Author name cluster

Weisheng Li

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.

15 papers

1 author row

JBHI Journal 2026 Journal Article

SAFusion: Scenario-Adaptive Network for Multimodal Medical Image Fusion

Weisheng Li
Pengtao Jia
Dan He
Shiqiang Liu
Guofen Wang
Yuping Huang

Multimodal medical image fusion aims to integrate complementary information from different modalities to support clinical diagnosis and treatment. Although deep learning has significantly advanced this field, existing methods often overlook the differences between various fusion scenarios, making a single network inadequate for diverse fusion requirements. Therefore, we propose a novel scenario-adaptive fusion network. The network employs a two-stage training process. In the first stage, an autoencoder is trained for multiscale feature extraction and image reconstruction. In the second stage, the autoencoder parameters are frozen, and a Fusion Layer is trained to achieve multimodal feature integration. The Fusion Layer consists of a Scenario-Specific Fusion Module and a Scenario-General Fusion Module. The former uses a mixture-of-experts model to customize fusion strategies for different scenarios to optimize the fusion process. The latter employs a dual-path fusion structure based on standard convolution and deformable convolution gating mechanisms to achieve general feature fusion across multi-scenario. Compared to eleven state-of-the-art methods, our method demonstrates superior information integration and visual consistency, offering a flexible and efficient solution for various fusion scenarios. The code is available at https://github.com/PengtaoJia/SAFusion.

Details DOI

NeurIPS Conference 2025 Conference Paper

A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding

Mengjingcheng Mo
Xinyang Tong
Mingpi Tan
Jiaxu Leng
JianKang Zheng
Yiran Liu
Haosheng Chen
Ji Gan

While unmanned aerial vehicles (UAVs) offer wide-area, high-altitude coverage for anomaly detection, they face challenges such as dynamic viewpoints, scale variations, and complex scenes. Existing datasets and methods, mainly designed for fixed ground-level views, struggle to adapt to these conditions, leading to significant performance drops in drone-view scenarios. To bridge this gap, we introduce A2Seek (Aerial Anomaly Seek), a large-scale, reasoning-centric benchmark dataset for aerial anomaly understanding. This dataset covers various scenarios and environmental conditions, providing high-resolution real-world aerial videos with detailed annotations, including anomaly categories, frame-level timestamps, region-level bounding boxes, and natural language explanations for causal reasoning. Building on this dataset, we propose A2Seek-R1, a novel reasoning framework that generalizes R1-style strategies to aerial anomaly understanding, enabling a deeper understanding of “Where” anomalies occur and “Why” they happen in aerial frames. To this end, A2Seek-R1 first employs a graph-of-thought (GoT)-guided supervised fine-tuning approach to activate the model's latent reasoning capabilities on A2Seek. Then, we introduce Aerial Group Relative Policy Optimization (A-GRPO) to design rule-based reward functions tailored to aerial scenarios. Furthermore, we propose a novel “seeking” mechanism that simulates UAV flight behavior by directing the model's attention to informative regions. Extensive experiments demonstrate that A2Seek-R1 achieves up to a 22. 04\% improvement in AP for prediction accuracy and a 13. 9\% gain in mIoU for anomaly localization, exhibiting strong generalization across complex environments and out-of-distribution scenarios. Our dataset and code are released at https: //2-mo. github. io/A2Seek/.

PDF Details

JBHI Journal 2025 Journal Article

Contrastive Learning Guided Fusion Network for Brain CT and MRI

Yuping Huang
Weisheng Li
Bin Xiao
Guofen Wang
Dan He
Xiaoyu Qiao

Medical image fusion technology provides professionals with more detailed and precise diagnostic information. This paper introduces a new efficient CT and MRI fusion network, CLGFusion, based on a contrastive learning-guided network. CLGFusion includes two encoding branches at the feature encoding stage, enabling them to interact and learn from each other. The approach begins with training a single-view encoder to predict the feature representation of an image from varied augmented views. Simultaneously, the multi-view encoder is improved using the exponential moving average of the single-view encoder. Contrastive learning is integrated into medical image fusion by creating a feature contrast space without constructing negative samples. This feature contrast space cleverly uses the information of the difference in the feature product of the source image and its corresponding augmented image. It continuously guides the network to constantly optimize its fusion effect by combining the method of structural similarity loss, to achieve more accurate and efficient image fusion. This approach represents an end-to-end unsupervised fusion model. Experimental validation shows that our proposed method demonstrates performance comparable to state-of-the-art techniques in both subjective evaluation and objective metrics.

