Ta Huu Anh Duong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ta Huu Anh Duong has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Anh-Nhat Nguyen
FPT University
4 shared publications - Dinh-Cuong Hoang
Greenwich Vietnam, FPT University, Hanoi, Vietnam
4 shared publications - Phan Xuan Tan
College of Engineering, Shibaura Institute of Technology, Tokyo, Japan
4 shared publications - Van-Hiep Duong
FPT University
4 shared publications - Duc-Long Pham
IT Department, FPT University, Hanoi, Vietnam
3 shared publications - Duc-Manh Nguyen
Greenwich Vietnam, FPT University, Hanoi, Vietnam
3 shared publications
Latest Publications
- Open Access
- 20 January 2026
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 137, 171-193
Vote3D-AD: Unsupervised point cloud anomaly localization via varied defect synthesis and differentiable vote-clustering
- 20 January 2026
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 137, 171-193
Open AccessVote3D-AD: Unsupervised point cloud anomaly localization via varied defect synthesis and differentiable vote-clustering
- Open Access
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 110166-110184
Depth-Guided Monocular Object Pose Estimation for Warehouse Automation
Accurate object pose estimation is essential for warehouse automation, enabling tasks such as robotic picking, sorting, and inventory management. Current state-of-the-art approaches rely on both color (RGB) and depth (D) images, as depth information provides critical geometric cues that enhance object localization and improve robustness against occlusions. However, RGBD-based methods require specialized depth sensors, which can be costly and may not function reliably in warehouse environments with reflective surfaces, varying lighting conditions, or sensor occlusions. To address these limitations, researchers have explored RGB-only approaches, but the absence of depth cues makes it challenging to handle occlusions, estimate object geometry, and differentiate between textureless or highly similar objects, which are common in warehouses. In this paper, we propose a novel end-to-end depth-guided object pose estimation method tailored for warehouse automation. Our approach leverages both depth and color images during training but relies solely on RGB images during inference. Depth images are used to supervise the training of a depth estimation network, which generates initial depth-aware features. These features are then refined using our proposed depth-guided feature enhancement module to improve spatial understanding and robustness. The enhanced features are subsequently utilized for keypoint-based 6D object pose estimation. By integrating depth-guided feature learning, our method significantly enhances pose estimation accuracy, especially in cluttered warehouse environments with severe occlusions and textureless objects. Extensive experiments on warehouse-specific datasets, as well as standard benchmark datasets, demonstrate that our approach outperforms existing RGB-based methods while maintaining real-time inference speeds, making it a highly practical solution for real-world warehouse automation applications.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 110166-110184
Open AccessDepth-Guided Monocular Object Pose Estimation for Warehouse Automation
Accurate object pose estimation is essential for warehouse automation, enabling tasks such as robotic picking, sorting, and inventory management. Current state-of-the-art approaches rely on both color (RGB) and depth (D) images, as depth information provides critical geometric cues that enhance object localization and improve robustness against occlusions. However, RGBD-based methods require specialized depth sensors, which can be costly and may not function reliably in warehouse environments with reflective surfaces, varying lighting conditions, or sensor occlusions. To address these limitations, researchers have explored RGB-only approaches, but the absence of depth cues makes it challenging to handle occlusions, estimate object geometry, and differentiate between textureless or highly similar objects, which are common in warehouses. In this paper, we propose a novel end-to-end depth-guided object pose estimation method tailored for warehouse automation. Our approach leverages both depth and color images during training but relies solely on RGB images during inference. Depth images are used to supervise the training of a depth estimation network, which generates initial depth-aware features. These features are then refined using our proposed depth-guided feature enhancement module to improve spatial understanding and robustness. The enhanced features are subsequently utilized for keypoint-based 6D object pose estimation. By integrating depth-guided feature learning, our method significantly enhances pose estimation accuracy, especially in cluttered warehouse environments with severe occlusions and textureless objects. Extensive experiments on warehouse-specific datasets, as well as standard benchmark datasets, demonstrate that our approach outperforms existing RGB-based methods while maintaining real-time inference speeds, making it a highly practical solution for real-world warehouse automation applications.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1548-1564
Self-Supervised Object Pose Estimation With Multitask Learning
Object pose estimation using learning-based methods often necessitates vast amounts of meticulously labeled training data. The process of capturing real-world object images under diverse conditions and annotating these images with 6 Degrees of Freedom (6DOF) object poses is both time-consuming and resource-intensive. In this study, we propose an innovative approach to monocular 6D pose estimation through self-supervised learning, eliminating the need for labor-intensive manual annotations. Our method initiates by training a multi-task neural network in a fully supervised manner, leveraging synthetic RGBD data. We leverage semantic segmentation, instance-level depth estimation, and vector-field prediction as auxiliary tasks to enhance the primary task of pose estimation. Subsequently, we harness advancements in multi-task learning to further self-supervise the model using unlabeled real-world RGB data. A pivotal element of our self-supervised object pose estimation is a geometry-guided pseudo-label filtering module that relies on estimated depth from instance-level depth estimation. Our extensive experiments conducted on benchmark datasets demonstrate the effectiveness and potential of our approach in achieving accurate monocular 6D pose estimation. Importantly, our method showcases a promising avenue for overcoming the challenges associated with the labor-intensive annotation process, offering a more efficient and scalable solution for real-world object pose estimation.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1548-1564
