Author name cluster

Wei Zeng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

1 author row

AAAI Conference 2026 Conference Paper

Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension

Le Liu
Yuhao Wang
Bohan Shen
Wei Zeng
Shizhou Zhang
Di Xu
Peng Wang

Uncertainty visualizations, such as hurricane cones and ensemble tracks, are essential for risk communication but are often misinterpreted, leading to harmful decisions. As AI assistants like large language models (LLMs) increasingly support understanding of graphics and decision-making, they offer a promising pathway to enhance the interpretation of complex visualizations and a new opportunity to examine and improve the interpretation of uncertainty. We introduce UnReason, the first benchmark that systematically compares how humans and LLMs reason about hurricane forecast uncertainty visualizations. UnReason spans two escalating phases, seven representative visualization formats, six real hurricane cases, and three agent types (humans, LLMs with context, and LLMs without context), including 880 visualizations and 117,600 structured question–answer pairs under matched evaluation conditions. Phase 1 evaluates reasoning across implicit and explicit uncertainty encodings; Phase 2 examines reasoning under single- versus multi-dimensional uncertainty representations. We thoroughly assess damage estimation, reasoning strategies, and comprehension patterns, revealing that LLMs have a stronger semantic and conceptual understanding of uncertainty, and are less misled by visual variability, but still replicate key human biases during decision-making. Our findings offer insights into aligning LLM behavior with human cognition in uncertainty-rich visual reasoning tasks.

PDF Details DOI

EAAI Journal 2026 Journal Article

Enhancing small object detection in low-altitude remote sensing via high-resolution feature extraction and multi-scale fusion

Xinyuan Le
Ying Chen
Wei Zeng
Xiang Ao
Huiling Chen
Jingyan Xie

To address insufficient feature representation, redundancy in multi-scale fusion, and weak directional perception in low-altitude remote sensing images, this paper proposes a detection model based on convolutional neural networks and attention mechanisms, named Multi-Scale Fusion You Only Look Once (MSF-YOLO), with enhanced feature extraction and multi-scale fusion. First, the detection head hierarchy is reconstructed by adding a P2 tiny object head and removing the large object head, enhancing high-resolution feature utilization. Second, the Improved Selective Contour Aggregation (ISBA) module is designed to construct the Improved Selective Contour Aggregation Network (ISBANet), which dynamically adjusts fusion weights and performs consistency correction. Third, Enhanced Spatial and Directional Convolution (ESDConv) is proposed, improving small-object feature representation via spatial slicing-channel concatenation and multi-direction convolution while avoiding detail loss from traditional downsampling. Experimental results on the Vision Meets Drone Object Detection in Image Challenge (2019) (VisDrone-DET2019) dataset show that MSF-YOLO-n achieves detection accuracy close to You Only Look Once version 8x (YOLOv8x) with only 4% of its parameters and 18. 4% of its computational cost. Compared to baseline You Only Look Once version 8n (YOLOv8n), MSF-YOLO-n reduces parameters by 10% while increasing mean average precision at IoU thresholds 50–95% (mAP50-95) by 9. 3%, albeit with an expected increase in floating-point operations (FLOPs). Verification on the Unmanned Aerial Vehicle Benchmark Object Detection and Tracking (UAVDT) dataset confirms the model's generalization ability, demonstrating the effectiveness of the proposed artificial intelligence method for low-altitude remote sensing small-object detection.

Details DOI

AAAI Conference 2026 Conference Paper

G-IR: Geometric Image Representation for Learning

Xin Chen
Qi Zhao
Wei Zeng
Zongben Xu

Images are generally represented by pixel intensities or color values, which are usually used as direct inputs for learning. This study innovatively proposes a geometric image representation method and refreshes the general learning model (e.g., autoencoder) in the diffeomorphic space. Based on the theory of geometric optimal transport and quasiconformal mapping, we equivalently transform the intensity representation into a shape representation. The image space becomes a diffeomorphic space, where any image can be uniquely represented as a Beltrami coefficient function defined on a uniform grid reference, and vice versa. This innovative geometric image representation (G-IR) captures the fine-grained structure inherent in the entire image, which is different from the traditional feature extraction that focuses on the internal geometric objects of the image (such as boundaries and axes). The diffeomorphic property preserves structure in the generation process, which is very necessary in the field of real physics. It can be assembled into existing pipelines as a plug-in, providing structure-preserving properties for the entire framework. Experiments on image restoration and interpolation validated the high efficiency, efficacy and applicability of the G-IR method, demonstrating its superior performance compared to common pixel-level image appearance representations.

