arXiv subjects

Lin Mei

Publications and source records attributed to Lin Mei.

12 recordsLinked to original sources

arXiv2026

Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport process instead of static projection and propose the Optimal Transport Flow Concept Bottleneck Model (OTF-CBM). It first learns a data-driven semantic cost via Inverse Optimal Transport to measure cross-modal distances, and then performs unbalanced optimal-transport-based flow matching to model semantic transitions between visual patches and textual concepts. With velocity-based concept activation, OTF-CBM captures interpretable geometric relations without ODE integration. Experiments further show that OTF-CBM achieves superior classification accuracy and concept faithfulness, offering a new geometric and dynamical perspective for interpretable cross-modal reasoning.

cs.CV↗

arXiv2026

SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition

Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings within a shared latent space. However, the absence of contextual cues, such as objects involved in the action, introduces an inherent gap between skeleton and semantic representations, making it difficult to distinguish visually similar actions. To address this, we propose SkeletonContext, a prompt-based framework that enriches skeletal motion representations with language-driven contextual semantics. Specifically, we introduce a Cross-Modal Context Prompt Module, which leverages a pretrained language model to reconstruct masked contextual prompts under guidance derived from LLMs. This design effectively transfers linguistic context to the skeleton encoder for instance-level semantic grounding and improved cross-modal alignment. In addition, a Key-Part Decoupling Module is incorporated to decouple motion-relevant joint features, ensuring robust action understanding even in the absence of explicit object interactions. Extensive experiments on multiple benchmarks demonstrate that SkeletonContext achieves state-of-the-art performance under both conventional and generalized zero-shot settings, validating its effectiveness in reasoning about context and distinguishing fine-grained, visually similar actions.

cs.CV↗

arXiv2025

Multi-Granularity Mutual Refinement Network for Zero-Shot Learning

Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.

cs.CV↗

arXiv2025

Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning

Clinical adoption of multi-shot diffusion-weighted magnetic resonance imaging (multi-shot DWI) for body-wide tumor diagnostics is limited by severe motion-induced phase artifacts from respiration, peristalsis, and so on, compounded by multi-organ, multi-slice, multi-direction and multi-b-value complexities. Here, we introduce a reconstruction framework, LoSP-Prompt, that overcomes these challenges through physics-informed modeling and synthetic-data-driven prompt learning. We model inter-shot phase variations as a high-order Locally Smooth Phase (LoSP), integrated into a low-rank Hankel matrix reconstruction. Crucially, the algorithm's rank parameter is automatically set via prompt learning trained exclusively on synthetic abdominal DWI data emulating physiological motion. Validated across 10,000+ clinical images (43 subjects, 4 scanner models, 5 centers), LoSP-Prompt: (1) Achieved twice the spatial resolution of clinical single-shot DWI, enhancing liver lesion conspicuity; (2) Generalized to seven diverse anatomical regions (liver, kidney, sacroiliac, pelvis, knee, spinal cord, brain) with a single model; (3) Outperformed state-of-the-art methods in image quality, artifact suppression, and noise reduction (11 radiologists' evaluations on a 5-point scale, $p<0.05$), achieving 4-5 points (excellent) on kidney DWI, 4 points (good to excellent) on liver, sacroiliac and spinal cord DWI, and 3-4 points (good) on knee and tumor brain. The approach eliminates navigator signals and realistic data supervision, providing an interpretable, robust solution for high-resolution multi-organ multi-shot DWI. Its scanner-agnostic performance signifies transformative potential for precision oncology.

cs.CV↗

arXiv2025

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images

Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless, real-world data are obviously more valuable comparing to artificially intelligence generated data, particularly in constructing image datasets. For this reason, we propose a novel method for auto-constructing datasets from real-world images by a multiagent collaborative system, named as DatasetAgent. By coordinating four different agents equipped with Multi-modal Large Language Models (MLLMs), as well as a tool package for image optimization, DatasetAgent is able to construct high-quality image datasets according to user-specified requirements. In particular, two types of experiments are conducted, including expanding existing datasets and creating new ones from scratch, on a variety of open-source datasets. In both cases, multiple image datasets constructed by DatasetAgent are used to train various vision models for image classification, object detection, and image segmentation.

cs.CV↗

arXiv2025

Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most lack effective interventions or only operate at sample-level without modifying the model itself. To address this, we propose the Concept Bottleneck Model for Enhancing Human-Neural Network Mutual Understanding (CBM-HNMU). CBM-HNMU leverages the Concept Bottleneck Model (CBM) as an interpretable framework to approximate black-box reasoning and communicate conceptual understanding. Detrimental concepts are automatically identified and refined (removed/replaced) based on global gradient contributions. The modified CBM then distills corrected knowledge back into the black-box model, enhancing both interpretability and accuracy. We evaluate CBM-HNMU on various CNN and transformer-based models across Flower-102, CIFAR-10, CIFAR-100, FGVC-Aircraft, and CUB-200, achieving a maximum accuracy improvement of 2.64% and a maximum increase in average accuracy across 1.03%. Source code is available at: https://github.com/XiGuaBo/CBM-HNMU.

cs.CV↗

arXiv2024

DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing

Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.

cs.CV↗

arXiv2024

Formation and Evolution of Transient Prominence Bubbles Driven by Erupting Mini-filaments

