arXiv subjects

Zexi Chen

Publications and source records attributed to Zexi Chen.

At least 19 recordsLinked to original sources

arXiv2026

RoadWeaver: Large-Scale Lane-Level HD Map Generation from Scratch for Autonomous Driving Simulation

Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks. Existing approaches either rely on handcrafted or reconstructed real-world maps, which limits scalability, or generate only local road structures rather than complete HD maps. We present RoadWeaver, a coarse-to-fine framework for from-scratch generation of diverse, large-scale HD maps. RoadWeaver first synthesizes a global road layout, expands it into a connected road network, and then constructs lane-level geometry with topologically consistent lane connectivity. Experimental results show that RoadWeaver achieves a 99.8\% reachability, a 10.7\% dead-end ratio, and an endpoint alignment error of 0.24 m. Compared with SOTA generation methods, it reduces endpoint alignment error by 94.4\% while generating complete HD maps in 1.39--3.50 s. The generated maps can be directly deployed in driving simulators, providing scalable simulation environments for future closed-loop evaluation of autonomous driving systems. The training code and an out-of-the-box implementation of RoadWeaver will be released upon acceptance.

cs.RO↗

arXiv2026

From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection

Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between visually distinct domains: open decks with sparse textures and severe illumination changes, and enclosed cabins with repetitive structures and high visual ambiguity. Existing VPR methods, designed primarily for urban or indoor scenes, fail to generalize reliably across these starkly different scenarios. To address this, we propose ProteusVPR, a two-stage retrieval-refinement framework. The first stage employs any standard VPR model for initial image retrieval. The second stage introduces a geometric-visual estimation network that fuses the retrieved image with two temporally preceding frames, incorporating geometric descriptors, a local affine coordinate system, and camera azimuth encoding to achieve precise localization. To support this task, we introduce the XHZ dataset, an 8K-panoramic ship-borne dataset collected from an operational vessel, featuring multi-floor cabin structures, deck transition zones, and strict query-database separation for rigorous evaluation. Extensive experiments on the XHZ dataset demonstrate that ProteusVPR consistently improves the localization accuracy across multiple VPR backbones, reducing mean localization error by over 60\% on average and that ProteusVPR offers an effective and robust solution for precise visual localization in challenging, cross-scene maritime environments.

cs.CV↗

arXiv2026

DOCFORGE-BENCH: A Comprehensive 0-shot Benchmark for Document Forgery Detection and Analysis

We present DOCFORGE-BENCH, the first unified zero-shot benchmark for document forgery detection, evaluating 14 methods across eight datasets spanning text tampering, receipt forgery, and identity document manipulation. Unlike fine-tuning-oriented evaluations such as ForensicHub [Du et al., 2025], DOCFORGE-BENCH applies all methods with their published pretrained weights and no domain adaptation -- a deliberate design choice that reflects the realistic deployment scenario where practitioners lack labeled document training data. Our central finding is a pervasive calibration failure invisible under single-threshold protocols: methods achieve moderate Pixel-AUC (>=0.76) yet near-zero Pixel-F1. This AUC-F1 gap is not a discrimination failure but a score-distribution shift: tampered regions occupy only 0.27-4.17% of pixels in document images -- an order of magnitude less than in natural image benchmarks -- making the standard tau=0.5 threshold catastrophically miscalibrated. Oracle-F1 is 2-10x higher than fixed-threshold Pixel-F1, confirming that calibration, not representation, is the bottleneck. A controlled calibration experiment validates this: adapting a single threshold on N=10 domain images recovers 39-55% of the Oracle-F1 gap, demonstrating that threshold adaptation -- not retraining -- is the key missing step for practical deployment. Overall, no evaluated method works reliably out-of-the-box on diverse document types, underscoring that document forgery detection remains an unsolved problem. We further note that all eight datasets predate the era of generative AI editing; benchmarks covering diffusion- and LLM-based document forgeries represent a critical open gap on the modern attack surface.

