arXiv subjects

Ding Xia

Publications and source records attributed to Ding Xia.

At least 19 recordsLinked to original sources

arXiv2026

Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking

Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete sampling strategies, which inherently deviate from the continuity of spatio-temporal context, thereby deteriorating tracking performance. To address this challenge, we propose TLCTrack, a novel tracking framework that models token-level spatio-temporal context through continuously updated salient tokens, enabling more accurate target representation. Specifically, TLCTrack incorporates three components: Masked Unidirectional Attention (MUA), Spatial Salient Token Collection (SSTC), and Temporal Salient Token Bank (TSTB) modules. By explicitly integrating spatio-temporal context, MUA extracts discriminative targetaware spatial features in the search region. To avoid the negative impact of background on feature learning, SSTC progressively suppresses background interference, thereby enhancing target spatial representation. Finally, TSTB captures high-quality spatio-temporal information through continuous salient token updates. Extensive experiments on five benchmarks demonstrate that our method achieves superior performance over state-of-the-art trackers. Code and models are available at https://github.com/xiading123/TLCTrack.

cs.CV↗

arXiv2026

Query-Driven Multimodal Information Extraction from Long Documents

In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results.

cs.AI↗

arXiv2026

Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation

Deciphering ancient Chinese Oracle Bone Script (OBS) is a challenging task that offers insights into the beliefs, systems, and culture of the ancient era. Existing approaches treat decipherment as a closed-set image recognition problem, which fails to bridge the ``interpretation gap'': while individual characters are often unique and rare, they are composed of a limited set of recurring, pictographic components that carry transferable semantic meanings. To leverage this structural logic, we propose an agent-driven Vision-Language Model (VLM) framework that integrates a VLM for precise visual grounding with an LLM-based agent to automate a reasoning chain of component identification, graph-based knowledge retrieval, and relationship inference for linguistically accurate interpretation. To support this, we also introduce OB-Radix, an expert-annotated dataset providing structural and semantic data absent from prior corpora, comprising 1,022 character images (934 unique characters) and 1,853 fine-grained component images across 478 distinct components with verified explanations. By evaluating our system across three benchmarks of different tasks, we demonstrate that our framework yields more detailed and precise decipherments compared to baseline methods.

cs.CV↗

arXiv2026

Peeking Ahead of the Field Study: Exploring VLM Personas as Support Tools for Embodied Studies in HCI

Field studies are irreplaceable but costly, time-consuming, and error-prone, which need careful preparation. Inspired by rapid-prototyping in manufacturing, we propose a fast, low-cost evaluation method using Vision-Language Model (VLM) personas to simulate outcomes comparable to field results. While LLMs show human-like reasoning and language capabilities, autonomous vehicle (AV)-pedestrian interaction requires spatial awareness, emotional empathy, and behavioral generation. This raises our research question: To what extent can VLM personas mimic human responses in field studies? We conducted parallel studies: 1) one real-world study with 20 participants, and 2) one video-study using 20 VLM personas, both on a street-crossing task. We compared their responses and interviewed five HCI researchers on potential applications. Results show that VLM personas mimic human response patterns (e.g., average crossing times of 5.25 s vs. 5.07 s) lack the behavioral variability and depth. They show promise for formative studies, field study preparation, and human data augmentation.

cs.HC↗

arXiv2026

See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers

Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language model (VLM) perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of See2Refine for scalable action design.

cs.HC↗

arXiv2026

Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning

While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.

cs.CL↗

arXiv2025

TailCue: Exploring Animal-inspired Robotic Tail for Automated Vehicles Interaction

