TNTruong Q. Nguyen

Truong Q. Nguyen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Truong Q. Nguyen has a total of 148 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    KeyNode-Driven Geometry Coding for Real-World Scanned Human Dynamic Mesh Compression

    by Huong Hoang, Truong Nguyen, Pamela Cosman

    The compression of real-world scanned 3D human dynamic meshes is an emerging research area, driven by applications such as telepresence, virtual reality, and 3D digital streaming. Unlike synthesized dynamic meshes with fixed topology, scanned dynamic meshes often not only have varying topology across frames but also scan defects such as holes and outliers, increasing the complexity of prediction and compression. Additionally, human meshes often combine rigid and non-rigid motions, making accurate prediction and encoding significantly more difficult compared to objects that exhibit purely rigid motion. To address these challenges, we propose a compression method designed for real-world scanned human dynamic meshes, leveraging embedded key nodes. The temporal motion of each vertex is formulated as a distance-weighted combination of transformations from neighboring key nodes, requiring the transmission of solely the key nodes' transformations. To enhance the quality of the KeyNode-driven prediction, we introduce an octree-based residual coding scheme and a Dual-direction prediction mode, which uses I-frames from both directions. Extensive experiments demonstrate that our method achieves significant improvements over the state-of-the-art, with an average bitrate savings of 58.43% across the evaluated sequences, particularly excelling at low bitrates.


  • Open Access

    Image-Conditioned 3-D Gaussian Splat Quantization for Scene Archival

    by Xinshuang Liu, Runfa Blark Li, Keito Suzuki, Truong Q. Nguyen

    3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. In this work, we focus on archiving precomputed 3DGS scenes. Although 3DGS compression methods have been proposed for deployment on storage-constrained devices, two limitations hinder archival use: (1) they compress medium-scale scenes only down to the megabyte range, which remains impractical for extensive scene collections and (2) they lack mechanisms to accommodate scene changes in appearance and illumination after long-term archival. To address these limitations, we propose an Image-Conditioned Gaussian Splat Quantizer (ICGS-Quantizer) that substantially enhances compression efficiency and provides adaptability to scene changes after archiving. ICGS-Quantizer improves quantization efficiency by jointly exploiting inter-Gaussian and inter-attribute correlations and by using shared codebooks across all training scenes. These codebooks are then fixed and applied to previously unseen test scenes, eliminating the overhead of per-scene codebooks. This approach effectively reduces the storage requirements for 3DGS to the kilobyte range while preserving visual fidelity. To enable adaptability to post-archival scene changes, ICGS-Quantizer conditions scene decoding on images captured at decoding time. The encoding, quantization, and decoding processes are trained jointly, ensuring that the codes (quantized representations of the scene) are effective for conditional decoding. We evaluate ICGS-Quantizer on 3D scene compression and 3D scene updating using synthetic scenes composed of Google Scanned Objects (GSO) assets. Experimental results show that ICGS-Quantizer consistently outperforms state-of-the-art methods in compression efficiency and adaptability to scene changes. Our code, model, and data will be publicly available on GitHub.


  • NIARE: Noise-Induced Analysis for Model Robustness Evaluation in Asthma Phenotype Classification

    by Mehmet F. Bagci, Samantha R. Spierling Bagsic, Truong Nguyen, Brian D. Modena, Yusuf Ozturk

    Robust unsupervised modeling is critical in medical applications where high-dimensional noise and outliers can destabilize clustering and mislead clinical interpretation. However, existing internal validation indices- such as the Silhouette score, Davies-Bouldin index, and Calinski-Harabasz index- mainly quantify cohesion and separation, providing limited insight into noise resistance. In addition, adversarial robustness techniques developed for supervised learning cannot be directly applied to unsupervised biomedical phenotyping, leaving a critical methodological gap. We introduce Noise-Induced Analysis for Robustness Evaluation (NIARE), a framework that quantifies robustness by augmenting datasets with synthetic noise-only features drawn from controlled distributions. NIARE operates in two modes: (i) feature-reduction scoring, which identifies the onset of noise-dominated components to guide dimensionality selection, and (ii) clustering scoring, which measures the importance assigned to injected noise features relative to real features to assess cluster stability. Applied to a high-dimensional asthma cohort of 1,112 patients across 3,471 clinical visits, NIARE selected a five-component PCA representation and a five-cluster operating point, yielding clinically distinct asthma phenotypes characterized by differences in lung function, inflammatory markers, oral corticosteroid burden, and visit frequency. External validation on the Severe Asthma Research Program (SARP) cohort further supported generalizability by recovering the established five-phenotype asthma structure without requiring ground-truth labels. Compared with conventional validation indices, NIARE provides a scalable and interpretable measure of robustness for highdimensional biomedical clustering, offering a practical alternative to supervised adversarial methods in unsupervised clinical phenotyping.

