Searcharxiv⌕ Search

arXiv subjects

Xiao Wang

Publications and source records attributed to Xiao Wang.

At least 199 records · Page 11Linked to original sources
arXiv2025

Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline

Sign Language Translation (SLT) is a core task in the field of AI-assisted disability. Traditional SLT methods are typically based on visible light videos, which are easily affected by factors such as lighting variations, rapid hand movements, and privacy concerns. This paper proposes the use of bio-inspired event cameras to alleviate the aforementioned issues. Specifically, we introduce a new high-definition event-based sign language dataset, termed Event-CSL, which effectively addresses the data scarcity in this research area. The dataset comprises 14,827 videos, 14,821 glosses, and 2,544 Chinese words in the text vocabulary. These samples are collected across diverse indoor and outdoor scenes, covering multiple viewpoints, lighting conditions, and camera motions. We have also benchmarked existing mainstream SLT methods on this dataset to facilitate fair comparisons in future research.Furthermore, we propose a novel event-based sign language translation framework, termed EvSLT. The framework first segments continuous video features into clips and employs a Mamba-based memory aggregation module to compress and aggregate spatial detail features at the clip level. Subsequently, these spatial features, along with temporal representations obtained from temporal convolution, are then fused by a graph-guided spatiotemporal fusion module. Extensive experiments on Event-CSL, as well as other publicly available datasets, demonstrate the superior performance of our method. The dataset and source code will be released on https://github.com/Event-AHU/OpenESL

cs.CV↗
arXiv2025

SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning

Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote sensing images captured at different times. Existing methods typically employ CNNs/Transformers to extract visual representations from the given images or incorporate auxiliary tasks to enhance the final results, with weak region awareness and limited temporal alignment. To address these issues, this paper explores the use of the SAM (Segment Anything Model) foundation model to extract region-level representations and inject region-of-interest knowledge into the captioning framework. Specifically, we employ a CNN/Transformer model to extract global-level vision features, leverage the SAM foundation model to delineate semantic- and motion-level change regions, and utilize a specially constructed knowledge graph to provide information about objects of interest. These heterogeneous sources of information are then fused via cross-attention, and a Transformer decoder is used to generate the final natural language description of the observed changes. Extensive experimental results demonstrate that our method achieves state-of-the-art performance across multiple widely used benchmark datasets. The source code of this paper will be released on https://github.com/Event-AHU/SAM_ChangeCaptioning

cs.CV↗
arXiv2025

EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation

Event cameras produce asynchronous event streams that are spatially sparse yet temporally dense. Mainstream event representation learning algorithms typically use event frames, voxels, or tensors as input. Although these approaches have achieved notable progress, they struggle to address the undersampling problem caused by spatial sparsity. In this paper, we propose a novel hypergraph-guided spatio-temporal event stream completion mechanism, which connects event tokens across different times and spatial locations via hypergraphs and leverages contextual information message passing to complete these sparse events. The proposed method can flexibly incorporate RGB tokens as nodes in the hypergraph within this completion framework, enabling multi-modal hypergraph-based information completion. Subsequently, we aggregate hypergraph node information across different time steps through self-attention, enabling effective learning and fusion of multi-modal features. Extensive experiments on both single- and multi-label event classification tasks fully validated the effectiveness of our proposed framework. The source code of this paper will be released on https://github.com/Event-AHU/EvRainDrop.

cs.CV↗
arXiv2025

DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models

The precise reading recognition of pointer meters plays a key role in smart power systems, but existing approaches remain fragile due to challenges like reflections, occlusions, dynamic viewing angles, and overly between thin pointers and scale markings. Up to now, this area still lacks large-scale datasets to support the development of robust algorithms. To address these challenges, this paper first presents a new large-scale benchmark dataset for dial reading, termed RPM-10K, which contains 10730 meter images that fully reflect the aforementioned key challenges. Built upon the dataset, we propose a novel vision-language model for pointer meter reading recognition, termed MRLM, based on physical relation injection. Instead of exhaustively learning image-level correlations, MRLM explicitly encodes the geometric and causal relationships between the pointer and the scale, aligning perception with physical reasoning in the spirit of world-model perspectives. Through cross-attentional fusion and adaptive expert selection, the model learns to interpret dial configurations and generate precise numeric readings. Extensive experiments fully validated the effectiveness of our proposed framework on the newly proposed benchmark dataset. Both the dataset and source code will be released on https://github.com/Event-AHU/DialBench