Details DOI

AAAI Conference 2025 Conference Paper

CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training

Xiuli Bi
Jian Lu
Bo Liu
Xiaodong Cun
Yong Zhang
Weisheng Li
Bin Xiao

Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, given some reference images or videos, the parameter-efficient fine-tuning method, i.e. LoRA, can generate high-quality customized concepts, e.g., the specific subject or the motions from a reference video. However, combining the trained multiple concepts from different references into a single network shows obvious artifacts. To this end, we propose CustomTTT, where we can joint custom the appearance and the motion of the given video easily. In detail, we first analyze the prompt influence in the current video diffusion model and find the LoRAs are only needed for the specific layers for appearance and motion customization. Besides, since each LoRA is trained individually, we propose a novel test-time training technique to update parameters after combination utilizing the trained customized models. We conduct detailed experiments to verify the effectiveness of the proposed methods. Our method outperforms several state-of-the-art works in both qualitative and quantitative evaluations.

PDF Details DOI

EAAI Journal 2025 Journal Article

Modal disentangled generative adversarial networks for bidirectional magnetic resonance image synthesis

Liming Xu
Yanrong Lei
Jie Shao
Xianhua Zeng
Weisheng Li

Magnetic resonance imaging (MRI) is commonly used both in clinical diagnosis and scientific research. Owing to the high cost, time constraints, and limited application of multi-contrast MRI images obtained from metallic implants, it incurs low throughput and misses a specific modality. Medical image cross-modal synthesis based on Artificial Intelligence (AI) technologies is proposed to synthesize the desired missing modal images. However, it still suffers from low expandability, invisible latent representations, and poor interpretability. We thus propose modal disentanglement generative adversarial networks for bidirectional T1-weighted (T1-w) and T1-weighted (T2-w) medical image synthesis with controllable cross-modal synthesis and disentangled interpretability. Firstly, we construct a cross-modal synthesis model to achieve bidirectional generation between T1-w and T2-w MRI images, which can be easily extended for adaptive modality synthesis without training multiple generators and discriminators. Then, we use an easily trained deep network to disentangle deep representations in latent space and map representations in latent space into pixel space to visualize morphological images and yield multi-contrast MRI images with controllable feature generation. Besides, we construct an easy-to-interpret deep structure by incorporating morphology consistency to preserve edge contours and visualize deep representations in latent space to enable interpretability, which is critical for artificial intelligence oriented to engineering applications and clinical diagnostics. The experiments demonstrate that ours outperforms recent state-of-the-art methods with average improvements of 15. 8% structural similarity (SSIM), 12. 7% multiscale structural similarity (MSIM), 38. 2% peak signal-to-noise ratio (PSNR) and 5. 2% visual information fidelity (VIF) on benchmark datasets.

Details DOI

JBHI Journal 2025 Journal Article

Whole Heart Segmentation Based on 3D Contour-Guided Multi-Head Attention Network From CT and MRI Images

