arXiv subjects

Tuan Anh Tran

Publications and source records attributed to Tuan Anh Tran.

7 recordsLinked to original sources

arXiv2026

A Hybrid Vision Transformer Approach for Mathematical Expression Recognition

One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated problem because of its two-dimensional structure and different symbol size. In this paper, we propose using a Hybrid Vision Transformer (HVT) with 2D positional encoding as the encoder to extract the complex relationship between symbols from the image. A coverage attention decoder is used to better track attention's history to handle the under-parsing and over-parsing problems. We also showed the benefit of using the [CLS] token of ViT as the initial embedding of the decoder. Experiments performed on the IM2LATEX-100K dataset have shown the effectiveness of our method by achieving a BLEU score of 89.94 and outperforming current state-of-the-art methods.

cs.CV↗

arXiv2026

Facial Expression Recognition Using Residual Masking Network

Automatic facial expression recognition (FER) has gained much attention due to its applications in human-computer interaction. Among the approaches to improve FER tasks, this paper focuses on deep architecture with the attention mechanism. We propose a novel Masking idea to boost the performance of CNN in facial expression task. It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions. In experiments, we combine the ubiquitous Deep Residual Network and Unet-like architecture to produce a Residual Masking Network. The proposed method holds state-of-the-art (SOTA) accuracy on the well-known FER2013 and private VEMO datasets. The source code is available at https://github.com/phamquiluan/ResidualMaskingNetwork.

cs.CV↗

arXiv2026

Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation

Skew estimation is one of the vital tasks in document processing systems, especially for scanned document images, because its performance impacts subsequent steps directly. Over the years, an enormous number of researches focus on this challenging problem in the rise of digitization age. In this research, we first propose a novel skew estimation method that extracts the dominant skew angle of the given document image by applying an Adaptive Radial Projection on the 2D Discrete Fourier Magnitude spectrum. Second, we introduce a high quality skew estimation dataset DISE-2021 to assess the performance of different estimators. Finally, we provide comprehensive analyses that focus on multiple improvement aspects of Fourier-based methods. Our results show that the proposed method is robust, reliable, and outperforms all compared methods. The source code is available at https://github.com/phamquiluan/jdeskew.

cs.CV↗

arXiv2025

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely on dense token representations, incurring high computational and memory costs during training and inference. In this work, we present the finding that tokens are remarkably redundant, leading to substantial inefficiency. We introduce gitmerge3D, a globally informed graph token merging method that can reduce the token count by up to 90-95% while maintaining competitive performance. This finding challenges the prevailing assumption that more tokens inherently yield better performance and highlights that many current models are over-tokenized and under-optimized for scalability. We validate our method across multiple 3D vision tasks and show consistent improvements in computational efficiency. This work is the first to assess redundancy in large-scale 3D transformer models, providing insights into the development of more efficient 3D foundation architectures. Our code and checkpoints are publicly available at https://gitmerge3d.github.io

cs.CV↗

arXiv2023

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which are notoriously laborious to annotate. Few attempts have been made to circumvent the need for dense per-point annotations. In this work, we look at weakly-supervised 3D semantic instance segmentation. The key idea is to leverage 3D bounding box labels which are easier and faster to annotate. Indeed, we show that it is possible to train dense segmentation models using only bounding box labels. At the core of our method, \name{}, lies a deep model, inspired by classical Hough voting, that directly votes for bounding box parameters, and a clustering method specifically tailored to bounding box votes. This goes beyond commonly used center votes, which would not fully exploit the bounding box annotations. On ScanNet test, our weakly supervised model attains leading performance among other weakly supervised approaches (+18 mAP@50). Remarkably, it also achieves 97% of the mAP@50 score of current fully supervised models. To further illustrate the practicality of our work, we train Box2Mask on the recently released ARKitScenes dataset which is annotated with 3D bounding boxes only, and show, for the first time, compelling 3D instance segmentation masks.

cs.CV↗

arXiv2023

PaaS: Planning as a Service for reactive driving in CARLA Leaderboard

End-to-end deep learning approaches has been proven to be efficient in autonomous driving and robotics. By using deep learning techniques for decision-making, those systems are often referred to as a black box, and the result is driven by data. In this paper, we propose PaaS (Planning as a Service), a vanilla module to generate local trajectory planning for autonomous driving in CARLA simulation. Our method is submitted in International CARLA Autonomous Driving Leaderboard (CADL), which is a platform to evaluate the driving proficiency of autonomous agents in realistic traffic scenarios. Our approach focuses on reactive planning in Frenet frame under complex urban street's constraints and driver's comfort. The planner generates a collection of feasible trajectories, leveraging heuristic cost functions with controllable driving style factor to choose the optimal-control path that satisfies safe travelling criteria. PaaS can provide sufficient solutions to handle well under challenging traffic situations in CADL. As the strict evaluation in CADL Map Track, our approach ranked 3rd out of 9 submissions regarding the measure of driving score. However, with the focus on minimizing the risk of maneuver and ensuring passenger safety, our figures corresponding to infraction penalty dominate the two leading submissions for 20 percent.

cs.RO↗

arXiv2022

Incommensurate antiferromagnetic order in weakly frustrated two-dimensional van der Waals insulator CrPSe$_3$

Although the magnetic order is suppressed by a strong magnetic frustration, it is maintained but appears in complex order forms such as a cycloid or spin density wave in weakly frustrated systems. Herein, we report a weakly magnetic-frustrated two-dimensional van der Waals material CrPSe$_3$. Polycrystalline CrPSe$_3$ was synthesized at an optimized temperature of 700$^\circ$C to avoid the formation of any secondary phases (e.g., Cr$_2$Se$_3$). The antiferromagnetic transition appeared at $T_N\sim 126$ K with a large Curie-Weiss temperature $T_{\rm CW} \sim -371$ via magnetic susceptibility measurements, indicating weak frustration in CrPSe$_3$ with a frustration factor $f (|T_{\rm CW}|/T_N) \sim 3$. Evidently, the formation of long-range incommensurate spin-density wave antiferromagnetic order with the propagation vector $k = (0, 0.04, 0)$ was revealed by neutron diffraction measurements at low temperatures (below 120K). The monoclinic crystal structure of C2/m symmetry is preserved over the studied temperature range down to 20K, as confirmed by Raman spectroscopy measurements. Our findings on the spin density wave antiferromagnetic order in two-dimensional (2D) magnetic materials, not previously observed in the MPX$_3$ family, are expected to enrich the physics of magnetism at the 2D limit, thereby opening opportunities for their practical applications in spintronics and quantum devices.

cond-mat.mtrl-sci↗