arXiv subjects

Qiang Ma

Publications and source records attributed to Qiang Ma.

At least 37 records · Page 2Linked to original sources

arXiv2025

edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer

Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements, existing systems commonly employ cloud-edge collaborative architectures, such as partitioned Large Vision-Language Models (LVLMs) or task offloading strategies between Large and Small Vision-Language Models (SVLMs). However, these methods fail to accommodate cloud latency fluctuations and overlook the full potential of delayed but accurate LVLM responses. In this work, we propose a novel cloud-edge collaborative paradigm for VLMs, termed Context Transfer, which treats the delayed outputs of LVLMs as historical context to provide real-time guidance for SVLMs inference. Based on this paradigm, we design edgeVLM, which incorporates both context replacement and visual focus modules to refine historical textual input and enhance visual grounding consistency. Extensive experiments on three real-time vision-lanuage reasoning tasks across four datasets demonstrate the effectiveness of the proposed framework. The new paradigm lays the groundwork for more effective and latency-aware collaboration strategies in future VLM systems.

cs.CV↗

arXiv2025

CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching

Learning 3D+t shape completion and generation from multi-view cardiac magnetic resonance (CMR) images requires a large amount of high-resolution 3D whole-heart segmentations (WHS) to capture shape priors. In this work, we leverage flow matching techniques to learn deep generative flows for augmentation, completion, and generation of 3D+t shapes of four cardiac chambers represented implicitly by segmentations. Firstly, we introduce a latent rectified flow to generate 3D cardiac shapes for data augmentation, learnt from a limited number of 3D WHS data. Then, a label completion network is trained on both real and synthetic data to reconstruct 3D+t shapes from sparse multi-view CMR segmentations. Lastly, we propose CardiacFlow, a novel one-step generative flow model for efficient 3D+t four-chamber cardiac shape generation, conditioned on the periodic Gaussian kernel encoding of time frames. The experiments on the WHS datasets demonstrate that flow-based data augmentation reduces geometric errors by 16% in 3D shape completion. The evaluation on the UK Biobank dataset validates that CardiacFlow achieves superior generation quality and periodic consistency compared to existing baselines.

eess.IV↗

arXiv2025

OpenMoCap: Rethinking Optical Motion Capture under Real-world Occlusion

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in real-world applications. An in-depth analysis identifies two primary limitations of current models: (i) the lack of training datasets accurately reflecting realistic marker occlusion patterns, and (ii) the absence of training strategies designed to capture long-range dependencies among markers. To tackle these challenges, we introduce the CMU-Occlu dataset, which incorporates ray tracing techniques to realistically simulate practical marker occlusion patterns. Furthermore, we propose OpenMoCap, a novel motion-solving model designed specifically for robust motion capture in environments with significant occlusions. Leveraging a marker-joint chain inference mechanism, OpenMoCap enables simultaneous optimization and construction of deep constraints between markers and joints. Extensive comparative experiments demonstrate that OpenMoCap consistently outperforms competing methods across diverse scenarios, while the CMU-Occlu dataset opens the door for future studies in robust motion solving. The proposed OpenMoCap is integrated into the MoSen MoCap system for practical deployment. The code is released at: https://github.com/qianchen214/OpenMoCap.

cs.CV↗

arXiv2025

CAMEF: Causal-Augmented Multi-Modality Event-Driven Financial Forecasting by Integrating Time Series Patterns and Salient Macroeconomic Announcements

Accurately forecasting the impact of macroeconomic events is critical for investors and policymakers. Salient events like monetary policy decisions and employment reports often trigger market movements by shaping expectations of economic growth and risk, thereby establishing causal relationships between events and market behavior. Existing forecasting methods typically focus either on textual analysis or time-series modeling, but fail to capture the multi-modal nature of financial markets and the causal relationship between events and price movements. To address these gaps, we propose CAMEF (Causal-Augmented Multi-Modality Event-Driven Financial Forecasting), a multi-modality framework that effectively integrates textual and time-series data with a causal learning mechanism and an LLM-based counterfactual event augmentation technique for causal-enhanced financial forecasting. Our contributions include: (1) a multi-modal framework that captures causal relationships between policy texts and historical price data; (2) a new financial dataset with six types of macroeconomic releases from 2008 to April 2024, and high-frequency real trading data for five key U.S. financial assets; and (3) an LLM-based counterfactual event augmentation strategy. We compare CAMEF to state-of-the-art transformer-based time-series and multi-modal baselines, and perform ablation studies to validate the effectiveness of the causal learning mechanism and event types.

