Match tier Listed
Presence Current · Arkansas
Last published 2026
Sources OpenAlex · ORCID
Refreshed 2026-10-05

Thanh-Dat Truong

Postdoctoral Fellow

Also affiliated: Vietnam National University Ho Chi Minh City (2018–2019); Ho Chi Minh City University of Science (2018–2019)

11 h-index 64 pubs 433 cited

Biography and Research Information

OverviewAI-generated summary

Thanh-Dat Truong's research focuses on the application of machine learning and deep learning techniques to various analytical challenges. His work includes developing advanced models for action recognition, domain adaptation in semantic scene segmentation, and fairness in semantic scene understanding. Truong has also investigated the use of graph convolutional neural networks for movement analysis in neurological and musculoskeletal disorders, and lightweight deep convolutional networks for tiny object recognition.

His publications also address vehicle re-identification and abnormality detection for traffic video analysis, as well as traffic flow analysis and velocity estimation. Furthermore, Truong has explored smart lifelog retrieval systems utilizing habit-based concepts and moment visualization. He has a publication record of 64 papers, with 433 citations, and an h-index of 11. Truong collaborates with researchers from the University of Arkansas at Fayetteville, including Ky Luu, Ashley P. G. Dowling, Xuan-Bac Nguyen, and Jackson Cothren.

Metrics

  • h-index: 11
  • Publications: 64
  • Citations: 433

Positions

  • Postdoctoral Fellow 2025–present
    University of Arkansas at Fayetteville Electrical Engineering and Computer Science ORCID
  • Postdoctoral Fellow publications 2022–2026
    Arkansas State University ORCID

Selected Publications

  • $ϕ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models (2026)
    arXiv (Cornell University) OpenAlex
  • MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning (2025)
    1 citation DOI OpenAlex
  • DEGA: Dynamic Entropy Guided Adaptation (2025)
  • Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models (2025)
    arXiv (Cornell University) DOI OpenAlex
  • Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding (2025)
    International Journal of Computer Vision 10 citations DOI OpenAlex
  • Cross-view action recognition understanding from exocentric to egocentric perspective (2024)
    Neurocomputing 5 citations DOI OpenAlex
  • CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars (2024)
    7 citations DOI OpenAlex
  • Insect-Foundation: A Foundation Model and Large-Scale 1M Dataset for Visual Insect Understanding (2024)
    18 citations DOI OpenAlex
  • LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition (2023)
    Neurocomputing 14 citations DOI OpenAlex
  • OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation (2022)
    2022 26th International Conference on Pattern Recognition (ICPR) 9 citations DOI OpenAlex
  • Self-Supervised Domain Adaptation in Crowd Counting (2022)
    2022 IEEE International Conference on Image Processing (ICIP) 10 citations DOI OpenAlex
  • EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring (2022)
    IEEE Access 10 citations DOI OpenAlex
  • BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation (2021)
    arXiv (Cornell University) DOI OpenAlex
  • Movement Analysis for Neurological and Musculoskeletal Disorders Using Graph Convolutional Neural Network (2021)
    Future Internet 24 citations DOI OpenAlex
  • Fast Flow Reconstruction via Robust Invertible n × n Convolution (2021)
    Future Internet 6 citations DOI OpenAlex

View all publications on OpenAlex →

Collaboration Network

50 Collaborators 17 Institutions 7 Countries

Top Collaborators

View profile →
View profile →
View profile →
View profile →
View profile →

Similar Researchers

Based on overlapping research topics