint locations for both hands via only monocular RGB input images.
Ranked #1 on 3D Canonical Hand Pose Estimation on STB
no code implementations • 4 Aug 2018 • Chris Tensmeyer, Curtis Wigington, Brian Davis, Seth Stewart, Tony Martinez, William Barrett
Training state-of-the-art offline handwriting recognition (HWR) models requires large labeled datasets, but unfortunately such datasets are not available in all languages and domains due to the high cost of manual labeling. We address this problem by showing how high resource languages can be leveraged to help train models for low resource languages. We propose a transfer learning methodology where we adapt HWR models trained on a source language to a target language that uses the same writing script. This methodology only requires labeled data in the source language, unlabeled data in the target language, and a language model of the target language.
no code implementations • 11 Aug 2017 • Chris Tensmeyer, Daniel Saunders, Tony Martinez
This same method also achieves the highest reported accuracy of 86. 6% in predicting paleographic scribal script classes at the page level on medieval Latin manuscripts.
no code implementations • 10 Aug 2017 • Chris Tensmeyer, Tony Martinez
Binarization of degraded historical manuscript images is an important pre-processing step for many document processing tasks.
no code implementations • 10 Aug 2017 • Chris Tensmeyer, Tony Martinez
Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks.
Ranked #28 on Document Image Classification on RVL-CDIP
no code implementations • 17 Oct 2014 • Richard G. Morris, Tony Martinez, Michael R. Smith
Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other.
no code implementations • 7 Jul 2014 • Michael R. Smith, Logan Mitchell, Christophe Giraud-Carrier, Tony Martinez
The success of machine learning on a given task dependson, among other things, which learning algorithm is selected and its associated hyperparameters.
no code implementations • 9 Jun 2014 • Michael R. Smith, Tony Martinez
We examine RIDL on a set of 54 data sets and 5 learning algorithms and compare RIDL with other weighting and filtering approaches.
no code implementations • 9 Jun 2014 • Michael R. Smith, Tony Martinez, Michael Gashler
Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques.
no code implementations • 28 May 2014 • Michael R. Smith, Andrew White, Christophe Giraud-Carrier, Tony Martinez
The results from most machine learning experiments are used for a specific purpose and then discarded.
no code implementations • 13 Mar 2014 • Michael R. Smith, Tony Martinez, Christophe Giraud-Carrier
We find that, while both significantly improve the induced model, improving the quality of the training set has a greater potential effect than hyper-parameter optimization.
no code implementations • 7 Mar 2014 • Michael R. Smith, Tony Martinez
We compare NICD with several other noise handling techniques that do not consider classifier diversity on a set of 54 data sets and 5 learning algorithms.
no code implementations • 19 Dec 2013 • Michael S. Gashler, Michael R. Smith, Richard Morris, Tony Martinez
We evaluate UBP with the task of imputing missing values in datasets, and show that UBP is able to predict missing values with significantly lower sum-squared error than other collaborative filtering and imputation techniques.
no code implementations • 17 Dec 2013 • Michael R. Smith, Tony Martinez
Some instances (such as outliers) are detrimental to inferring a model of the data.
no code implementations • 13 Dec 2013 • Michael R. Smith, Tony Martinez
Additionally, we find that a majority voting ensemble is robust to noise as filtering with a voting ensemble does not increase the classification accuracy of the voting ensemble.
2 code implementations • 18 Jul 1998 • Dan Ventura, Tony Martinez
The unique characteristics of quantum theory may also be used to create a quantum associative memory with a capacity exponential in the number of neurons.
Quantum Physics