cs.LG↗

arXiv2025

Topology Optimization in Medical Image Segmentation with Fast Euler Characteristic

Deep learning-based medical image segmentation techniques have shown promising results when evaluated based on conventional metrics such as the Dice score or Intersection-over-Union. However, these fully automatic methods often fail to meet clinically acceptable accuracy, especially when topological constraints should be observed, e.g., continuous boundaries or closed surfaces. In medical image segmentation, the correctness of a segmentation in terms of the required topological genus sometimes is even more important than the pixel-wise accuracy. Existing topology-aware approaches commonly estimate and constrain the topological structure via the concept of persistent homology (PH). However, these methods are difficult to implement for high dimensional data due to their polynomial computational complexity. To overcome this problem, we propose a novel and fast approach for topology-aware segmentation based on the Euler Characteristic ($χ$). First, we propose a fast formulation for $χ$ computation in both 2D and 3D. The scalar $χ$ error between the prediction and ground-truth serves as the topological evaluation metric. Then we estimate the spatial topology correctness of any segmentation network via a so-called topological violation map, i.e., a detailed map that highlights regions with $χ$ errors. Finally, the segmentation results from the arbitrary network are refined based on the topological violation maps by a topology-aware correction network. Our experiments are conducted on both 2D and 3D datasets and show that our method can significantly improve topological correctness while preserving pixel-wise segmentation accuracy.

eess.IV↗

arXiv2025

OpenMap: Instruction Grounding via Open-Vocabulary Visual-Language Mapping

Grounding natural language instructions to visual observations is fundamental for embodied agents operating in open-world environments. Recent advances in visual-language mapping have enabled generalizable semantic representations by leveraging vision-language models (VLMs). However, these methods often fall short in aligning free-form language commands with specific scene instances, due to limitations in both instance-level semantic consistency and instruction interpretation. We present OpenMap, a zero-shot open-vocabulary visual-language map designed for accurate instruction grounding in navigation tasks. To address semantic inconsistencies across views, we introduce a Structural-Semantic Consensus constraint that jointly considers global geometric structure and vision-language similarity to guide robust 3D instance-level aggregation. To improve instruction interpretation, we propose an LLM-assisted Instruction-to-Instance Grounding module that enables fine-grained instance selection by incorporating spatial context and expressive target descriptions. We evaluate OpenMap on ScanNet200 and Matterport3D, covering both semantic mapping and instruction-to-target retrieval tasks. Experimental results show that OpenMap outperforms state-of-the-art baselines in zero-shot settings, demonstrating the effectiveness of our method in bridging free-form language and 3D perception for embodied navigation.

cs.RO↗

arXiv2025

Relationship Analysis of Image-Text Pair in SNS Posts

Social networking services (SNS) contain vast amounts of image-text posts, necessitating effective analysis of their relationships for improved information retrieval. This study addresses the classification of image-text pairs in SNS, overcoming prior limitations in distinguishing relationships beyond similarity. We propose a graph-based method to classify image-text pairs into similar and complementary relationships. Our approach first embeds images and text using CLIP, followed by clustering. Next, we construct an Image-Text Relationship Clustering Line Graph (ITRC-Line Graph), where clusters serve as nodes. Finally, edges and nodes are swapped in a pseudo-graph representation. A Graph Convolutional Network (GCN) then learns node and edge representations, which are fused with the original embeddings for final classification. Experimental results on a publicly available dataset demonstrate the effectiveness of our method.

cs.MM↗

arXiv2025

Cancellation in sums over special sequences on $\mathbf{\rm{GL}_{m}}$ and their applications

Let $a(n)$ be the $n$-th Dirichlet coefficient of the automorphic $L$-function or the Rankin--Selberg $L$-function. We investigate the cancellation of $a(n)$ over sequences linked to the Waring--Goldbach problem, by establishing a nontrivial bound for the additive twisted sums over primes on ${\mathrm{GL}}_m .$ The bound does not depend on the generalized Ramanujan conjecture or the nonexistence of Landau--Siegel zeros. Furthermore, we present an application associated with the Sato--Tate conjecture and propose a conjecture about the Goldbach conjecture on average bound.

math.NT↗

arXiv2025

XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?