Automated vehicles (AVs) are gradually becoming part of our daily lives. However, effective communication between road users and AVs remains a significant challenge. Although various external human-machine interfaces (eHMIs) have been developed to facilitate interactions, psychological factors, such as a lack of trust and inadequate emotional signaling, may still deter users from confidently engaging with AVs in certain contexts. To address this gap, we propose TailCue, an exploration of how tail-based eHMIs affect user interaction with AVs. We first investigated mappings between tail movements and emotional expressions from robotics and zoology, and accordingly developed a motion-emotion mapping scheme. A physical robotic tail was implemented, and specific tail motions were designed based on our scheme. An online, video-based user study with 21 participants was conducted. Our findings suggest that, although the intended emotions conveyed by the tail were not consistently recognized, open-ended feedback indicated that the tail motion needs to align with the scenarios and cues. Our result highlights the necessity of scenario-specific optimization to enhance tail-based eHMIs. Future work will refine tail movement strategies to maximize their effectiveness across diverse interaction contexts.

cs.HC↗

arXiv2025

ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

Colors play a crucial role in the design of vector graphic documents by enhancing visual appeal, facilitating communication, improving usability, and ensuring accessibility. In this context, color recommendation involves suggesting appropriate colors to complete or refine a design when one or more colors are missing or require alteration. Traditional methods often struggled with these challenges due to the complex nature of color design and the limited data availability. In this study, we explored the use of pretrained Large Language Models (LLMs) and their commonsense reasoning capabilities for color recommendation, raising the question: Can pretrained LLMs serve as superior designers for color recommendation tasks? To investigate this, we developed a robust, rigorously validated pipeline, ColorGPT, that was built by systematically testing multiple color representations and applying effective prompt engineering techniques. Our approach primarily targeted color palette completion by recommending colors based on a set of given colors and accompanying context. Moreover, our method can be extended to full palette generation, producing an entire color palette corresponding to a provided textual description. Experimental results demonstrated that our LLM-based pipeline outperformed existing methods in terms of color suggestion accuracy and the distribution of colors in the color palette completion task. For the full palette generation task, our approach also yielded improvements in color diversity and similarity compared to current techniques.

cs.CV↗

arXiv2025

EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing

Chinese essay writing and its evaluation are critical in educational contexts, yet the capabilities of Large Language Models (LLMs) in this domain remain largely underexplored. Existing benchmarks often rely on coarse-grained text quality metrics, largely overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. To address this gap, we propose \benchName, a multi-genre benchmark specifically designed for Chinese essay writing across four major genres: Argumentative, Narrative, Descriptive, and Expository. We curate and refine a total of 728 real-world prompts to ensure authenticity and meticulously categorize them into the \textit{Open-Ended} and \textit{Constrained} sets to capture diverse writing scenarios. To reliably evaluate generated essays, we develop a fine-grained, genre-specific scoring framework that hierarchically aggregates scores. We further validate our evaluation protocol through a comprehensive human agreement study. Finally, we benchmark 15 large-sized LLMs, analyzing their strengths and limitations across genres and instruction types. With \benchName, we aim to advance LLM-based Chinese essay evaluation and inspire future research on improving essay generation in educational settings.

cs.CL↗

arXiv2025

Automating eHMI Action Design with LLMs for Automated Vehicle Communication

The absence of explicit communication channels between automated vehicles (AVs) and other road users requires the use of external Human-Machine Interfaces (eHMIs) to convey messages effectively in uncertain scenarios. Currently, most eHMI studies employ predefined text messages and manually designed actions to perform these messages, which limits the real-world deployment of eHMIs, where adaptability in dynamic scenarios is essential. Given the generalizability and versatility of large language models (LLMs), they could potentially serve as automated action designers for the message-action design task. To validate this idea, we make three contributions: (1) We propose a pipeline that integrates LLMs and 3D renderers, using LLMs as action designers to generate executable actions for controlling eHMIs and rendering action clips. (2) We collect a user-rated Action-Design Scoring dataset comprising a total of 320 action sequences for eight intended messages and four representative eHMI modalities. The dataset validates that LLMs can translate intended messages into actions close to a human level, particularly for reasoning-enabled LLMs. (3) We introduce two automated raters, Action Reference Score (ARS) and Vision-Language Models (VLMs), to benchmark 18 LLMs, finding that the VLM aligns with human preferences yet varies across eHMI modalities.