Feiyan Li
Weisheng Li
Yidong Peng
Yucheng Shu

Heart image segmentation is a critical task in medical image processing, which is crucial for the diagnosis and treatment planning of cardiovascular diseases. It helps doctors understand patients’ cardiac anatomy and functional status more comprehensively and lays the foundation for personalized medicine and precision medicine research. Addressing the current challenges of rough surfaces on the entire heart, incomplete segmentation of heart substructures, and the lack of structured prediction of pulmonary arteries due to artifacts, scale diversity, uneven intensity, and boundary ambiguity in cardiac computed tomography (CT) and magnetic resonance imaging (MRI) images, we propose a whole heart segmentation algorithm based on 3D contour guided network. The proposed algorithm achieves robust whole heart segmentation results and has few network structure parameters. To enhance the consistency of features extracted by the codec, we propose a 3D codec information integration module to focus on task-related areas. In the final stage of information integration, features of different scales are combined. A 3D contour attention module enhances the perception of the heart’s structure and shape. Contour prediction results from the initial stage, generating a low-resolution voxel of the entire heart with contour details. The second stage builds upon the initial phase of secondary learning to achieve multi-label segmentation results. The proposed algorithm achieved average Dice scores of 0. 905 and 0. 865 for the CT and MRI modalities, respectively, in 40 cases.

Details DOI

JBHI Journal 2024 Journal Article

CGFTrans: Cross-Modal Global Feature Fusion Transformer for Medical Report Generation

Liming Xu
Quan Tang
Bochuan Zheng
Jiancheng Lv
Weisheng Li
Xianhua Zeng

Medical report generation, as a cross-modal automatic text generation task, can be highly significant both in research and clinical fields. The core is to generate diagnosis reports in clinical language from medical images. However, several limitations persist, including a lack of global information, inadequate cross-modal fusion capabilities, and high computational demands. To address these issues, we propose cross-modal global feature fusion Transformer (CGFTrans) to extract global information meanwhile reduce computational strain. Firstly, we introduce mesh recurrent network to capture inter-layer information at different levels to address the absence of global features. Then, we design feature fusion decoder and define ‘mid-fusion’ strategy to separately fuse visual and global features with medical report embeddings, which enhances the ability of the cross-modal joint learning. Finally, we integrate shifted window attention into Transformer encoder to alleviate computational pressure and capture pathological information at multiple scales. Extensive experiments conducted on three datasets demonstrate that the proposed method achieves average increments of 2. 9%, 1. 5%, and 0. 7% in terms of the BLEU-1, METEOR and ROUGE-L metrics, respectively. Besides, it achieves average increments −22. 4% and 17. 3% training time and images throughput, respectively.

Details DOI

AAAI Conference 2024 Conference Paper

Focus Stacking with High Fidelity and Superior Visual Effects

Bo Liu
Bin Hu
Xiuli Bi
Weisheng Li
Bin Xiao

Focus stacking is a technique in computational photography, and it synthesizes a single all-in-focus image from different focal plane images. It is difficult for previous works to produce a high-quality all-in-focus image that meets two goals: high-fidelity to its source images and good visual effects without defects or abnormalities. This paper proposes a novel method based on optical imaging process analysis and modeling. Based on a foreground segmentation - diffusion elimination architecture, the foreground segmentation makes most of the areas in full-focus images heritage information from the source images to achieve high fidelity; diffusion elimination models the physical imaging process and is specially used to solve the transition region (TR) problem that is a long-term neglected issue and degrades visual effects of synthesized images. Based on extensive experiments on simulated dataset, existing realistic dataset and our proposed BetaFusion dataset, the results show that our proposed method can generate high-quality all-in-focus images by achieving two goals simultaneously, especially can successfully solve the TR problem and eliminate the visual effect degradation of synthesized images caused by the TR problem.

PDF Details DOI

TCS Journal 2023 Journal Article

A unified greedy approximation for several dominating set problems

Hao Zhong
Yong Tang
Qi Zhang
Ronghua Lin
Weisheng Li

Minimum Dominating Set and Minimum Connected Dominating Set are classic graph problems that have been studied extensively in the literature. These two problems and their various variants are NP-hard in a general graph, and for some of them greedy approximation algorithms have been proposed. In this paper, by designing two potential functions that enjoy submodularity or a weak submodularity, we propose a unified O( ln ⁡ δ )-approximation algorithm for a generalized Minimum (Connected) Dominating Set that includes Minimum (Connected) Dominating Set, Minimum (Connected) Total Dominating Set, Minimum (Connected) *-Dominating Set and Minimum (Connected) Positive Influence Dominating Set, where δ is the maximum node degree of the input graph. For each specific version of the generalized Minimum (Connected) Dominating Set, the unified algorithm either matches the best one of existing approximation algorithms, or gives the first approximation solution.

