arXiv subjects

Duc Nguyen

Publications and source records attributed to Duc Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

DeQL: A Decision Query Language for Prescriptive Analytics over Relational Data

DeQL (Decision Query Language) extends SQL to express decision queries: given options drawn from relational data, constraints from policy, and a measurable objective, a DeQL query computes the best course of action. Two constructs carry the core of the extension: CREATE CANDIDATES, which defines the space of options from relational sources, and DECIDE, which declares decision variables, named constraints, and an objective over them. The design follows SQL's principles: the user states what to optimize while the engine chooses how to solve it, every query consumes and produces relations, and the structure of a problem stays visible to the engine. This document specifies the language: its design principles, syntax, formal grammar, and execution model. The examples span subset selection, allocation, assignment, scheduling, and decisions at multiple levels of aggregation. The specification also covers extensions for optimization under uncertainty, inline model scoring, and time- and quality-bounded solving. It is an early version of the specification; the language is under active development, and this version fixes the core constructs on which later revisions will build.

cs.DB↗

arXiv2026

ARGUSTRACK: A Multi-View Annotation System for Multi-Object Tracking

Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monitoring. While recent advances have yielded sophisticated tracking algorithms, the availability of annotated multi-view data remains a significant bottleneck. Existing annotation tools predominantly support single-camera workflows or rely on LiDAR sensors, making cross-view labeling tedious and impractical for camera-only setups. We present ARGUS-TRACK, a multi-camera annotation system that addresses these limitations by enabling annotators to work directly on a bird's-eye-view (BEV) plane. Given calibrated camera parameters, a single ground-plane annotation is automatically projected into 2D bounding boxes across all relevant views, inherently ensuring identity consistency without manual cross-view alignment. To further accelerate the labeling process, ARGUSTRACK incorporates two complementary mechanisms: a Temporal Aware module that propagates annotations from preceding frames to initialize new ones, requiring only minor positional adjustments; and a Multi-camera Semi-annotation module that leverages off-the-shelf 2D detectors combined with foot-point estimation to automatically generate candidate BEV positions for annotator verification. We evaluate ARGUSTRACK through a pilot study on multi-camera broiler tracking and demonstrate that it substantially reduces annotation time compared to conventional single-camera labeling workflows.

cs.CV↗

arXiv2026

Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning

Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to them. Second, the token renormalization used in Slot Attention can amplify weakly attending slots, allowing them to absorb tokens from other objects and destabilize slot-to-object correspondence. We propose Dual-State Slot Attention (DSSA), a fully self-supervised framework that addresses these limitations by separating appearance from identity and by reducing spurious updates from weakly matching slots. DSSA decomposes each slot into a local state for per-frame appearance and an identity state for temporally stable object information, thereby aligning reconstruction and temporal consistency with separate representations. The identity state is updated through a learned recurrent transition that acts as a temporal filter on the local state, while competition-modulated aggregation (CMA) down-weights updates from weakly matching slots and prevents them from absorbing tokens from other objects. Experiments on MOVi-C, MOVi-D, and YouTube-VIS demonstrate that DSSA consistently improves segmentation quality and temporal consistency over prior methods, while also yielding stronger downstream object recognition and video dynamics prediction. Code and models will be made publicly available upon acceptance.

cs.CV↗

arXiv2026

TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation

Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propagate a fixed set of slots across frames, but typically assume unconditional slot propagation: every slot is updated and decoded at every frame, regardless of whether its corresponding object is visible. We show that this design violates a basic lifecycle requirement for persistent slots: when an object is absent or fully occluded, its slot should preserve its previous state and avoid explaining unrelated visible content. Instead, unconditional propagation creates two failure pathways: update-induced state drift, where current-frame evidence overwrites the absent object's representation, and decoder-induced reconstruction interference, where the inactive slot remains coupled to reconstruction through decoder attention. We propose Temporal Slot Activation (TSA), a mechanism that learns a per-slot, per-frame activation score $\alpha_{k,t} \in (0, 1)$ without visibility supervision. TSA uses this activation as a shared latent control variable for slot lifecycle modeling. When a slot is inactive, TSA anchors its state to the previous slot via activation-gated updating and suppresses its decoder participation through an activation-dependent additive bias on attention logits before softmax normalization. This jointly reduces state drift and reconstruction-driven interference. To improve decisions under partial occlusion and gradual reappearance, TSA further conditions activation prediction on a per-slot temporal memory produced by a Temporal Context Encoder. We evaluate TSA on MOVi-C/E, YT-VIS, and OVIS benchmarks using both standard and tracking-based metrics (FG-ARI, mBO, IDF1, HOTA). TSA consistently improves object decomposition and temporal identity preservation, with large gains on long, heavily occluded videos.