The astonishing breakthrough of multimodal large language models (MLLMs) has necessitated new benchmarks to quantitatively assess their capabilities, reveal their limitations, and indicate future research directions. However, this is challenging in the context of remote sensing (RS), since the imagery features ultra-high resolution that incorporates extremely complex semantic relationships. Existing benchmarks usually adopt notably smaller image sizes than real-world RS scenarios, suffer from limited annotation quality, and consider insufficient dimensions of evaluation. To address these issues, we present XLRS-Bench: a comprehensive benchmark for evaluating the perception and reasoning capabilities of MLLMs in ultra-high-resolution RS scenarios. XLRS-Bench boasts the largest average image size (8500$\times$8500) observed thus far, with all evaluation samples meticulously annotated manually, assisted by a novel semi-automatic captioner on ultra-high-resolution RS images. On top of the XLRS-Bench, 16 sub-tasks are defined to evaluate MLLMs' 10 kinds of perceptual capabilities and 6 kinds of reasoning capabilities, with a primary emphasis on advanced cognitive processes that facilitate real-world decision-making and the capture of spatiotemporal changes. The results of both general and RS-focused MLLMs on XLRS-Bench indicate that further efforts are needed for real-world RS applications. We have open-sourced XLRS-Bench to support further research in developing more powerful MLLMs for remote sensing.

cs.CV↗

arXiv2025

Food Recommendation With Balancing Comfort and Curiosity

Food is a key pleasure of traveling, but travelers face a trade-off between exploring curious new local food and choosing comfortable, familiar options. This creates demand for personalized recommendation systems that balance these competing factors. To the best of our knowledge, conventional recommendation methods cannot provide recommendations that offer both curiosity and comfort for food unknown to the user at a travel destination. In this study, we propose new quantitative methods for estimating comfort and curiosity: Kernel Density Scoring (KDS) and Mahalanobis Distance Scoring (MDS). KDS probabilistically estimates food history distribution using kernel density estimation, while MDS uses Mahalanobis distances between foods. These methods score food based on how their representation vectors fit the estimated distributions. We also propose a ranking method measuring the balance between comfort and curiosity based on taste and ingredients. This balance is defined as curiosity (return) gained per unit of comfort (risk) in choosing a food. For evaluation the proposed method, we newly collected a dataset containing user surveys on Japanese food and assessments of foreign food regarding comfort and curiosity. Comparing our methods against the existing method, the Wilcoxon signed-rank test showed that when estimating comfort from taste and curiosity from ingredients, the MDS-based method outperformed the Baseline, while the KDS-based method showed no significant differences. When estimating curiosity from taste and comfort from ingredients, both methods outperformed the Baseline. The MDS-based method consistently outperformed KDS in ROC-AUC values.

cs.IR↗

arXiv2025

Ensemble ToT of LLMs and Its Application to Automatic Grading System for Supporting Self-Learning

Providing students with detailed and timely grading feedback is essential for self-learning. While existing LLM-based grading systems are promising, most of them rely on one single model, which limits their performance. To address this, we propose Ensemble Tree-of-Thought (ToT), a framework that enhances LLM outputs by integrating multiple models. Using this framework, we develop a grading system. Ensemble ToT follows three steps: (1) analyzing LLM performance, (2) generating candidate answers, and (3) refining them into a final result. Based on this, our grading system first evaluates the grading tendencies of LLMs, then generates multiple results, and finally integrates them via a simulated debate. Experimental results demonstrate our approach's ability to provide accurate and explainable grading by effectively coordinating multiple LLMs.

