activity
20142023
most citedFast learning rates with heavy-tailed losses

9 citations · 17 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CV2024

I-MPN: Inductive Message Passing Network for Efficient Human-in-the-Loop Annotation of Mobile Eye Tracking Data

Hoang H. Le, Duy M. H. Nguyen, Omair Shahzad Bhatti +5

Comprehending how humans process visual information in dynamic settings is crucial for psychology and designing user-centered interactions. While mobile eye-tracking systems combin…

eess.IV20234 cited

On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation

Duy Minh Ho Nguyen, Tan Ngoc Pham, Nghiem Tuong Diep +9

Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging. The foundatio…

stat.ML20233 cited

A Generalization Bound of Deep Neural Networks for Dependent Data

Quan Huu Do, Binh T. Nguyen, Lam Si Tung Ho

Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid). This assumption may not hold in real-life applications suc…

cs.LG20231 cited

Adaptive-saturated RNN: Remember more with less instability

Khoi Minh Nguyen-Duy, Quang Pham, Binh T. Nguyen

Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs). With orthogonal parameters and non-saturated activ…

cs.CV2023

Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification

Cuong V. Nguyen, Khiem H. Le, Anh M. Tran +2

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. Our work explo…

cs.CV2023

HADA: A Graph-based Amalgamation Framework in Image-text Retrieval

Manh-Duy Nguyen, Binh T. Nguyen, Cathal Gurrin

Many models have been proposed for vision and language tasks, especially the image-text retrieval task. All state-of-the-art (SOTA) models in this challenge contained hundreds of m…