PDF Details DOI

JBHI Journal 2026 Journal Article

Multi-Scale Temporal Analysis With a Dual-Branch Attention Network for Interpretable Gait-Based Classification of Neurodegenerative Diseases

Wei Zeng
Zhangbo Peng
Yang Chen
Shaoyi Du

The accurate diagnosis of neurodegenerative diseases (NDDs), such as Amyotrophic Lateral Sclerosis (ALS), Huntington’s Disease (HD), and Parkinson’s Disease (PD), remains a clinical challenge due to the complexity and subtlety of gait abnormalities. This paper proposes the Dual-Branch Attention-Enhanced Residual Network (DAERN), a novel deep learning architecture that integrates Dilated Causal Convolutions (DCCBlock) for local gait pattern extraction and Multi-Head Self-Attention (MHSA) for long-range dependency modeling. A Cross-Attention Fusion module enhances feature integration, while SHapley Additive exPlanations (SHAP) and Integrated Gradients (IG) improve interpretability, providing clinically relevant insights into gait-based NDD classification. Uniform Manifold Approximation and Projection (UMAP) visualizations reveal well-separated clusters corresponding to distinct NDDs categories, demonstrating the model’s ability to capture discriminative features. Comprehensive ablation studies validate the contributions of model components and preprocessing strategies, highlighting the significance of each in achieving state-of-the-art classification performance. Experimental evaluations on the Gait in Neurodegenerative Disease (GaitNDD) dataset demonstrate that DAERN achieves an accuracy of 99. 64%, an F1-score of 99. 65%, and an AUC of 0. 9997, significantly outperforming conventional deep learning and machine learning baselines. These findings suggest that DAERN could be a valuable and interpretable tool for clinical gait assessment, aiding in early-stage monitoring and automated screening of NDDs, with potential applications in real-time wearable sensor-based gait analysis.

Details DOI

AAAI Conference 2026 Conference Paper

When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?

Qilang Ye
Wei Zeng
Meng Liu
Jie Zhang
Yupeng Hu
Zitong Yu
Yu Zhou

Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an “Audio-Visual Confusion” scene by modifying the corresponding sound of an object in the video, e.g., mute the sounding object and ask MLLMs “Is there a/an {muted-object} sound”. Experimental results reveal that MLLMs, such as Qwen2.5-Omni and Gemini 2.5, struggle to discriminate non-existent audio due to visually dominated reasoning. Motivated by this observation, we introduce RL-CoMM, a Reinforcement Learning-based Collaborative Multi-MLLM that is built upon the Qwen2.5-Omni foundation. RL-CoMM includes two stages: 1) To alleviate visually dominated ambiguities, we introduce an external model, a Large Audio Language Model (LALM), as the reference model to generate audio-only reasoning. Then, we design a Step-wise Reasoning Reward function that enables MLLMs to self-improve audio-visual reasoning with the audio-only reference. 2) To ensure an accurate answer prediction, we introduce Answer-centered Confidence Optimization to reduce the uncertainty of potential heterogeneous reasoning differences. Extensive experiments on audio-visual question answering and audio-visual hallucination show that RL-CoMM improves accuracy by 10~30% over the baseline model with limited training data.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

Tianqi Luo
Chuhan Huang
Leixian Shen
Boyan Li
Shuyu Shen
Wei Zeng
Nan Tang
Yuyu Luo

Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in interpreting ambiguous queries, as users often express their visualization needs in imprecise language. To address this challenge, we introduce nBench 2. 0, a new benchmark designed to evaluate Text2VIS systems in scenarios involving ambiguous queries. nvBench 2. 0 includes 7, 878 natural language queries and 24, 076 corresponding visualizations, derived from 780 tables across 153 domains. It is built using a controlled ambiguity-injection pipeline that generates ambiguous queries through a reverse-generation workflow. By starting with unambiguous seed visualizations and selectively injecting ambiguities, the pipeline yields multiple valid interpretations for each query, with each ambiguous query traceable to its corresponding visualization through step-wise reasoning paths. We evaluate various Large Language Models (LLMs) on their ability to perform ambiguous Text2VIS tasks using nBench 2. 0. We also propose Step-Text2Vis, an LLM-based model trained on nvBench 2. 0, which enhances performance in ambiguous scenarios through step-wise preference optimization. Our results show that Step-Text2Vis outperforms all baselines, setting a new state-of-the-art for ambiguous Text2VIS tasks. Our source code and data are available at https: //nvbench2. github. io/

PDF Details

EAAI Journal 2025 Journal Article

Zero-shot image translation via query compensation and style enhancement

Heng Zhang
Yi-Jun Yang
Wei Zeng

In zero-shot image translation methods based on diffusion models, two prevalent challenges are the loss of identity information and insufficient stylization. To address these issues, we propose a zero-shot image translation method. Specifically, we use the edit-friendly noise space for image inversion. By this way, the identity of the input image is largely preserved. Additionally, we introduce an identity compensation mechanism by injecting the source query vectors into the denoising process. Furthermore, to tackle the model’s insufficient stylization ability, we propose cross-attention style modulation (CSM) to transfer style information from the reference to the input image. Finally, to further enhance the style effect of the translated image, we design initial latent self-enhancement (ILS), style supplementation (SS), and style alignment (SA) strategies. Our zero-shot image translation method does not require training samples, optimization, or fine-tuning. We achieve this by manipulating the self-attention features of a pre-trained diffusion model in a manner analogous to cross-attention—by replacing the key and value vectors of the input image with those of the reference image during the denoising process. Extensive in-domain and cross-domain translation experiments demonstrate the effectiveness of our method across a wide range of object categories and show strong robustness to variations in object shape, size, posture and instance between the input and reference image. The proposed method achieves competitive performance in identity preservation, as measured by the mean Intersection over Union (mIoU), and attains the best style transfer in terms of Single Image Fréchet Inception Distance (SIFID). In addition, qualitative comparisons demonstrate that our approach significantly outperforms the baselines.

Details DOI

IJCAI Conference 2024 Conference Paper

End-to-End Real-World Polyphonic Piano Audio-to-Score Transcription with Hierarchical Decoding

Wei Zeng
Xian He
Ye Wang

Piano audio-to-score transcription (A2S) is an important yet underexplored task with extensive applications for music composition, practice, and analysis. However, existing end-to-end piano A2S systems faced difficulties in retrieving bar-level information such as key and time signatures, and have been trained and evaluated with only synthetic data. To address these limitations, we propose a sequence-to-sequence (Seq2Seq) model with a hierarchical decoder that aligns with the hierarchical structure of musical scores, enabling the transcription of score information at both the bar and note levels by multi-task learning. To bridge the gap between synthetic data and recordings of human performance, we propose a two-stage training scheme, which involves pre-training the model using an expressive performance rendering (EPR) system on synthetic audio, followed by fine-tuning the model using recordings of human performance. To preserve the voicing structure for score reconstruction, we propose a pre-processing method for **Kern scores in scenarios with an unconstrained number of voices. Experimental results support the effectiveness of our proposed approaches, in terms of both transcription performance on synthetic audio data in comparison to the current state-of-the-art, and the first experiment on human recordings.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Keypoint-Guided Optimal Transport with Applications in Heterogeneous Domain Adaptation

