The proposed composition-based data generation technique can create two-hand instances with quality, quantity and diversity that generalize well to unseen domains.
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.
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.
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
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.
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.
Binarization of degraded historical manuscript images is an important pre-processing step for many document processing tasks.
Convolutional Neural Networks (CNNs) are state-of-the-art models for document image classification tasks.
Ranked #21 on Document Image Classification on RVL-CDIP
Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other.
The success of machine learning on a given task dependson, among other things, which learning algorithm is selected and its associated hyperparameters.
Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques.
The results from most machine learning experiments are used for a specific purpose and then discarded.
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.
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.
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.
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.