T
Research Areas
Links
Biography and Research Information
OverviewAI-generated summary
Thanh-Dat Truong's research focuses on the application of advanced machine learning techniques, particularly deep learning models, to address complex problems in computer vision and artificial intelligence. His work involves developing and refining algorithms for tasks such as action recognition, semantic scene segmentation, and face recognition. Truong has investigated domain adaptation strategies to improve model performance across different datasets and conditions, as seen in his publications on BiMaL and FREDOM. He has also explored the use of graph convolutional neural networks for movement analysis in medical contexts and foundation models for large-scale visual understanding tasks, exemplified by his work on insect imagery. His research network includes frequent collaborations with researchers at the University of Arkansas at Fayetteville, including Khoa Luu, Ashley P. G. Dowling, Xuan-Bac Nguyen, and Jackson Cothren. Truong's scholarly output is characterized by an h-index of 11 and over 60 publications.
Metrics
- h-index: 11
- Publications: 60
- Citations: 397
Selected Publications
-
DEGA: Dynamic Entropy Guided Adaptation (2025)
-
Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding (2025)
-
Cross-view action recognition understanding from exocentric to egocentric perspective (2024)
-
CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars (2024)
-
Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding (2024)
-
LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition (2023)
-
Self-Supervised Domain Adaptation in Crowd Counting (2022)
-
EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring (2022)
-
BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation (2021)
-
Movement Analysis for Neurological and Musculoskeletal Disorders Using Graph Convolutional Neural Network (2021)
-
Fast Flow Reconstruction via Robust Invertible n × n Convolution (2021)
-
DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking (2021)
Collaboration Network
Top Collaborators
Khoa Luu
39 shared publications
In database
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- Movement Analysis for Neurological and Musculoskeletal Disorders Using Graph Convolutional Neural Network
- Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding
Showing 5 of 39 shared publications
Ngan Le
University of Arkansas at Fayetteville (US)
13 shared publications
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition
- Self-Supervised Domain Adaptation in Crowd Counting
- OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
Showing 5 of 13 shared publications
Chi Nhan Duong
Concordia University (CA)
12 shared publications
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition
- Fast Flow Reconstruction via Robust Invertible n × n Convolution
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
Showing 5 of 12 shared publications
Bhiksha Raj
10 shared publications
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
- The Right to Talk: An Audio-Visual Transformer Approach
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
- EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
Showing 5 of 10 shared publications
Ashley P. G. Dowling
University of Arkansas at Fayetteville
8 shared publications
In database
- Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding
- OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
- Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding
- CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation
- CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation
Showing 5 of 8 shared publications
Jackson Cothren
Centre de Géosciences
6 shared publications
In database
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
- FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models
Showing 5 of 6 shared publications
Son Lam Phung
5 shared publications
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
Hoang-Quan Nguyen
University of Arkansas at Fayetteville
5 shared publications
In database
- Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding
- Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
- Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding
- Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding
- Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding
Xin Li
University at Albany, State University of New York
4 shared publications
In database
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models
Xuan-Bac Nguyen
University of Arkansas at Fayetteville
4 shared publications
In database
- Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding
- OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
- OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
- Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding
Pierce Helton
University of Arkansas at Fayetteville
4 shared publications
In database
- EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring
- CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars
- CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars
- CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation
Utsav Prabhu
4 shared publications
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
- EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
- EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
Pha Nguyen
University of Arkansas at Fayetteville
3 shared publications
In database
- Self-Supervised Domain Adaptation in Crowd Counting
- DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking
- Self-supervised Domain Adaptation in Crowd Counting
Han‐Seok Seo
University of Arkansas System
3 shared publications
In database
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
- Movement Analysis for Neurological and Musculoskeletal Disorders Using Graph Convolutional Neural Network
- DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
Chase Rainwater
University of Arkansas at Fayetteville
3 shared publications
In database
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
- EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring
- BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
Similar Researchers
Based on overlapping research topics
Katerina Klimoska
University of Arkansas at Fayetteville
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques
J.P. Maxwell
University of Central Arkansas
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques
Richard J. Ham
University of Arkansas at Fayetteville
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques
Kashu Kamazaki
University of Arkansas at Fayetteville
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques
Derya Cansever
Harding University Main Campus
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques
Nandagopal Parise
Southern Arkansas University
Advanced Neural Network Applications
Machine Learning Applications
Computer Graphics and Visualization Techniques