Search Results for author:
Found 47 papers, 22 papers with code
REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
Specifically, REMEMBER outputs diagnostic predictions alongside an interpretable report, including reference images and explanations aligned with clinical workflows.
Triply Laplacian Scale Mixture Modeling for Seismic Data Noise Suppression
Sparsity-based tensor recovery methods have shown great potential in suppressing seismic data noise.
VisTA: Vision-Text Alignment Model with Contrastive Learning using Multimodal Data for Evidence-Driven, Reliable, and Explainable Alzheimer's Disease Diagnosis
Here, we propose VisTA, a multimodal language-vision model assisted by contrastive learning, to optimize disease prediction and evidence-based, interpretable explanations for clinical decision-making.
DPERC: Direct Parameter Estimation for Mixed Data
In this paper, we propose Direct Parameter Estimation for Randomly Missing Data with Categorical Features (DPERC), an efficient approach for direct parameter estimation tailored to mixed data that contains missing values within continuous features.
HORUS: Multimodal Large Language Models Framework for Video Retrieval at VBS 2025
In the dynamic field of video retrieval, precise and effective search methods are crucial for managing complex datasets.
Missing data imputation for noisy time-series data and applications in healthcare
Healthcare time series data is vital for monitoring patient activity but often contains noise and missing values due to various reasons such as sensor errors or data interruptions.
Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator
Federated Class-Incremental Learning (FCIL) increasingly becomes important in the decentralized setting, where it enables multiple participants to collaboratively train a global model to perform well on a sequence of tasks without sharing their private data.
Accelerating Transformers with Spectrum-Preserving Token Merging
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e. g., GPT, LLaVa), is an important problem in machine learning.
CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width.
Semidefinite Relaxations of the Gromov-Wasserstein Distance
The relaxation can be viewed as the Lagrangian dual of the GW distance augmented with constraints that relate to the linear and quadratic terms of transportation plans.
On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging.
A Generalization Bound of Deep Neural Networks for Dependent Data
Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid).
LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images.
Correlation visualization under missing values: a comparison between imputation and direct parameter estimation methods
Correlation matrix visualization is essential for understanding the relationships between variables in a dataset, but missing data can pose a significant challenge in estimating correlation coefficients.
Blockwise Principal Component Analysis for monotone missing data imputation and dimensionality reduction
To address this issue, we propose a Blockwise principal component analysis Imputation (BPI) framework for dimensionality reduction and imputation of monotone missing data.
Adaptive-saturated RNN: Remember more with less instability
Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs).
Ranked #15 on
Sequential Image Classification
on Sequential MNIST
Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification
Transfer learning plays an essential role in Deep Learning, which can remarkably improve the performance of the target domain, whose training data is not sufficient.
Conditional expectation with regularization for missing data imputation
Missing data frequently occurs in datasets across various domains, such as medicine, sports, and finance.
HADA: A Graph-based Amalgamation Framework in Image-text Retrieval
It is not easy to propose a new model with a novel architecture and intensively train it on a massive dataset with many GPUs to surpass many SOTA models, which are already available to use on the Internet.
Ranked #1 on
Image Retrieval
on MSCOCO
DRG-Net: Interactive Joint Learning of Multi-lesion Segmentation and Classification for Diabetic Retinopathy Grading
Diabetic Retinopathy (DR) is a leading cause of vision loss in the world, and early DR detection is necessary to prevent vision loss and support an appropriate treatment.
Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering
Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the lack of labeled training samples by learning feature representations from unlabeled data.
When can we reconstruct the ancestral state? Beyond Brownian motion
Reconstructing the ancestral state of a group of species helps answer many important questions in evolutionary biology.
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice.
A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension
Identifying the relevant variables for a classification model with correct confidence levels is a central but difficult task in high-dimension.
Unequal Covariance Awareness for Fisher Discriminant Analysis and Its Variants in Classification
Fisher Discriminant Analysis (FDA) is one of the essential tools for feature extraction and classification.
Fall detection using multimodal data
In recent years, the occurrence of falls has increased and has had detrimental effects on older adults.
TaDeR: A New Task Dependency Recommendation for Project Management Platform
This paper proposes an efficient task dependency recommendation algorithm to suggest tasks dependent on a given task that the user has just created.
FPSRS: A Fusion Approach for Paper Submission Recommendation System
Recommender systems have been increasingly popular in entertainment and consumption and are evident in academics, especially for applications that suggest submitting scientific articles to scientists.
SimCPSR: Simple Contrastive Learning for Paper Submission Recommendation System
This study suggests a more advanced method for enhancing the efficiency of the paper submission recommendation system compared to previous approaches when we respectively achieve 0. 5173, 0. 8097, 0. 8862, 0. 9496 for Top 1, 3, 5, and 10 accuracies on the test set for combining the title, abstract, and keywords as input features.
An Improved Subject-Independent Stress Detection Model Applied to Consumer-grade Wearable Devices
Using our proposed model architecture, we compare the accuracy between stress detection models that use measures from each individual signal source, and one model employing the fusion of multiple sensor sources.
Posterior concentration and fast convergence rates for generalized Bayesian learning
We prove that under the multi-scale Bernstein's condition, the generalized posterior distribution concentrates around the set of optimal hypotheses and the generalized Bayes estimator can achieve fast learning rate.
An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator
In this paper, we perform an empirical study on the impact of several loss functions on the performance of standard GAN models, Deep Convolutional Generative Adversarial Networks (DCGANs).
Leaf Recognition Using Convolutional Neural Networks Based Features
In recent years, there is a considerable increase in the number of studies related to plant taxonomy.
An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models
Accurate insect pest recognition is significant to protect the crop or take the early treatment on the infected yield, and it helps reduce the loss for the agriculture economy.
An Efficient Transformer-Based Model for Vietnamese Punctuation Prediction
In both formal and informal texts, missing punctuation marks make the texts confusing and challenging to read.
SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs
In this paper, we propose SPBERT, a transformer-based language model pre-trained on massive SPARQL query logs.
DPER: Efficient Parameter Estimation for Randomly Missing Data
The missing data problem has been broadly studied in the last few decades and has various applications in different areas such as statistics or bioinformatics.
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
In this paper, we introduce the Local and Global Scene Graph Matching (LGSGM) model that enhances the state-of-the-art method by integrating an extra graph convolution network to capture the general information of a graph.
Ranked #4 on
Image Retrieval
on Flickr30K 1K test
OASIS: An Active Framework for Set Inversion
In this work, we introduce a novel method for solving the set inversion problem by formulating it as a binary classification problem.
TATL: Task Agnostic Transfer Learning for Skin Attributes Detection
Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task.
VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations
Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs.
EPEM: Efficient Parameter Estimation for Multiple Class Monotone Missing Data
The problem of monotone missing data has been broadly studied during the last two decades and has many applications in different fields such as bioinformatics or statistics.
An Attention Mechanism with Multiple Knowledge Sources for COVID-19 Detection from CT Images
Until now, Coronavirus SARS-CoV-2 has caused more than 850, 000 deaths and infected more than 27 million individuals in over 120 countries.
ASMCNN: An Efficient Brain Extraction Using Active Shape Model and Convolutional Neural Networks
Brain extraction (skull stripping) is a challenging problem in neuroimaging.
Fast learning rates with heavy-tailed losses
We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails.
Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers
We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution.
