26 citations · 59 across the 12 of their papers we have counts for
13 papers
SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering
Davit Soselia, Joseph JaJa, Amitabh Varshney
3D Gaussian language fields provide an explicit, spatially grounded representation for 3D visual question answering (VQA), but their dense semantic features can require tens of tho…
ProtoVAE: Prototypical Networks for Unsupervised Disentanglement
Vaishnavi Patil, Matthew Evanusa, Joseph JaJa
Generative modeling and self-supervised learning have in recent years made great strides towards learning from data in a completely unsupervised way. There is still however an open…
DOT-VAE: Disentangling One Factor at a Time
Vaishnavi Patil, Matthew Evanusa, Joseph JaJa
As we enter the era of machine learning characterized by an overabundance of data, discovery, organization, and interpretation of the data in an unsupervised manner becomes a criti…
TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
Jun Wang, Mingfei Gao, Yuqian Hu +5
Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers fro…
FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing
Amit Kumar Kundu, Joseph Jaja
Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under…
Class-Similarity Based Label Smoothing for Confidence Calibration
Chihuang Liu, Joseph JaJa
Generating confidence calibrated outputs is of utmost importance for the applications of deep neural networks in safety-critical decision-making systems. The output of a neural net…
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
Chihuang Liu, Joseph JaJa
Adversarial training has been successfully applied to build robust models at a certain cost. While the robustness of a model increases, the standard classification accuracy decline…
Learning Graph-Level Representations with Recurrent Neural Networks
Yu Jin, Joseph F. JaJa
Recently a variety of methods have been developed to encode graphs into low-dimensional vectors that can be easily exploited by machine learning algorithms. The majority of these m…
A High Performance Implementation of Spectral Clustering on CPU-GPU Platforms
Yu Jin, Joseph F. JaJa
Spectral clustering is one of the most popular graph clustering algorithms, which achieves the best performance for many scientific and engineering applications. However, existing…
A Data-Driven Approach to Extract Connectivity Structures from Diffusion Tensor Imaging Data
Yu Jin, Joseph F. JaJa, Rong Chen +1
Diffusion Tensor Imaging (DTI) is an effective tool for the analysis of structural brain connectivity in normal development and in a broad range of brain disorders. However efforts…
Graph Coarsening with Preserved Spectral Properties
Yu Jin, Andreas Loukas, Joseph F. JaJa
Large-scale graphs are widely used to represent object relationships in many real world applications. The occurrence of large-scale graphs presents significant computational challe…
Scalable Algorithms for Generating and Analyzing Structural Brain Networks with a Varying Number of Nodes
Yu Jin, Joseph F. JaJa, Rong Chen +1
Diffusion Magnetic Resonance Imaging (MRI) exploits the anisotropic diffusion of water molecules in the brain to enable the estimation of the brain's anatomical fiber tracts at a r…
From Maxout to Channel-Out: Encoding Information on Sparse Pathways
Qi Wang, Joseph JaJa
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks. The framework is based o…