cs.CV↗

arXiv2025

TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding

3D semantic scene understanding remains a long-standing challenge in the 3D computer vision community. One of the key issues pertains to limited real-world annotated data to facilitate generalizable models. The common practice to tackle this issue is to simulate new data. Although synthetic datasets offer scalability and perfect labels, their designer-crafted scenes fail to capture real-world complexity and sensor noise, resulting in a synthetic-to-real domain gap. Moreover, no benchmark provides synchronized real and simulated point clouds for segmentation-oriented domain shift analysis. We introduce TrueCity, the first urban semantic segmentation benchmark with cm-accurate annotated real-world point clouds, semantic 3D city models, and annotated simulated point clouds representing the same city. TrueCity proposes segmentation classes aligned with international 3D city modeling standards, enabling consistent evaluation of synthetic-to-real gap. Our extensive experiments on common baselines quantify domain shift and highlight strategies for exploiting synthetic data to enhance real-world 3D scene understanding. We are convinced that the TrueCity dataset will foster further development of sim-to-real gap quantification and enable generalizable data-driven models. The data, code, and 3D models are available online: https://tum-gis.github.io/TrueCity/

cs.CV↗

arXiv2025

VM14K: First Vietnamese Medical Benchmark

Medical benchmarks are indispensable for evaluating the capabilities of language models in healthcare for non-English-speaking communities,therefore help ensuring the quality of real-life applications. However, not every community has sufficient resources and standardized methods to effectively build and design such benchmark, and available non-English medical data is normally fragmented and difficult to verify. We developed an approach to tackle this problem and applied it to create the first Vietnamese medical question benchmark, featuring 14,000 multiple-choice questions across 34 medical specialties. Our benchmark was constructed using various verifiable sources, including carefully curated medical exams and clinical records, and eventually annotated by medical experts. The benchmark includes four difficulty levels, ranging from foundational biological knowledge commonly found in textbooks to typical clinical case studies that require advanced reasoning. This design enables assessment of both the breadth and depth of language models' medical understanding in the target language thanks to its extensive coverage and in-depth subject-specific expertise. We release the benchmark in three parts: a sample public set (4k questions), a full public set (10k questions), and a private set (2k questions) used for leaderboard evaluation. Each set contains all medical subfields and difficulty levels. Our approach is scalable to other languages, and we open-source our data construction pipeline to support the development of future multilingual benchmarks in the medical domain.

cs.CL↗

arXiv2025

Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer architectures using highly flexible non-autonomous neural ordinary differential equations (ODEs). Our proposed model parameterizes all weights of attention and feed-forward blocks through neural networks, expressing these weights as functions of a continuous layer index. Through spectral analysis of the model's dynamics, we uncover an increase in eigenvalue magnitude that challenges the weight-sharing assumption prevalent in existing theoretical studies. We also leverage the Lyapunov exponent to examine token-level sensitivity, enhancing model interpretability. Our neural ODE transformer demonstrates performance comparable to or better than vanilla transformers across various configurations and datasets, while offering flexible fine-tuning capabilities that can adapt to different architectural constraints.

cs.LG↗

arXiv2024

Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients

In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle during aggregation, can negate progress, leading to severe weight and gradient update degradation. To address this issue, we introduce a new approach to pFL design, namely Federated Learning with Layer-wise Aggregation via Gradient Analysis (FedLAG), utilizing the concept of gradient conflict at the layer level. Specifically, when layer-wise gradients of different clients form acute angles, those gradients align in the same direction, enabling updates across different clients toward identifying client-invariant features. Conversely, when layer-wise gradient pairs make create obtuse angles, the layers tend to focus on client-specific tasks. In hindsights, FedLAG assigns layers for personalization based on the extent of layer-wise gradient conflicts. Specifically, layers with gradient conflicts are excluded from the global aggregation process. The theoretical evaluation demonstrates that when integrated into other pFL baselines, FedLAG enhances pFL performance by a certain margin. Therefore, our proposed method achieves superior convergence behavior compared with other baselines. Extensive experiments show that our FedLAG outperforms several state-of-the-art methods and can be easily incorporated with many existing methods to further enhance performance.

cs.LG↗

arXiv2024

A change-point problem for $m$-dependent multivariate random field

In this paper, we consider a change-point problem for a centered, stationary and $m$-dependent multivariate random field. Under the distribution free assumption, a change-point test using CUSUM statistic is proposed to detect anomalies within a multidimensional random field, controlling the false positive rate as well as the Family-Wise Error in the multiple hypotheses testing context.