cs.HC↗

arXiv2025

Hybrid Learning: A Novel Combination of Self-Supervised and Supervised Learning for Joint MRI Reconstruction and Denoising in Low-Field MRI

Deep learning has demonstrated strong potential for MRI reconstruction. However, conventional supervised learning requires high-quality, high-SNR references for network training, which are often difficult or impossible to obtain in different scenarios, particularly in low-field MRI. Self-supervised learning provides an alternative by removing the need for training references, but its reconstruction performance can degrade when the baseline SNR is low. To address these limitations, we propose hybrid learning, a two-stage training framework that integrates self-supervised and supervised learning for joint MRI reconstruction and denoising when only low-SNR training references are available. Hybrid learning is implemented in two sequential stages. In the first stage, self-supervised learning is applied to fully sampled low-SNR data to generate higher-quality pseudo-references. In the second stage, these pseudo-references are used as targets for supervised learning to reconstruct and denoise undersampled noisy data. The proposed technique was evaluated in multiple experiments involving simulated and real low-field MRI in the lung and brain at different field strengths. Hybrid learning consistently improved image quality over both standard self-supervised learning and supervised learning with noisy training references at different acceleration rates, noise levels, and field strengths, achieving higher SSIM and lower NMSE. The hybrid learning approach is effective for both Cartesian and non-Cartesian acquisitions. Hybrid learning provides an effective solution for training deep MRI reconstruction models in the absence of high-SNR references. By improving image quality in low-SNR settings, particularly for low-field MRI, it holds promise for broader clinical adoption of deep learning-based reconstruction methods.

eess.IV↗

arXiv2025

HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models

Seeking dietary guidance often requires navigating complex professional knowledge while accommodating individual health conditions. Knowledge Graphs (KGs) offer structured and interpretable nutritional information, whereas Large Language Models (LLMs) naturally facilitate conversational recommendation delivery. In this paper, we present HealthGenie, an interactive system that combines the strengths of LLMs and KGs to provide personalized dietary recommendations along with hierarchical information visualization for a quick and intuitive overview. Upon receiving a user query, HealthGenie performs query refinement and retrieves relevant information from a pre-built KG. The system then visualizes and highlights pertinent information, organized by defined categories, while offering detailed, explainable recommendation rationales. Users can further tailor these recommendations by adjusting preferences interactively. Our evaluation, comprising a within-subject comparative experiment and an open-ended discussion, demonstrates that HealthGenie effectively supports users in obtaining personalized dietary guidance based on their health conditions while reducing interaction effort and cognitive load. These findings highlight the potential of LLM-KG integration in supporting decision-making through explainable and visualized information. We examine the system's usefulness and effectiveness with an N=12 within-subject study and provide design considerations for future systems that integrate conversational LLM and KG.

cs.HC↗

arXiv2025

Draw2Cut: Direct On-Material Annotations for CNC Milling

Creating custom artifacts with computer numerical control (CNC) milling machines typically requires mastery of complex computer-aided design (CAD) software. To eliminate this user barrier, we introduced Draw2Cut, a novel system that allows users to design and fabricate artifacts by sketching directly on physical materials. Draw2Cut employs a custom-drawing language to convert user-drawn lines, symbols, and colors into toolpaths, thereby enabling users to express their creative intent intuitively. The key features include real-time alignment between material and virtual toolpaths, a preview interface for validation, and an open-source platform for customization. Through technical evaluations and user studies, we demonstrate that Draw2Cut lowers the entry barrier for personal fabrication, enabling novices to create customized artifacts with precision and ease. Our findings highlight the potential of the system to enhance creativity, engagement, and accessibility in CNC-based woodworking.

