arXiv subjects

Thanh-Hai Le

Publications and source records attributed to Thanh-Hai Le.

3 recordsLinked to original sources

arXiv2026

A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors

The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization techniques often struggle to balance accuracy with computational efficiency. In this work, we develop and evaluate a temporal action localization framework tailored for driver monitoring scenarios, particularly suitable for periodic inspection settings such as transportation safety checkpoints or fleet management assessment systems. Our approach follows a two-stage pipeline that combines VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector, enhanced by a Spatial Pyramid Pooling-Fast (SPPF) module to capture multi-scale temporal features. Experimental results reveal a distinct trade-off between model capacity and efficiency. At the feature extraction stage, the ViT-Giant backbone delivers higher representations with 88.09% Top-1 test accuracy, while the ViT-based variant proves to be a practical alternative, achieving 82.55% accuracy with significantly lower computational fine-tuning costs (101.85 GFLOPs/segment compared to 1584.06 GFLOPs/segment for Giant). In the downstream localization task, the integration of SPPF consistently improves performance across all configurations. Notably, the ViT-Giant + SPPF model achieves a peak mAP of 92.67%, while the lightweight ViT-based configuration maintains robust results.

cs.CV↗

arXiv2026

Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

This paper presents Few TensoRF, a 3D reconstruction framework that combines TensorRF's efficient tensor based representation with FreeNeRF's frequency driven few shot regularization. Using TensorRF to significantly accelerate rendering speed and introducing frequency and occlusion masks, the method improves stability and reconstruction quality under sparse input views. Experiments on the Synthesis NeRF benchmark show that Few TensoRF method improves the average PSNR from 21.45 dB (TensorRF) to 23.70 dB, with the fine tuned version reaching 24.52 dB, while maintaining TensorRF's fast \(\approx10-15\) minute training time. Experiments on the THuman 2.0 dataset further demonstrate competitive performance in human body reconstruction, achieving 27.37 - 34.00 dB with only eight input images. These results highlight Few TensoRF as an efficient and data effective solution for real-time 3D reconstruction across diverse scenes.

cs.CV↗

arXiv2026

Comparative Study of UNet-based Architectures for Liver Tumor Segmentation in Multi-Phase Contrast-Enhanced Computed Tomography

Segmentation of liver structures in multi-phase contrast-enhanced computed tomography (CECT) plays a crucial role in computer-aided diagnosis and treatment planning. In this study, we investigate the performance of UNet-based architectures for liver tumor segmentation, evaluating ResNet, Transformer-based, and State-space (Mamba) backbones initialized with pretrained weights. Our comparative analysis reveals that despite the theoretical advantages of modern architectures in modeling long-range dependencies, ResNet-based models demonstrated superior sample efficiency on this dataset. This suggests that the inherent inductive biases of Convolutional Neural Networks (CNNs) remain advantageous for generalizing on limited medical data compared to data-hungry alternatives. To further improve segmentation quality, we introduce attention mechanisms into the backbone, finding that the Convolutional Block Attention Module (CBAM) yields the optimal configuration. The ResNetUNet3+ with CBAM achieved the highest nominal performance with a Dice score of 0.755 and IoU of 0.662, while also delivering the most precise boundary delineation (lowest HD95 of 77.911). Critically, while statistical testing indicated that the improvement in mean Dice score was not significant (p > 0.05) compared to the baseline, the proposed model exhibited greater stability (lower standard deviation) and higher specificity (0.926). These findings demonstrate that classical ResNet architectures, when enhanced with modern attention modules, provide a robust and statistically comparable alternative to emerging methods, offering a stable direction for liver tumor segmentation in clinical practice.

cs.CV↗