cs.CV↗

arXiv2026

Out of the box age estimation through facial imagery: A Comprehensive Benchmark of Vision-Language Models vs. out-of-the-box Traditional Architectures

Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has systematically compared modern vision-language models (VLMs) with specialized age estimation architectures. We present the first large-scale cross-paradigm benchmark, evaluating 34 models - 22 specialized architectures with publicly available pretrained weights and 12 general-purpose VLMs - across eight standard datasets (UTKFace, IMDB-WIKI, MORPH, AFAD, CACD, FG-NET, APPA-REAL, and AgeDB), totaling 1,100 test images per model. Our key finding is striking: zero-shot VLMs significantly outperform most specialized models, achieving an average mean absolute error (MAE) of 5.65 years compared to 9.88 years for non-LLM models. The best-performing VLM (Gemini 3 Flash Preview, MAE 4.32) surpasses the strongest non-LLM model (MiVOLO, MAE 5.10) by 15%. MiVOLO - unique in combining face and body features using Vision Transformers - is the only specialized model that remains competitive with VLMs. We further analyze age verification at the 18-year threshold and find that most non-LLM models exhibit false adult rates between 39% and 100% for minors, whereas VLMs reduce this to 16%-29%. Additionally, coarse age binning (8-9 classes) consistently increases MAE beyond 13 years. Stratified analysis across 14 age groups reveals that all models struggle most at extreme ages (under 5 and over 65). Overall, these findings challenge the assumption that task-specific architectures are necessary for high-performance age estimation and suggest that future work should focus on distilling VLM capabilities into efficient specialized models.

cs.CV↗

arXiv2025

Can Multi-modal (reasoning) LLMs detect document manipulation?

Document fraud poses a significant threat to industries reliant on secure and verifiable documentation, necessitating robust detection mechanisms. This study investigates the efficacy of state-of-the-art multi-modal large language models (LLMs)-including OpenAI O1, OpenAI 4o, Gemini Flash (thinking), Deepseek Janus, Grok, Llama 3.2 and 4, Qwen 2 and 2.5 VL, Mistral Pixtral, and Claude 3.5 and 3.7 Sonnet-in detecting fraudulent documents. We benchmark these models against each other and prior work on document fraud detection techniques using a standard dataset with real transactional documents. Through prompt optimization and detailed analysis of the models' reasoning processes, we evaluate their ability to identify subtle indicators of fraud, such as tampered text, misaligned formatting, and inconsistent transactional sums. Our results reveal that top-performing multi-modal LLMs demonstrate superior zero-shot generalization, outperforming conventional methods on out-of-distribution datasets, while several vision LLMs exhibit inconsistent or subpar performance. Notably, model size and advanced reasoning capabilities show limited correlation with detection accuracy, suggesting task-specific fine-tuning is critical. This study underscores the potential of multi-modal LLMs in enhancing document fraud detection systems and provides a foundation for future research into interpretable and scalable fraud mitigation strategies.

cs.CV↗

arXiv2024

Attention Mechanism and Context Modeling System for Text Mining Machine Translation

This paper advances a novel architectural schema anchored upon the Transformer paradigm and innovatively amalgamates the K-means categorization algorithm to augment the contextual apprehension capabilities of the schema. The transformer model performs well in machine translation tasks due to its parallel computing power and multi-head attention mechanism. However, it may encounter contextual ambiguity or ignore local features when dealing with highly complex language structures. To circumvent this constraint, this exposition incorporates the K-Means algorithm, which is used to stratify the lexis and idioms of the input textual matter, thereby facilitating superior identification and preservation of the local structure and contextual intelligence of the language. The advantage of this combination is that K-Means can automatically discover the topic or concept regions in the text, which may be directly related to translation quality. Consequently, the schema contrived herein enlists K-Means as a preparatory phase antecedent to the Transformer and recalibrates the multi-head attention weights to assist in the discrimination of lexis and idioms bearing analogous semantics or functionalities. This ensures the schema accords heightened regard to the contextual intelligence embodied by these clusters during the training phase, rather than merely focusing on locational intelligence.