Prominence bubbles, the dark arch-shaped "voids" below quiescent prominences, are generally believed to be caused by the interaction between the prominences and the slowly-emerging or quasi-stable underlying magnetic loops. However, this scenario could not explain some short-lived bubbles with extremely dynamic properties of evolution. Based on high-resolution H$\alpha$ observations, here we propose that bubbles should be classified into two categories according to their dynamic properties: quasi-steady (Type-I) bubbles and transient (Type-II) bubbles. Type-I bubbles could remain relatively stable and last for several hours, indicating the existence of a quasi-stable magnetic topology, while Type-II bubbles grow and collapse quickly within one hour without stability duration, which are usually associated with erupting mini-filaments. Analysis of several typical Type-II bubbles from different views, especially including an on-disk event, reveals that Type-II bubbles quickly appear and expand at a velocity of $\thicksim$5--25 km s$^{-1}$ accompanied by an erupting mini-filament below. The mini-filament's rising velocity is slightly larger than that of the Type-II bubbles' boundary, which will lead to the collision with each other in a short time, subsequent collapse of Type-II bubbles, and formation of a large plume into the above prominence. We also speculate that only if the angle between the axis of the erupting mini-filament and the line-of-sight is large enough, the interaction between the erupting mini-filament and the overlying prominence could trigger a Type-II bubble with a typical arch-shaped but quickly-expanding bright boundary.

astro-ph.SR↗

arXiv2023

Long-term Effects of Temperature Variations on Economic Growth: A Machine Learning Approach

This study investigates the long-term effects of temperature variations on economic growth using a data-driven approach. Leveraging machine learning techniques, we analyze global land surface temperature data from Berkeley Earth and economic indicators, including GDP and population data, from the World Bank. Our analysis reveals a significant relationship between average temperature and GDP growth, suggesting that climate variations can substantially impact economic performance. This research underscores the importance of incorporating climate factors into economic planning and policymaking, and it demonstrates the utility of machine learning in uncovering complex relationships in climate-economy studies.

econ.GN↗

arXiv2021

A Systematic Collection of Medical Image Datasets for Deep Learning

The astounding success made by artificial intelligence (AI) in healthcare and other fields proves that AI can achieve human-like performance. However, success always comes with challenges. Deep learning algorithms are data-dependent and require large datasets for training. The lack of data in the medical imaging field creates a bottleneck for the application of deep learning to medical image analysis. Medical image acquisition, annotation, and analysis are costly, and their usage is constrained by ethical restrictions. They also require many resources, such as human expertise and funding. That makes it difficult for non-medical researchers to have access to useful and large medical data. Thus, as comprehensive as possible, this paper provides a collection of medical image datasets with their associated challenges for deep learning research. We have collected information of around three hundred datasets and challenges mainly reported between 2013 and 2020 and categorized them into four categories: head & neck, chest & abdomen, pathology & blood, and ``others''. Our paper has three purposes: 1) to provide a most up to date and complete list that can be used as a universal reference to easily find the datasets for clinical image analysis, 2) to guide researchers on the methodology to test and evaluate their methods' performance and robustness on relevant datasets, 3) to provide a ``route'' to relevant algorithms for the relevant medical topics, and challenge leaderboards.

eess.IV↗

arXiv2009

A Study of Active Galactic Nuclei in Low Surface Brightness Galaxies with Sloan Digital Sky Survey Spectroscopy

Active galactic nuclei (AGN) in low surface brightness galaxies (LSBGs) have received little attention in previous studies. In this paper, we present detailed spectral analysis of 194 LSBGs from the Impey et al. (1996) APM LSBG sample which have been observed spectroscopically by the Sloan Digital Sky Survey Data Release 5 (SDSS DR5). Our elaborate spectral analysis enables us to carry out, for the first time, reliable spectral classification of nuclear activities in LSBGs based on the standard emission line diagnostic diagrams in a rigorous way. Star-forming galaxies are common, as found in about 52% LSBGs. We find, contrary to some of the previous claims, that the fraction of galaxies containing an AGN is significantly lower than that found in nearby normal galaxies of high surface brightness. This is qualitatively in line with the finding of Impey et al. (2001). This result holds true even within each morphological type from Sa to Sc. LSBGs having larger central stellar velocity dispersions, or larger physical sizes, tend to have a higher chance to harbor an AGN. For three AGNs with broad emission lines, the black hole masses estimated from the emission lines are broadly consistent with the well known M-$σ_\ast$ relation established for normal galaxies and AGNs.

astro-ph.GA↗

arXiv2006

On the correlation measure of a family of commuting Hermitian operators with applications to particle densities of the quasi-free representations of the CAR and CCR

Let $X$ be a locally compact, second countable Hausdorff topological space. We consider a family of commuting Hermitian operators $a(Δ)$ indexed by all measurable, relatively compact sets $Δ$ in $X$ (a quantum stochastic process over $X$). For such a family, we introduce the notion of a correlation measure. We prove that, if the family of operators possesses a correlation measure which satisfies some condition of growth, then there exists a point process over $X$ having the same correlation measure. Furthermore, the operators $a(Δ)$ can be realized as multiplication operators in the $L^2$-space with respect to this point process. In the proof, we utilize the notion of $\star$-positive definiteness, proposed in [Y. G. Kondratiev and T.\ Kuna, {\it Infin. Dimens. Anal. Quantum Probab. Relat. Top.} {\bf 5} (2002), 201--233]. In particular, our result extends the criterion of existence of a point process from that paper to the case of the topological space $X$, which is a standard underlying space in the theory of point processes. As applications, we discuss particle densities of the quasi-free representations of the CAR and CCR, which lead to fermion, boson, fermion-like, and boson-like (e.g. para-fermions and para-bosons of order 2) point processes. In particular, we prove that any fermion point process corresponding to a Hermitian kernel may be derived in this way.

math.PR↗