cs.HC↗

arXiv2023

PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are always difficult to tune hyperparameters for extensive data and computationally time-consuming. Therefore, we propose a neural network that can effectively utilize neighbor textures with contour shape information to fundamentally improve performance. First, we employ a graph-based network to extract the local contour and texture features of fragments. Then, for the pair-searching task, we adopt a linear transformer-based module to integrate these local features and use contrastive loss to encode the global features of each fragment. For the pair-matching task, we design a weighted fusion module to dynamically fuse extracted local contour and texture features, and formulate a similarity matrix for each pair of fragments to calculate the matching score and infer the adjacent segment of contours. To faithfully evaluate our proposed network, we created a new image fragment dataset through an algorithm we designed that tears complete images into irregular fragments. The experimental results show that our proposed network achieves excellent pair-searching accuracy, reduces matching errors, and significantly reduces computational time. Details, sourcecode, and data are available in our supplementary material.

cs.CV↗

arXiv2022

SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing

We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data. Firstly, we visualize high-dimensional data features through dimensionality reduction methods and design an interactive system \textit{SpaceEditing} to display the visualized data. \textit{SpaceEditing} provides a 2D workspace based on the idea of spatial layout. In this workspace, the user can move the projection data in it according to the system guidance. Then, \textit{SpaceEditing} will find the corresponding high-dimensional features according to the projection data moved by the user, and feed the high-dimensional features back to the network for retraining, therefore achieving the purpose of interactively modifying the high-dimensional latent space for the user. Secondly, to more rationally incorporate human knowledge into the training process of neural networks, we design a new loss function that enables the network to learn user-modified information. Finally, We demonstrate how \textit{SpaceEditing} meets user needs through three case studies while evaluating our proposed new method, and the results confirm the effectiveness of our method.

cs.LG↗

arXiv2021

A Two-step Surface-based 3D Deep Learning Pipeline for Segmentation of Intracranial Aneurysms

The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited. In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly higher performance. Our proposed model takes a surface model of entire principal brain arteries containing aneurysms as input and returns aneurysms surfaces as output. A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images. The system then samples small surface fragments from the entire brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network (PointNet++). Finally, the system applies surface segmentation (SO-Net) to surface fragments containing aneurysms. We conduct a direct comparison of segmentation performance by counting voxels between the proposed surface-based framework and the existing voxel-based method, in which our framework achieves a much higher dice similarity coefficient score (72%) than the prior approach (46%).

eess.IV↗

arXiv2020

Optimization of MR Fingerprinting for Free-Breathing Quantitative Abdominal Imaging

In this work, we propose a free-breathing magnetic resonance fingerprinting method that can be used to obtain $B_1^+$-robust quantitative maps of the abdomen in a clinically acceptable time. A three-dimensional MR fingerprinting sequence with a radial stack-of-stars trajectory was implemented for quantitative abdominal imaging. The k-space acquisition ordering was adjusted to improve motion-robustness. The flip angle pattern was optimized using the Cram\'er-Rao Lower Bound, and the encoding efficiency of sequences with 300, 600, 900, and 1800 flip angles was evaluated. To validate the sequence, a movable multicompartment phantom was developed. Reference multiparametric maps were acquired under stationary conditions using a previously validated MRF method. Periodic motion of the phantom was used to investigate the motion-robustness of the proposed sequence. The best performing sequence length (600 flip angles) was used to image the abdomen during a free-breathing volunteer scan. When using a series of 600 or more flip angles, the estimated $T_1$ values in the stationary phantom showed good agreement with the reference scan. Phantom experiments revealed that motion-related artefacts can appear in the quantitative maps, and confirmed that a motion-robust k-space ordering is essential in preventing these artefacts. The in vivo scan demonstrated that the proposed sequence can produce clean parameter maps while the subject breathes freely. Using this sequence, it is possible to generate $B_1^+$-robust quantitative maps of proton density, $T_1$, and $B_1^+$ under free-breathing conditions at a clinically usable resolution within 5 minutes.

physics.med-ph↗

arXiv2020

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning

Medicine is an important application area for deep learning models. Research in this field is a combination of medical expertise and data science knowledge. In this paper, instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available. Our dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction. We provide a large-scale benchmark of classification and part segmentation by testing state-of-the-art networks. We also discuss the performance of each method and demonstrate the challenges of our dataset. The published dataset can be accessed here: https://github.com/intra3d2019/IntrA.

eess.IV↗