cs.CL↗

arXiv2024

Research on Feature Extraction Data Processing System For MRI of Brain Diseases Based on Computer Deep Learning

Most of the existing wavelet image processing techniques are carried out in the form of single-scale reconstruction and multiple iterations. However, processing high-quality fMRI data presents problems such as mixed noise and excessive computation time. This project proposes the use of matrix operations by combining mixed noise elimination methods with wavelet analysis to replace traditional iterative algorithms. Functional magnetic resonance imaging (fMRI) of the auditory cortex of a single subject is analyzed and compared to the wavelet domain signal processing technology based on repeated times and the world's most influential SPM8. Experiments show that this algorithm is the fastest in computing time, and its detection effect is comparable to the traditional iterative algorithm. However, this has a higher practical value for the processing of FMRI data. In addition, the wavelet analysis method proposed signal processing to speed up the calculation rate.

eess.IV↗

arXiv2024

Research on Disease Prediction Model Construction Based on Computer AI deep Learning Technology

The prediction of disease risk factors can screen vulnerable groups for effective prevention and treatment, so as to reduce their morbidity and mortality. Machine learning has a great demand for high-quality labeling information, and labeling noise in medical big data poses a great challenge to efficient disease risk warning methods. Therefore, this project intends to study the robust learning algorithm and apply it to the early warning of infectious disease risk. A dynamic truncated loss model is proposed, which combines the traditional mutual entropy implicit weight feature with the mean variation feature. It is robust to label noise. A lower bound on training loss is constructed, and a method based on sampling rate is proposed to reduce the gradient of suspected samples to reduce the influence of noise on training results. The effectiveness of this method under different types of noise was verified by using a stroke screening data set as an example. This method enables robust learning of data containing label noise.

cs.LG↗

arXiv2024

Exploration of Attention Mechanism-Enhanced Deep Learning Models in the Mining of Medical Textual Data

The research explores the utilization of a deep learning model employing an attention mechanism in medical text mining. It targets the challenge of analyzing unstructured text information within medical data. This research seeks to enhance the model's capability to identify essential medical information by incorporating deep learning and attention mechanisms. This paper reviews the basic principles and typical model architecture of attention mechanisms and shows the effectiveness of their application in the tasks of disease prediction, drug side effect monitoring, and entity relationship extraction. Aiming at the particularity of medical texts, an adaptive attention model integrating domain knowledge is proposed, and its ability to understand medical terms and process complex contexts is optimized. The experiment verifies the model's effectiveness in improving task accuracy and robustness, especially when dealing with long text. The future research path of enhancing model interpretation, realizing cross-domain knowledge transfer, and adapting to low-resource scenarios is discussed in the research outlook, which provides a new perspective and method support for intelligent medical information processing and clinical decision assistance. Finally, cross-domain knowledge transfer and adaptation strategies for low-resource scenarios, providing theoretical basis and technical reference for promoting the development of intelligent medical information processing and clinical decision support systems.

cs.CL↗

arXiv2024

Enhancing Medical Imaging with GANs Synthesizing Realistic Images from Limited Data

In this research, we introduce an innovative method for synthesizing medical images using generative adversarial networks (GANs). Our proposed GANs method demonstrates the capability to produce realistic synthetic images even when trained on a limited quantity of real medical image data, showcasing commendable generalization prowess. To achieve this, we devised a generator and discriminator network architecture founded on deep convolutional neural networks (CNNs), leveraging the adversarial training paradigm for model optimization. Through extensive experimentation across diverse medical image datasets, our method exhibits robust performance, consistently generating synthetic images that closely emulate the structural and textural attributes of authentic medical images.