cs.IR↗

arXiv2024

The Developing Human Connectome Project: A Fast Deep Learning-based Pipeline for Neonatal Cortical Surface Reconstruction

The Developing Human Connectome Project (dHCP) aims to explore developmental patterns of the human brain during the perinatal period. An automated processing pipeline has been developed to extract high-quality cortical surfaces from structural brain magnetic resonance (MR) images for the dHCP neonatal dataset. However, the current implementation of the pipeline requires more than 6.5 hours to process a single MRI scan, making it expensive for large-scale neuroimaging studies. In this paper, we propose a fast deep learning (DL) based pipeline for dHCP neonatal cortical surface reconstruction, incorporating DL-based brain extraction, cortical surface reconstruction and spherical projection, as well as GPU-accelerated cortical surface inflation and cortical feature estimation. We introduce a multiscale deformation network to learn diffeomorphic cortical surface reconstruction end-to-end from T2-weighted brain MRI. A fast unsupervised spherical mapping approach is integrated to minimize metric distortions between cortical surfaces and projected spheres. The entire workflow of our DL-based dHCP pipeline completes within only 24 seconds on a modern GPU, which is nearly 1000 times faster than the original dHCP pipeline. The qualitative assessment demonstrates that for 82.5% of the test samples, the cortical surfaces reconstructed by our DL-based pipeline achieve superior (54.2%) or equal (28.3%) surface quality compared to the original dHCP pipeline.

eess.IV↗

arXiv2024

Universal Topology Refinement for Medical Image Segmentation with Polynomial Feature Synthesis

Although existing medical image segmentation methods provide impressive pixel-wise accuracy, they often neglect topological correctness, making their segmentations unusable for many downstream tasks. One option is to retrain such models whilst including a topology-driven loss component. However, this is computationally expensive and often impractical. A better solution would be to have a versatile plug-and-play topology refinement method that is compatible with any domain-specific segmentation pipeline. Directly training a post-processing model to mitigate topological errors often fails as such models tend to be biased towards the topological errors of a target segmentation network. The diversity of these errors is confined to the information provided by a labelled training set, which is especially problematic for small datasets. Our method solves this problem by training a model-agnostic topology refinement network with synthetic segmentations that cover a wide variety of topological errors. Inspired by the Stone-Weierstrass theorem, we synthesize topology-perturbation masks with randomly sampled coefficients of orthogonal polynomial bases, which ensures a complete and unbiased representation. Practically, we verified the efficiency and effectiveness of our methods as being compatible with multiple families of polynomial bases, and show evidence that our universal plug-and-play topology refinement network outperforms both existing topology-driven learning-based and post-processing methods. We also show that combining our method with learning-based models provides an effortless add-on, which can further improve the performance of existing approaches.

eess.IV↗

arXiv2024

Weakly Supervised Learning of Cortical Surface Reconstruction from Segmentations

Existing learning-based cortical surface reconstruction approaches heavily rely on the supervision of pseudo ground truth (pGT) cortical surfaces for training. Such pGT surfaces are generated by traditional neuroimage processing pipelines, which are time consuming and difficult to generalize well to low-resolution brain MRI, e.g., from fetuses and neonates. In this work, we present CoSeg, a learning-based cortical surface reconstruction framework weakly supervised by brain segmentations without the need for pGT surfaces. CoSeg introduces temporal attention networks to learn time-varying velocity fields from brain MRI for diffeomorphic surface deformations, which fit an initial surface to target cortical surfaces within only 0.11 seconds for each brain hemisphere. A weakly supervised loss is designed to reconstruct pial surfaces by inflating the white surface along the normal direction towards the boundary of the cortical gray matter segmentation. This alleviates partial volume effects and encourages the pial surface to deform into deep and challenging cortical sulci. We evaluate CoSeg on 1,113 adult brain MRI at 1mm and 2mm resolution. CoSeg achieves superior geometric and morphological accuracy compared to existing learning-based approaches. We also verify that CoSeg can extract high-quality cortical surfaces from fetal brain MRI on which traditional pipelines fail to produce acceptable results.