math.ST↗

arXiv2024

DFS-based fast crack pre-detection

This paper develops a computationally efficient pre-detection method for cracks in three-dimensional CT images of concrete. Instead of attempting full voxel-wise crack segmentation, the method focuses on locating cubic subregions where crack structures are likely to be present and should be analyzed further. The proposed pipeline combines multiscale Maximal Hessian Entry filtering with graph-based connectivity analysis. After binarization, each subregion is represented by the boundary face with the largest foreground pixels, which transforms the local detection problem from a three-dimensional image task into a two-dimensional graph problem. A sparse lattice graph is constructed on the selected face, and Depth-First Search is applied to detect connected components corresponding to possible crack cross-sections. The choice of mesh size is justified by a probabilistic upper bound on a lattice-miss event. Experiments on semi-synthetic and real CT data show that the method gives fast, interpretable crack pre-localization while avoiding exhaustive analysis of the full image.

eess.IV↗

arXiv2024

A Subjective Quality Evaluation of 3D Mesh with Dynamic Level of Detail in Virtual Reality

3D meshes are one of the main components of Virtual Reality applications. However, many network and computational resources are required to process 3D meshes in real-time. A potential solution to this challenge is to dynamically adapt the Level of Detail (LoD) of a 3D mesh based on the object's position and the user's viewpoint. In this paper, we conduct a subjective study to investigate users' quality perception of 3D meshes with dynamic Level of Detail in a Virtual Reality environment. The subjective experiment is carried out with five 3D meshes of different characteristics, four Levels of Detail, and four distance settings. The results of the experiment show that the impact of the dynamic level of detail depends on both the position of the 3D object in the virtual world and the number of vertices of the original mesh. In addition, we present a quality model that can accurately predict the MOS score of a LoD version of a 3D mesh from the number of vertices and the distance from the viewpoint.

cs.MM↗

arXiv2024

A statistical method for crack pre-detection in 3D concrete images

In practical applications, effectively segmenting cracks in large-scale computed tomography (CT) images holds significant importance for understanding the structural integrity of materials. Classical image-processing techniques and modern deep-learning models both face substantial computational challenges when applied directly to high resolution big data volumes. This paper introduces a statistical framework for crack pre-localization, whose purpose is not to replace or compete with segmentation networks, but to identify, with controlled error rates, the regions of a 3D CT image that are most likely to contain cracks. The method combines a simple Hessian-based filter, geometric descriptors computed on a regular spatial partition, and a spatial multiple testing procedure to detect anomalous regions while relying only on minimal calibration data, rather than large annotated datasets. Experiments on semi-synthetic and real 3D CT scans demonstrate that the proposed approach reliably highlights regions likely to contain cracks while preserving linear computational complexity. By restricting subsequent high resolution segmentation to these localized regions, deep-learning models can be trained and operate more efficiently, reducing both training runtime as well as resource consumption. The framework thus offers a practical and interpretable preprocessing step for large-scale CT inspection pipelines.

cs.CV↗

arXiv2023

A Novel and Optimal Spectral Method for Permutation Synchronization

Permutation synchronization is an important problem in computer science that constitutes the key step of many computer vision tasks. The goal is to recover $n$ latent permutations from their noisy and incomplete pairwise measurements. In recent years, spectral methods have gained increasing popularity thanks to their simplicity and computational efficiency. Spectral methods utilize the leading eigenspace $U$ of the data matrix and its block submatrices $U_1,U_2,\ldots, U_n$ to recover the permutations. In this paper, we propose a novel and statistically optimal spectral algorithm. Unlike the existing methods which use $\{U_jU_1^\top\}_{j\geq 2}$, ours constructs an anchor matrix $M$ by aggregating useful information from all of the block submatrices and estimates the latent permutations through $\{U_jM^\top\}_{j\geq 1}$. This modification overcomes a crucial limitation of the existing methods caused by the repetitive use of $U_1$ and leads to an improved numerical performance. To establish the optimality of the proposed method, we carry out a fine-grained spectral analysis and obtain a sharp exponential error bound that matches the minimax rate.