eess.IV↗

arXiv2023

Leveraging Large Language Models in Conversational Recommender Systems

A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this paradigm. However, effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of information. These issues are exacerbated by a large, evolving item corpus and a lack of conversational data for training. In this paper, we provide a roadmap for building an end-to-end large-scale CRS using LLMs. In particular, we propose new implementations for user preference understanding, flexible dialogue management and explainable recommendations as part of an integrated architecture powered by LLMs. For improved personalization, we describe how an LLM can consume interpretable natural language user profiles and use them to modulate session-level context. To overcome conversational data limitations in the absence of an existing production CRS, we propose techniques for building a controllable LLM-based user simulator to generate synthetic conversations. As a proof of concept we introduce RecLLM, a large-scale CRS for YouTube videos built on LaMDA, and demonstrate its fluency and diverse functionality through some illustrative example conversations.

cs.IR↗

arXiv2023

One RING to Rule Them All: Radon Sinogram for Place Recognition, Orientation and Translation Estimation

LiDAR-based global localization is a fundamental problem for mobile robots. It consists of two stages, place recognition and pose estimation, which yields the current orientation and translation, using only the current scan as query and a database of map scans. Inspired by the definition of a recognized place, we consider that a good global localization solution should keep the pose estimation accuracy with a lower place density. Following this idea, we propose a novel framework towards sparse place-based global localization, which utilizes a unified and learning-free representation, Radon sinogram (RING), for all sub-tasks. Based on the theoretical derivation, a translation invariant descriptor and an orientation invariant metric are proposed for place recognition, achieving certifiable robustness against arbitrary orientation and large translation between query and map scan. In addition, we also utilize the property of RING to propose a global convergent solver for both orientation and translation estimation, arriving at global localization. Evaluation of the proposed RING based framework validates the feasibility and demonstrates a superior performance even under a lower place density.

cs.RO↗

arXiv2022

Learning Interpretable BEV Based VIO without Deep Neural Networks

Monocular visual-inertial odometry (VIO) is a critical problem in robotics and autonomous driving. Traditional methods solve this problem based on filtering or optimization. While being fully interpretable, they rely on manual interference and empirical parameter tuning. On the other hand, learning-based approaches allow for end-to-end training but require a large number of training data to learn millions of parameters. However, the non-interpretable and heavy models hinder the generalization ability. In this paper, we propose a fully differentiable, and interpretable, bird-eye-view (BEV) based VIO model for robots with local planar motion that can be trained without deep neural networks. Specifically, we first adopt Unscented Kalman Filter as a differentiable layer to predict the pitch and roll, where the covariance matrices of noise are learned to filter out the noise of the IMU raw data. Second, the refined pitch and roll are adopted to retrieve a gravity-aligned BEV image of each frame using differentiable camera projection. Finally, a differentiable pose estimator is utilized to estimate the remaining 3 DoF poses between the BEV frames: leading to a 5 DoF pose estimation. Our method allows for learning the covariance matrices end-to-end supervised by the pose estimation loss, demonstrating superior performance to empirical baselines. Experimental results on synthetic and real-world datasets demonstrate that our simple approach is competitive with state-of-the-art methods and generalizes well on unseen scenes.

cs.RO↗

arXiv2022

DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration

Pose registration is critical in vision and robotics. This paper focuses on the challenging task of initialization-free pose registration up to 7DoF for homogeneous and heterogeneous measurements. While recent learning-based methods show promise using differentiable solvers, they either rely on heuristically defined correspondences or are prone to local minima. We present a differentiable phase correlation (DPC) solver that is globally convergent and correspondence-free. When combined with simple feature extraction networks, our general framework DPCN++ allows for versatile pose registration with arbitrary initialization. Specifically, the feature extraction networks first learn dense feature grids from a pair of homogeneous/heterogeneous measurements. These feature grids are then transformed into a translation and scale invariant spectrum representation based on Fourier transform and spherical radial aggregation, decoupling translation and scale from rotation. Next, the rotation, scale, and translation are independently and efficiently estimated in the spectrum step-by-step using the DPC solver. The entire pipeline is differentiable and trained end-to-end. We evaluate DCPN++ on a wide range of registration tasks taking different input modalities, including 2D bird's-eye view images, 3D object and scene measurements, and medical images. Experimental results demonstrate that DCPN++ outperforms both classical and learning-based baselines, especially on partially observed and heterogeneous measurements.

