Welcome to Ba Hung Ngo's Site

Research Interests

• Transfer Learning

• Domain Adaptation

• Graph Convolutional Network (GCN) 

• Semi-Supervised Learning

• Knowledge Distillation

• Few-shot Learning

• Remote Sensing

• Metaverse (3D Reconstruction)

• Deep Learning for Fault Diagnostic

Recent News   

• [10-Dec-2024]: Congratulations! A paper on "HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation" has been accepted in The Association for the Advancement of Artificial Intelligence (AAAI-2025)  (Ranking A*) 

• [2-March-2024]: Congratulations! A paper on "Dual Dynamic Consistency Regularization for Semi-supervised Domain Adaptation" has been accepted in IEEE Access (First author) (IF: 3.9). 

• [27-Feb-2024]: Congratulations! A paper on "Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation" has been accepted in The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024 (Ranking A*) . 

• [26-Nov-2023]: Congratulations! A paper on "Multiple Task-based Multi-source Domain Adaptation Using Divide-and-conquer Strategy" has been accepted in IEEE Access (First author) (IF: 3.9).

• [25-Nov-2023]: Congratulations!  We are the official challenge winner for track 1 in UPAR Challenge 2024: Pedestrian Attribute Recognition and Attribute-based Person Retrieval - Dataset, Design, and Results of 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). 

• [18-Nov-2023]: Congratulations! A paper on "C2T-Net: Channel-Aware Cross-Fused Transformer-style Networks for Pedestrian Attribute Recognition" has been accepted in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). 

• [8-Aug-2023]: Congratulations! A paper on "Towards Robust Natural-Looking Mammography Lesion Synthesis on Ipsilateral Dual-Views Breast Cancer Analysis" has been accepted in International Conference on Computer Vision Workshop - ICCV Workshop (Co-author) (Ranking A*). 

• [5-Aug-2023]: Congratulations! A paper on "Adversarial Representation Teaching with Perturbation-agnostic Student-Teacher Structure for Semi-supervised Learning" has been accepted in Applied Intelligence (Springer) (Co-author) (IF: 5.3). 

• [14-Jul-2023]: Congratulations! A paper on "Improved Knowledge Transfer for Semi-supervised Domain Adaptation via Trico Training Strategy" has been accepted in International Conference on Computer Vision-ICCV  (First  author) (Ranking A*).  

• [12-Jul-2023]: Congratulations! A paper on "Point2Lane: Polyline-based Reconstruction with Principal Points for Lane Detection" has been accepted in Transactions on Intelligent Transportation Systems (Co-author) (IF: 8.5). 

• [3-Jan-2023]: Congratulations! A paper on "Easy-to-Hard Structure for Remote Sensing Scene Classification in Multi-Target Domain Adaptation" has been accepted in IEEE Transactions on Geoscience and Remote Sensing (First author) (IF: 8.125).

• [30-Step-2022]: Congratulations! A paper on "Distilling and Refining Domain-Specific Knowledge for Semi-Supervised Domain Adaptation" has been accepted in The 33rd British Machine Vision Conference (BMVC 2022)-ranking B) (Co-author).

• [21-Aug-2022]: Congratulations! A paper on"Pseudo Label Rectification via Co-teaching and Decoupling for Multi-source Domain Adaptation in Semantic Segmentation" has been accepted in IEEE Access (Co-author) (IF: 3.476).

• [05-Jul-2022]: Congratulations! A paper on "Collaboration between Multiple Experts for Knowledge Adaptation on Multiple Remote Sensing Sources" has been accepted in IEEE Transactions on Geoscience and Remote Sensing (First author) (IF: 8.125).

• [08-May-2022]: Congratulations! Receive "Research Award for Graduate Student" from Dongguk University.

• [14-Dec-2021 ]: Congratulations! A paper on "Multi-view Collaborative Learning for Semi-supervised Domain Adaption" has been accepted in IEEE Access (First author) (IF: 3.476).

• [02-Sep-2021 ]: Congratulations! A paper on "Semi-supervised Domain Adaptation using Explicit Class-wise Matching for Domain-Invariant and Class-Discriminative Feature Learning" has been accepted in IEEE Access (First author) (IF: 3.476).