  • Universal Vessel Segmentation for Multi-Modality Retinal Images

    by Bo Wen, Anna Heinke, Akshay Agnihotri, Dirk-Uwe Bartsch, William Freeman, Truong Nguyen, Cheolhong An

    We identify two major limitations in the existing studies on retinal vessel segmentation: (1) Most existing works are restricted to one modality, i.e., the Color Fundus (CF). However, multi-modality retinal images are used every day in the study of the retina and diagnosis of retinal diseases, and the study of vessel segmentation on other modalities is scarce; (2) Even though a few works extended their experiments to new modalities such as the Multi-Color Scanning Laser Ophthalmoscopy (MC), these works still require fine-tuning a separate model for the new modality. The fine-tuning will require extra training data, which is difficult to acquire. In this work, we present a novel universal vessel segmentation model (URVSM) for multi-modality retinal images. In addition to performing the study on a much wider range of image modalities, we also propose a universal model to segment the vessels in all these commonly used modalities. While being much more versatile compared with existing methods, our universal model also demonstrates comparable performance to the state-of-the-art fine-tuned methods. To the best of our knowledge, this is the first work that achieves modality-agnostic retinal vessel segmentation and the first to study retinal vessel segmentation in several novel modalities.


  • THP3D: Text-Driven Multi-granularity 3D Human Parsing

    by Keito Suzuki, Bang Du, Kunyao Chen, Runfa Li, Truong Nguyen


  • Postural Stability as a Measure of Fall Risk in Older People with and without HIV

    by Mary Clare Masters, Laura M. Campbell, Jimmy Yu, Anne Heaton, Kristine M. Erlandson, Hari Garudadri, Truong Nguyen, David J. Moore, Raeanne C. Moore

    As the number of older people with HIV (PWH) grows, accidental falls and their associated negative health outcomes are of increasing concern. Fall risk can be measured using novel screening tools such as evaluating postural stability using force plate technology. The aims of this study were to test this technology to assess fall risk among older PWH. In a cross-sectional, observational study of people with and without (PWoH) with a range of fall risk, participants underwent balance assessment using the validated BTrackS balance plate. Postural stability was compared by HIV serostatus. Multivariable linear regressions were used to examine the relationship between postural stability and validated measures of fall risk balance and frailty status. Among 34 PWH and 30 PWoH, all ≥50 years, postural stability was worse among PWH (35.4 cm vs 28.3 cm, p= 0.07). In multivariable models, worse postural stability was associated with reporting a fall in the past 6 months (β=0.32, p=0.004), worse fall efficacy (β=0.45, p<0.001), and being frail or pre-frail (β=0.26, p=0.027). In multivariable models stratified by HIV serostatus, worse postural stability was significantly associated with worse fall efficacy (β=0.53, p<0.01) and lower balance confidence (β=-0.33, p=0.04) among PWH but not PWoH. Among older PWH and PWoH, worse postural stability was associated with validated measures of fall risk, including history of falls and poorer falls efficacy. Assessment of postural sway is a promising objective screening test for fall risk among older PWH.

  • Enhancing lesion detection in liver and kidney CT scans via lesion mask selection from two models: A main model and a model focused on small lesions

    by Abdullah F. Al-Battal, Van Ha Tang, Quang Duc Tran, Steven Q.H. Truong, Chien Phan, Truong Q. Nguyen, Cheolhong An


  • Board 85: Work in Progress: Asset-Driven Equitable Partnerships (ADEP in Practice)

    by Kenneth Connor, Mohamed F. Chouikha, John C. Kelly, Pamela Leigh-Mack, Barry J. Sullivan, Stephen M Goodnick, Miguel Velez-Reyes, Michelle Klein, Truong Nguyen, Petru Andrei, et al.

  • Open Access

    A Lattice-Structure-Based Trainable Orthogonal Wavelet Unit for Image Classification

    by An D. Le, Shiwei Jin, You-Suk Bae, Truong Q. Nguyen

    This work introduces Orthogonal-LatticeUwU, a novel trainable wavelet unit for enhancing image classification and anomaly detection in convolutional neural networks by reducing information loss during pooling. The unit employs an orthogonal lattice structure, relaxing the zero-at-π condition and decreasing the number of trainable wavelet coefficients. This innovation is a key novelty of the work. The unit modifies convolution, pooling, and down-sampling operations. Implemented in ResNet18, it improved detection accuracy on CIFAR10 (by 2.67%), ImageNet1K (by 1.85%), and the Describable Textures dataset (by 9.52%), showcasing its advantages in detecting detailed features. Similar gains were seen in ResNet34 and ResNet50 implementations. For anomaly detection in hazelnut images on the MVTec Anomaly Detection dataset, the proposed method achieved a segmentation area under the receiver operating characteristic curve of 97.15% and better anomaly localization. The method excels in detecting detailed features, despite increased trainable parameters from using one-layer fully convolutional networks for feature combination.