cs.CV↗
arXiv2025

ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation

Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of large language models (LLMs) as source-based metrics for natural language generation (NLG) assessment. While promising, LLM-based metrics, particularly those using smaller models, still fall short in aligning with human judgments. In this work, we introduce ContrastScore, a contrastive evaluation metric designed to enable higher-quality, less biased, and more efficient assessment of generated text. We evaluate ContrastScore on two NLG tasks: machine translation and summarization. Experimental results show that ContrastScore consistently achieves stronger correlation with human judgments than both single-model and ensemble-based baselines. Notably, ContrastScore based on Qwen 3B and 0.5B even outperforms Qwen 7B, despite having only half as many parameters, demonstrating its efficiency. Furthermore, it effectively mitigates common evaluation biases such as length and likelihood preferences, resulting in more robust automatic evaluation.

cs.CL↗
arXiv2025

Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning

Recently, fine-tuning large-scale pre-trained GNNs has yielded remarkable attention in adapting pre-trained GNN models for downstream graph learning tasks. One representative fine-tuning method is to exploit adapter (termed AdapterGNN) which aims to 'augment' the pre-trained model by inserting a lightweight module to make the 'augmented' model better adapt to the downstream tasks. However, graph data may contain various types of noise in downstream tasks, such as noisy edges and ambiguous node attributes. Existing AdapterGNNs are often prone to graph noise and exhibit limited generalizability. How to enhance the robustness and generalization ability of GNNs' fine tuning remains an open problem. In this paper, we show that the above problem can be well addressed by integrating uncertainty learning into the GNN adapter. We propose the Uncertainty-aware Adapter (UAdapterGNN) that fortifies pre-trained GNN models against noisy graph data in the fine-tuning process. Specifically, in contrast to regular AdapterGNN, our UAdapterGNN exploits Gaussian probabilistic adapter to augment the pre-trained GNN model. In this way, when the graph contains various noises,our method can automatically absorb the effects of changes in the variances of the Gaussian distribution, thereby significantly enhancing the model's robustness. Also, UAdapterGNN can further improve the generalization ability of the model on the downstream tasks. Extensive experiments on several benchmarks demonstrate the effectiveness, robustness and high generalization ability of the proposed UAdapterGNN method.

cs.LG↗
arXiv2025

Unsupervised Motion-Compensated Decomposition for Cardiac MRI Reconstruction via Neural Representation

Cardiac magnetic resonance (CMR) imaging is widely used to characterize cardiac morphology and function. To accelerate CMR imaging, various methods have been proposed to recover high-quality spatiotemporal CMR images from highly undersampled k-t space data. However, current CMR reconstruction techniques either fail to achieve satisfactory image quality or are restricted by the scarcity of ground truth data, leading to limited applicability in clinical scenarios. In this work, we proposed MoCo-INR, a new unsupervised method that integrates implicit neural representations (INR) with the conventional motion-compensated (MoCo) framework. Using explicit motion modeling and the continuous prior of INRs, MoCo-INR can produce accurate cardiac motion decomposition and high-quality CMR reconstruction. Furthermore, we introduce a new INR network architecture tailored to the CMR problem, which significantly stabilizes model optimization. Experiments on retrospective (simulated) datasets demonstrate the superiority of MoCo-INR over state-of-the-art methods, achieving fast convergence and fine-detailed reconstructions at ultra-high acceleration factors (e.g., 20x in VISTA sampling). Additionally, evaluations on prospective (real-acquired) free-breathing CMR scans highlight the clinical practicality of MoCo-INR for real-time imaging. Several ablation studies further confirm the effectiveness of the critical components of MoCo-INR.

eess.IV↗
arXiv2025

Numerical renormalization group integrated Hamiltonian truncation: Toward generic deformation of integrable lattice models

We present a hybrid lattice Hamiltonian truncation method that integrates the numerical renormalization group (NRG) with a truncated lattice integrable spectrum. The technique is tailored for generic deformations of integrable lattice models, where the NRG enables a controlled incorporation of high-energy states. The method extends the basis set more effectively and efficiently than brute-force truncation, meanwhile significantly reducing errors. We show its capability on two paradigmatic models: an Ising chain in a magnetic field and a quantum Ising ladder. The resulting dynamical structure factors accurately capture the essential low-energy physics, including the $E_8$ and $\mathcal{D}_8^{(1)}$ excitations of the former and later models, respectively, demonstrating the approach's computational efficiency and high performance.