cs.CV↗

arXiv2022

Depth-Independent Depth Completion via Least Square Estimation

The depth completion task aims to complete a per-pixel dense depth map from a sparse depth map. In this paper, we propose an efficient least square based depth-independent method to complete the sparse depth map utilizing the RGB image and the sparse depth map in two independent stages. In this way can we decouple the neural network and the sparse depth input, so that when some features of the sparse depth map change, such as the sparsity, our method can still produce a promising result. Moreover, due to the positional encoding and linear procession in our pipeline, we can easily produce a super-resolution dense depth map of high quality. We also test the generalization of our method on different datasets compared to some state-of-the-art algorithms. Experiments on the benchmark show that our method produces competitive performance.

cs.CV↗

arXiv2022

Kinematic Motion Retargeting via Neural Latent Optimization for Learning Sign Language

Motion retargeting from a human demonstration to a robot is an effective way to reduce the professional requirements and workload of robot programming, but faces the challenges resulting from the differences between humans and robots. Traditional optimization-based methods are time-consuming and rely heavily on good initialization, while recent studies using feedforward neural networks suffer from poor generalization to unseen motions. Moreover, they neglect the topological information in human skeletons and robot structures. In this paper, we propose a novel neural latent optimization approach to address these problems. Latent optimization utilizes a decoder to establish a mapping between the latent space and the robot motion space. Afterward, the retargeting results that satisfy robot constraints can be obtained by searching for the optimal latent vector. Alongside with latent optimization, neural initialization exploits an encoder to provide a better initialization for faster and better convergence of optimization. Both the human skeleton and the robot structure are modeled as graphs to make better use of topological information. We perform experiments on retargeting Chinese sign language, which involves two arms and two hands, with additional requirements on the relative relationships among joints. Experiments include retargeting various human demonstrations to YuMi, NAO, and Pepper in the simulation environment and to YuMi in the real-world environment. Both efficiency and accuracy of the proposed method are verified.

cs.RO↗

arXiv2021

Domain Generalization for Vision-based Driving Trajectory Generation

One of the challenges in vision-based driving trajectory generation is dealing with out-of-distribution scenarios. In this paper, we propose a domain generalization method for vision-based driving trajectory generation for autonomous vehicles in urban environments, which can be seen as a solution to extend the Invariant Risk Minimization (IRM) method in complex problems. We leverage an adversarial learning approach to train a trajectory generator as the decoder. Based on the pre-trained decoder, we infer the latent variables corresponding to the trajectories, and pre-train the encoder by regressing the inferred latent variable. Finally, we fix the decoder but fine-tune the encoder with the final trajectory loss. We compare our proposed method with the state-of-the-art trajectory generation method and some recent domain generalization methods on both datasets and simulation, demonstrating that our method has better generalization ability.

cs.CV↗

arXiv2021

Learn to Differ: Sim2Real Small Defection Segmentation Network

Recent studies on deep-learning-based small defection segmentation approaches are trained in specific settings and tend to be limited by fixed context. Throughout the training, the network inevitably learns the representation of the background of the training data before figuring out the defection. They underperform in the inference stage once the context changed and can only be solved by training in every new setting. This eventually leads to the limitation in practical robotic applications where contexts keep varying. To cope with this, instead of training a network context by context and hoping it to generalize, why not stop misleading it with any limited context and start training it with pure simulation? In this paper, we propose the network SSDS that learns a way of distinguishing small defections between two images regardless of the context, so that the network can be trained once for all. A small defection detection layer utilizing the pose sensitivity of phase correlation between images is introduced and is followed by an outlier masking layer. The network is trained on randomly generated simulated data with simple shapes and is generalized across the real world. Finally, SSDS is validated on real-world collected data and demonstrates the ability that even when trained in cheap simulation, SSDS can still find small defections in the real world showing the effectiveness and its potential for practical applications.

cs.CV↗