Xiang Gu
Yucheng Yang
Wei Zeng
Jian Sun
Zongben Xu

Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimization, which may cause incorrect matching in some cases. In many applications, annotating a few matched keypoints across domains is reasonable or even effortless in annotation burden. It is valuable to investigate how to leverage the annotated keypoints to guide the correct matching in OT. In this paper, we propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL) that searches for the matching guided by the keypoints in OT. To impose the keypoints in OT, first, we propose a mask-based constraint of the transport plan that preserves the matching of keypoint pairs. Second, we propose to preserve the relation of each data point to the keypoints to guide the matching. The proposed KPG-RL model can be solved by the Sinkhorn's algorithm and is applicable even when distributions are supported in different spaces. We further utilize the relation preservation constraint in the Kantorovich Problem and Gromov-Wasserstein model to impose the guidance of keypoints in them. Meanwhile, the proposed KPG-RL model is extended to partial OT setting. As an application, we apply the proposed KPG-RL model to the heterogeneous domain adaptation. Experiments verified the effectiveness of the KPG-RL model.

PDF Details

AIIM Journal 2020 Journal Article

Classification of myocardial infarction based on hybrid feature extraction and artificial intelligence tools by adopting tunable-Q wavelet transform (TQWT), variational mode decomposition (VMD) and neural networks

Wei Zeng
Jian Yuan
Chengzhi Yuan
Qinghui Wang
Fenglin Liu
Ying Wang

Cardiovascular diseases (CVD) is the leading cause of human mortality and morbidity around the world, in which myocardial infarction (MI) is a silent condition that irreversibly damages the heart muscles. Currently, electrocardiogram (ECG) is widely used by the clinicians to diagnose MI patients due to its inexpensiveness and non-invasive nature. Pathological alterations provoked by MI cause slow conduction by increasing axial resistance on coupling between cells. This issue may cause abnormal patterns in the dynamics of the tip of the cardiac vector in the ECG signals. However, manual interpretation of the pathological alternations induced by MI is a time-consuming, tedious and subjective task. To overcome such disadvantages, computer-aided diagnosis techniques including signal processing and artificial intelligence tools have been developed. In this study we propose a novel technique for automatic detection of MI based on hybrid feature extraction and artificial intelligence tools. Tunable quality factor ( Q -factor) wavelet transform (TQWT), variational mode decomposition (VMD) and phase space reconstruction (PSR) are utilized to extract representative features to form cardiac vectors with synthesis of the standard 12-lead and Frank XYZ leads. They are combined with neural networks to model, identify and detect abnormal patterns in the dynamics of cardiac system caused by MI. First, 12-lead ECG signals are reduced to 3-dimensional VCG signals, which are synthesized with Frank XYZ leads to build a hybrid 4-dimensional cardiac vector. Second, this vector is decomposed into a set of frequency subbands with a number of decomposition levels by using the TQWT method. Third, VMD is employed to decompose the subband of the 4-dimensional cardiac vector into different intrinsic modes, in which the first intrinsic mode contains the majority of the cardiac vector's energy and is considered to be the predominant intrinsic mode. It is selected to construct the reference variable for analysis. Fourth, phase space of the reference variable is reconstructed, in which the properties associated with the nonlinear cardiac system dynamics are preserved. Three-dimensional (3D) PSR together with Euclidean distance (ED) has been utilized to derive features, which demonstrate significant difference in cardiac system dynamics between normal (healthy) and MI cardiac vector signals. Fifth, cardiac system dynamics can be modeled and identified using neural networks, which employ the ED of 3D PSR of the reference variable as the input features. The difference of cardiac system dynamics between healthy control and MI cardiac vector is computed and used for the detection of MI based on a bank of estimators. Finally, data sets, which include conventional 12-lead and Frank XYZ leads ECG signal fragments from 148 patients with MI and 52 healthy controls from PTB diagnostic ECG database, are used for evaluation. By using the 10-fold cross-validation style, the achieved average classification accuracy is reported to be 97. 98%. Currently, ST segment evaluation is one of the major and traditional ways for the MI detection. However, there exist weak or even undetectable ST segments in many ECG signals. Since the proposed method does not rely on the information of ST waves, it can serve as a complementary MI detection algorithm in the intensive care unit (ICU) of hospitals to assist the clinicians in confirming their diagnosis. Overall, our results verify that the proposed features may satisfactorily reflect cardiac system dynamics, and are complementary to the existing ECG features for automatic cardiac function analysis.

Details DOI