eess.IV↗

arXiv2023

Multi-Granularity Framework for Unsupervised Representation Learning of Time Series

Representation learning plays a critical role in the analysis of time series data and has high practical value across a wide range of applications. including trend analysis, time series data retrieval and forecasting. In practice, data confusion is a significant issue as it can considerably impact the effectiveness and accuracy of data analysis, machine learning models and decision-making processes. In general, previous studies did not consider the variability at various levels of granularity, thus resulting in inadequate information utilization, which further exacerbated the issue of data confusion. This paper proposes an unsupervised framework to realize multi-granularity representation learning for time series. Specifically, we employed a cross-granularity transformer to develop an association between fine- and coarse-grained representations. In addition, we introduced a retrieval task as an unsupervised training task to learn the multi-granularity representation of time series. Moreover, a novel loss function was designed to obtain the comprehensive multi-granularity representation of the time series via unsupervised learning. The experimental results revealed that the proposed framework demonstrates significant advantages over alternative representation learning models.

cs.LG↗

arXiv2023

High Q and high gradient performance of the first medium-temperature baking 1.3 GHz cryomodule

World's first 1.3 GHz cryomodule containing eight 9-cell superconducting radio-frequency (RF) cavities treated by medium-temperature furnace baking (mid-T bake) was developed, assembled and tested at IHEP for the Dalian Advanced Light Source (DALS) and CEPC R&D. The 9-cell cavities in the cryomodule achieved an unprecedented highest average Q0 of 3.8E10 at 16 MV/m and 3.6E10 at 21 MV/m in the horizontal test. The cryomodule can operate stably up to a total CW RF voltage greater than 191 MV, with an average cavity CW accelerating gradient of more than 23 MV/m. The results significantly exceed the specifications of CEPC, DALS and the other high repetition rate free electron laser facilities (LCLS-II, LCLS-II-HE, SHINE, S3FEL). There is evidence that the mid-T bake cavity may not require fast cool-down or long processing time in the cryomodule. This paper reviews the cryomodule performance and discusses some important issues in cryomodule assembly and testing.

physics.acc-ph↗

arXiv2023

Evaluating the quantum optimal biased bound in a unitary evolution process

Seeking the available precision limit of unknown parameters is a significant task in quantum parameter estimation. One often resorts to the widely utilized quantum Cramer-Rao bound (QCRB) based on unbiased estimators to finish this task. Nevertheless, most actual estimators are usually biased in the limited number of trials. For this reason, we introduce two effective error bounds for biased estimators based on a unitary evolution process in the framework of the quantum optimal biased bound. Furthermore, we show their estimation performance by two specific examples of the unitary evolution process, including the phase encoding and the SU(2) interferometer process. Our findings will provide an useful guidance for finding the precision limit of unknown parameters.

quant-ph↗

arXiv2023

Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction

Cortical surface reconstruction plays a fundamental role in modeling the rapid brain development during the perinatal period. In this work, we propose Conditional Temporal Attention Network (CoTAN), a fast end-to-end framework for diffeomorphic neonatal cortical surface reconstruction. CoTAN predicts multi-resolution stationary velocity fields (SVF) from neonatal brain magnetic resonance images (MRI). Instead of integrating multiple SVFs, CoTAN introduces attention mechanisms to learn a conditional time-varying velocity field (CTVF) by computing the weighted sum of all SVFs at each integration step. The importance of each SVF, which is estimated by learned attention maps, is conditioned on the age of the neonates and varies with the time step of integration. The proposed CTVF defines a diffeomorphic surface deformation, which reduces mesh self-intersection errors effectively. It only requires 0.21 seconds to deform an initial template mesh to cortical white matter and pial surfaces for each brain hemisphere. CoTAN is validated on the Developing Human Connectome Project (dHCP) dataset with 877 3D brain MR images acquired from preterm and term born neonates. Compared to state-of-the-art baselines, CoTAN achieves superior performance with only 0.12mm geometric error and 0.07% self-intersecting faces. The visualization of our attention maps illustrates that CoTAN indeed learns coarse-to-fine surface deformations automatically without intermediate supervision.

eess.IV↗