math.ST↗

arXiv2023

Optimal and Private Learning from Human Response Data

Item response theory (IRT) is the study of how people make probabilistic decisions, with diverse applications in education testing, recommendation systems, among others. The Rasch model of binary response data, one of the most fundamental models in IRT, remains an active area of research with important practical significance. Recently, Nguyen and Zhang (2022) proposed a new spectral estimation algorithm that is efficient and accurate. In this work, we extend their results in two important ways. Firstly, we obtain a refined entrywise error bound for the spectral algorithm, complementing the `average error' $\ell_2$ bound in their work. Notably, under mild sampling conditions, the spectral algorithm achieves the minimax optimal error bound (modulo a log factor). Building on the refined analysis, we also show that the spectral algorithm enjoys optimal sample complexity for top-$K$ recovery (e.g., identifying the best $K$ items from approval/disapproval response data), explaining the empirical findings in the previous work. Our second contribution addresses an important but understudied topic in IRT: privacy. Despite the human-centric applications of IRT, there has not been any proposed privacy-preserving mechanism in the literature. We develop a private extension of the spectral algorithm, leveraging its unique Markov chain formulation and the discrete Gaussian mechanism (Canonne et al., 2020). Experiments show that our approach is significantly more accurate than the baselines in the low-to-moderate privacy regime.

cs.LG↗

arXiv2023

Efficient and Accurate Learning of Mixtures of Plackett-Luce Models

Mixture models of Plackett-Luce (PL) -- one of the most fundamental ranking models -- are an active research area of both theoretical and practical significance. Most previously proposed parameter estimation algorithms instantiate the EM algorithm, often with random initialization. However, such an initialization scheme may not yield a good initial estimate and the algorithms require multiple restarts, incurring a large time complexity. As for the EM procedure, while the E-step can be performed efficiently, maximizing the log-likelihood in the M-step is difficult due to the combinatorial nature of the PL likelihood function (Gormley and Murphy 2008). Therefore, previous authors favor algorithms that maximize surrogate likelihood functions (Zhao et al. 2018, 2020). However, the final estimate may deviate from the true maximum likelihood estimate as a consequence. In this paper, we address these known limitations. We propose an initialization algorithm that can provide a provably accurate initial estimate and an EM algorithm that maximizes the true log-likelihood function efficiently. Experiments on both synthetic and real datasets show that our algorithm is competitive in terms of accuracy and speed to baseline algorithms, especially on datasets with a large number of items.

cs.LG↗

arXiv2022

A Spectral Approach to Item Response Theory

The Rasch model is one of the most fundamental models in \emph{item response theory} and has wide-ranging applications from education testing to recommendation systems. In a universe with $n$ users and $m$ items, the Rasch model assumes that the binary response $X_{li} \in \{0,1\}$ of a user $l$ with parameter $\theta^*_l$ to an item $i$ with parameter $\beta^*_i$ (e.g., a user likes a movie, a student correctly solves a problem) is distributed as $\Pr(X_{li}=1) = 1/(1 + \exp{-(\theta^*_l - \beta^*_i)})$. In this paper, we propose a \emph{new item estimation} algorithm for this celebrated model (i.e., to estimate $\beta^*$). The core of our algorithm is the computation of the stationary distribution of a Markov chain defined on an item-item graph. We complement our algorithmic contributions with finite-sample error guarantees, the first of their kind in the literature, showing that our algorithm is consistent and enjoys favorable optimality properties. We discuss practical modifications to accelerate and robustify the algorithm that practitioners can adopt. Experiments on synthetic and real-life datasets, ranging from small education testing datasets to large recommendation systems datasets show that our algorithm is scalable, accurate, and competitive with the most commonly used methods in the literature.

cs.LG↗

arXiv2022

Network-aware Prefetching Method for Short-Form Video Streaming

Recent years have witnessed the rising of short-form video platforms such as TikTok. Apart from conventional videos, short-form videos are much shorter and users frequently change the content to watch. Thus, it is crucial to have an effective streaming method for this new type of video. In this paper, we propose a resource-efficient prefetching method for short-form video streaming. Taking into account network throughput conditions and user viewing behaviors, the proposed method dynamically adapts the amount of prefetched video data. Experiment results show that our method can reduce the data waste by 37~52% compared to other existing methods.

cs.MM↗

arXiv2022

Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation

In recent years, using orthogonal matrices has been shown to be a promising approach in improving Recurrent Neural Networks (RNNs) with training, stability, and convergence, particularly, to control gradients. While Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM) architectures address the vanishing gradient problem by using a variety of gates and memory cells, they are still prone to the exploding gradient problem. In this work, we analyze the gradients in GRU and propose the usage of orthogonal matrices to prevent exploding gradient problems and enhance long-term memory. We study where to use orthogonal matrices and we propose a Neumann series-based Scaled Cayley transformation for training orthogonal matrices in GRU, which we call Neumann-Cayley Orthogonal GRU, or simply NC-GRU. We present detailed experiments of our model on several synthetic and real-world tasks, which show that NC-GRU significantly outperforms GRU as well as several other RNNs.

cs.LG↗