cond-mat.str-el↗
arXiv2025

Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection

The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard self-supervised methods capture generic features and remain vulnerable to domain shift. We propose \ours, a self-supervised framework that \emph{visually probes} target domains without labels. \ours introduces a Self-supervised Prompt Enhancement Module (SPEM), which derives defect-aware prompts from unlabeled target data to guide a frozen ViT backbone, and a Domain-Aware Prompt Alignment (DAPA) objective, which aligns prompt-conditioned source and target representations. Experiments on four challenging benchmarks show that \ours consistently outperforms strong supervised, self-supervised, and adaptation baselines, achieving robust zero-shot transfer, improved resilience to domain variations, and high data efficiency in few-shot adaptation. These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems. Source code is publicly available: https://github.com/xixiaouab/PROBE/tree/main

cs.CV↗
arXiv2025

Foundation Model in Biomedicine

Foundation models, first introduced in 2021, refer to large-scale pretrained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive unlabeled datasets through unsupervised methods, enabling them to excel in diverse downstream tasks. These models, like GPT, can be adapted to various applications such as question answering and visual understanding, outperforming task-specific AI models and earning their name due to broad applicability across fields. The development of biomedical foundation models marks a significant milestone in the use of artificial intelligence (AI) to understand complex biological phenomena and advance medical research and practice. This survey explores the potential of foundation models in diverse domains within biomedical fields, including computational biology, drug discovery and development, clinical informatics, medical imaging, and public health. The purpose of this survey is to inspire ongoing research in the application of foundation models to health science.

cs.LG↗
arXiv2025

CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in disentanglement is often unrealistic when target and sensitive factors are naturally correlated. To address this challenge, we propose \textbf{CAD-VAE} (\textbf{C}orrelation-\textbf{A}ware \textbf{D}isentangled \textbf{VAE}), which introduces a correlated latent code to capture the information shared between the target and sensitive attributes. Given this correlated latent, our method effectively separates overlapping factors without extra domain knowledge by directly minimizing the conditional mutual information between target and sensitive codes. A relevance-driven optimization strategy refines the correlated code by efficiently capturing essential correlated features and eliminating redundancy. Extensive experiments on benchmark datasets demonstrate that CAD-VAE produces fairer representations, realistic counterfactuals, and improved fairness-aware image editing. Source code is available : https://github.com/merry7cherry/CAD-VAE

cs.LG↗
arXiv2025

Learning Straight Flows: Variational Flow Matching for Efficient Generation

Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent interpolant intersections or introducing consistency and mean-velocity modeling to promote straight trajectory learning. However, these approaches often suffer from discrete approximation errors, training instability, and convergence difficulties. To tackle these issues, in the present work, we propose \textbf{S}traight \textbf{V}ariational \textbf{F}low \textbf{M}atching (\textbf{S-VFM}), which integrates a variational latent code representing the ``generation overview'' into the Flow Matching framework. \textbf{S-VFM} explicitly enforces trajectory straightness, ideally producing linear generation paths. The proposed method achieves competitive performance across three challenge benchmarks and demonstrates advantages in both training and inference efficiency compared with existing methods.

cs.LG↗
arXiv2025

Fundamentals of cubic skein modules

Over the past thirty-seven years, the study of linear and quadratic skein modules has produced a rich and far-reaching skein theory, intricately connected to diverse areas of mathematics and physics, including algebraic geometry, hyperbolic geometry, topological quantum field theories, and statistical mechanics. However, despite these advances, skein modules of higher degree-those depending on more parameters than the linear and quadratic cases-have received comparatively little attention, with only a few isolated explorations appearing in the literature. In this article, we undertake a systematic study of the cubic skein module, the first representative of this broader class. We begin by investigating its structure and properties in the $3$-sphere, and then extend the analysis to arbitrary $3$-manifolds. The results presented here aim to establish a foundational framework for the study of higher skein modules, thereby extending the scope of skein theory beyond its classical domains. Furthermore, studying the structure of cubic skein modules may lead to new polynomial invariants of knots.

math.GT↗
arXiv2025

Berry connection and quantum geometry in time-dependent systems with instantaneous quantum integrable field theory