Self-Supervised Object Pose Estimation With Multitask Learning
Object pose estimation using learning-based methods often necessitates vast amounts of meticulously labeled training data. The process of capturing real-world object images under diverse conditions and annotating these images with 6 Degrees of Freedom (6DOF) object poses is both time-consuming and resource-intensive. In this study, we propose an innovative approach to monocular 6D pose estimation through self-supervised learning, eliminating the need for labor-intensive manual annotations. Our method initiates by training a multi-task neural network in a fully supervised manner, leveraging synthetic RGBD data. We leverage semantic segmentation, instance-level depth estimation, and vector-field prediction as auxiliary tasks to enhance the primary task of pose estimation. Subsequently, we harness advancements in multi-task learning to further self-supervise the model using unlabeled real-world RGB data. A pivotal element of our self-supervised object pose estimation is a geometry-guided pseudo-label filtering module that relies on estimated depth from instance-level depth estimation. Our extensive experiments conducted on benchmark datasets demonstrate the effectiveness and potential of our approach in achieving accurate monocular 6D pose estimation. Importantly, our method showcases a promising avenue for overcoming the challenges associated with the labor-intensive annotation process, offering a more efficient and scalable solution for real-world object pose estimation.
- Open Access
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 54-60
Enhancing Facial Expression Recognition through Multi-branch Self-distillation with Collaborative Teacher
- 20 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 54-60
Open AccessEnhancing Facial Expression Recognition through Multi-branch Self-distillation with Collaborative Teacher
- Open Access
- 2 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 3667-3682
Unsupervised Visual-to-Geometric Feature Reconstruction for Vision-Based Industrial Anomaly Detection
Industrial anomaly detection involves identifying abnormal regions in products and plays a crucial role in quality inspection. While 2D image-based anomaly detection has been extensively explored, combining two-dimensional (2D) images with three-dimensional (3D) point clouds remains less studied. Existing multimodal methods often combine features from different modalities, leading to feature interference and degraded performance. To overcome this, we propose a novel framework for unsupervised industrial anomaly detection that leverages both visual and geometric information. Specifcally, we use pre-trained 2D and 3D models to extract visual features from color images and geometric features from 3D point clouds. Instead of directly fusing these features, we propose a geometric feature reconstruction network that predicts 3D geometric features from the 2D visual features. During training, we minimize the difference between the predicted geometric features and the extracted geometric features, enabling the model to learn how 2D appearance correlates with 3D structure in anomaly-free images. During inference, this learned relationship allows the model to detect anomalies: signifcant discrepancies between the reconstructed and actual geometric features indicate abnormal regions. Evaluated on the MVTec 3D-AD dataset, our method achieves state-of-the-art performance with an average image-level AUROC score of 0.968, surpassing previous approaches. Additionally, it provides fast inference at 8.2 frames per second with a memory footprint of only 1045 MB, making it highly effcient for industrial applications
- 2 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 3667-3682
Open AccessUnsupervised Visual-to-Geometric Feature Reconstruction for Vision-Based Industrial Anomaly Detection
Industrial anomaly detection involves identifying abnormal regions in products and plays a crucial role in quality inspection. While 2D image-based anomaly detection has been extensively explored, combining two-dimensional (2D) images with three-dimensional (3D) point clouds remains less studied. Existing multimodal methods often combine features from different modalities, leading to feature interference and degraded performance. To overcome this, we propose a novel framework for unsupervised industrial anomaly detection that leverages both visual and geometric information. Specifcally, we use pre-trained 2D and 3D models to extract visual features from color images and geometric features from 3D point clouds. Instead of directly fusing these features, we propose a geometric feature reconstruction network that predicts 3D geometric features from the 2D visual features. During training, we minimize the difference between the predicted geometric features and the extracted geometric features, enabling the model to learn how 2D appearance correlates with 3D structure in anomaly-free images. During inference, this learned relationship allows the model to detect anomalies: signifcant discrepancies between the reconstructed and actual geometric features indicate abnormal regions. Evaluated on the MVTec 3D-AD dataset, our method achieves state-of-the-art performance with an average image-level AUROC score of 0.968, surpassing previous approaches. Additionally, it provides fast inference at 8.2 frames per second with a memory footprint of only 1045 MB, making it highly effcient for industrial applications