We study many-body quantum geometric effects in time-dependent system with emergent quantum integrable field theory instantaneously. We establish a theorem stating that the Berry connection matrix thus all associated geometric quantities of the system can be precisely characterized by excitations up to two particles from the initial quantum integrable system. To illustrate the many-body geometric influence, we analyze an Ising chain subjected to both a small longitudinal field and a slowly rotating transverse field, whose low-energy physics in the scaling limit is instantaneously governed by the quantum $E_8$ integrable field theory. Focusing on the quantum geometric potential (QGP), we show the QGP continuously suppresses the instantaneous energy gaps with decreasing longitudinal field, thereby enhancing many-body Landau-Zener tunneling as evidenced by the Loschmidt echo and its associated spectral entropy. The critical threshold for the longitudinal field strength is determined,where the spectral entropy linearly increases with system size and exhibits hyperscaling behavior when approaching to the threshold. As the longitudinal field passes the threshold and decreases toward zero, the QGP continuously leads to vanishing instantaneous energy gaps involving more low-energy excitations, resulting in increasing spectral entropy indicative of many-body Landau-Zener tunneling. Our results unveil telltale quantum geometric signatures in time-dependent many-body systems, elucidating the intricate interplay between quantum geometry and dynamics.

cond-mat.str-el↗
arXiv2025

DeepAndes: A Self-Supervised Vision Foundation Model for Multi-Spectral Remote Sensing Imagery of the Andes

By mapping sites at large scales using remotely sensed data, archaeologists can generate unique insights into long-term demographic trends, inter-regional social networks, and past adaptations to climate change. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. While recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multi-spectral satellite imagery, such as the 8-band data used in our study. In this paper, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multi-spectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for 8-band multi-spectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pre-trained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pre-training in archaeological remote sensing. Codes will be available on https://github.com/geopacha/DeepAndes.

cs.CV↗
arXiv2025

When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework

Recent researchers have proposed using event cameras for person re-identification (ReID) due to their promising performance and better balance in terms of privacy protection, event camera-based person ReID has attracted significant attention. Currently, mainstream event-based person ReID algorithms primarily focus on fusing visible light and event stream, as well as preserving privacy. Although significant progress has been made, these methods are typically trained and evaluated on small-scale or simulated event camera datasets, making it difficult to assess their real identification performance and generalization ability. To address the issue of data scarcity, this paper introduces a large-scale RGB-event based person ReID dataset, called EvReID. The dataset contains 118,988 image pairs and covers 1200 pedestrian identities, with data collected across multiple seasons, scenes, and lighting conditions. We also evaluate 15 state-of-the-art person ReID algorithms, laying a solid foundation for future research in terms of both data and benchmarking. Based on our newly constructed dataset, this paper further proposes a pedestrian attribute-guided contrastive learning framework to enhance feature learning for person re-identification, termed TriPro-ReID. This framework not only effectively explores the visual features from both RGB frames and event streams, but also fully utilizes pedestrian attributes as mid-level semantic features. Extensive experiments on the EvReID dataset and MARS datasets fully validated the effectiveness of our proposed RGB-Event person ReID framework. The benchmark dataset and source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID

cs.CV↗
arXiv2025

Adaptive directional decomposition methods for nonconvex constrained optimization

In this paper, we study nonconvex constrained optimization problems with both equality and inequality constraints, covering deterministic and stochastic settings. We propose a novel first-order algorithm framework that employs a decomposition strategy to balance objective reduction and constraint satisfaction, together with adaptive update of stepsizes and merit parameters. Under certain conditions, the proposed adaptive directional decomposition methods attain an iteration complexity of order \(O(ε^{-2})\) for finding an \(ε\)-KKT point in the deterministic setting. In the stochastic setting, we further develop stochastic variants of approaches and analyze their theoretical properties by leveraging the perturbation theory. We establish the high-probability oracle complexity to find an $ε$-KKT point of order \( \tilde O(ε^{-4}, ε^{-6}) \) (resp. \(\tilde O(ε^{-3}, ε^{-5}) \)) for gradient and constraint evaluations, in the absence (resp. presence) of sample-wise smoothness. To the best of our knowledge, the obtained complexity bounds are comparable to, or improve upon, the state-of-the-art results in the literature.

math.OC↗