Details DOI

JBHI Journal 2023 Journal Article

HS-Vectors: Heart Sound Embeddings for Abnormal Heart Sound Detection Based on Time-Compressed and Frequency-Expanded TDNN With Dynamic Mask Encoder

Lihong Qiao
Yonghao Gao
Bin Xiao
Xiuli Bi
Weisheng Li
Xinbo Gao

In recent years, auxiliary diagnosis technology for cardiovascular disease based on abnormal heart sound detection has become a research hotspot. Heart sound signals are promising in the preliminary diagnosis of cardiovascular diseases. Previous studies have focused on capturing the local characteristics of heart sounds. In this paper, we investigate a method for mapping heart sound signals with complex patterns to fixed-length feature embedding called HS-Vectors for abnormal heart sound detection. To get the full embedding of the complex heart sound, HS-Vectors are obtained through the Time-Compressed and Frequency-Expanded Time-Delay Neural Network(TCFE-TDNN) and the Dynamic Masked-Attention (DMA) module. HS-Vectors extract and utilize the global and critical heart sound characteristics by masking out irreverent information. Based on the TCFE-TDNN module, the heart sound signal within a certain time is projected into fixed-length embedding. Then, with a learnable mask attention matrix, DMA stats pooling aggregates multi-scale hidden features from different TCFE-TDNN layers and masks out irrelevant frame-level features. Experimental evaluations are performed on a 10-fold cross-validation task using the 2016 PhysioNet/CinC Challenge dataset and the new publicly available pediatric heart sound dataset we collected. Experimental results demonstrate that the proposed method excels the state-of-the-art models in abnormality detection.

Details DOI

AAAI Conference 2023 Conference Paper

Self-Supervised Image Local Forgery Detection by JPEG Compression Trace

Xiuli Bi
Wuqing Yan
Bo Liu
Bin Xiao
Weisheng Li
Xinbo Gao

For image local forgery detection, the existing methods require a large amount of labeled data for training, and most of them cannot detect multiple types of forgery simultaneously. In this paper, we firstly analyzed the JPEG compression traces which are mainly caused by different JPEG compression chains, and designed a trace extractor to learn such traces. Then, we utilized the trace extractor as the backbone and trained self-supervised to strengthen the discrimination ability of learned traces. With its benefits, regions with different JPEG compression chains can easily be distinguished within a forged image. Furthermore, our method does not rely on a large amount of training data, and even does not require any forged images for training. Experiments show that the proposed method can detect image local forgery on different datasets without re-training, and keep stable performance over various types of image local forgery.

PDF Details DOI

JBHI Journal 2022 Journal Article

A Novel Framework With Weighted Decision Map Based on Convolutional Neural Network for Cardiac MR Segmentation

Fei yan Li
Weisheng Li
Xinbo Gao
Bin Xiao

For diagnosing cardiovascular disease, an accurate segmentation method is needed. There are several unresolved issues in the complex field of cardiac magnetic resonance imaging, some of which have been partially addressed by using deep neural networks. To solve two problems of over-segmentation and under-segmentation of anatomical shapes in the short-axis view from different cardiac magnetic resonance sequences, we propose a novel two-stage framework with a weighted decision map based on convolutional neural networks to segment the myocardium (Myo), left ventricle (LV), and right ventricle (RV) simultaneously. The framework comprises a decision map extractor and a cardiac segmenter. A cascaded U-Net++ is used as a decision map extractor to acquire the decision map that decides the category of each pixel. Cardiac segmenter is a multiscale dual-path feature aggregation network (MDFA-Net) which consists of a densely connected network and an asymmetric encoding and decoding network. The input to the cardiac segmenter is derived from processed original images weighted by the output of the decision map extractor. We conducted experiments on two datasets of multi-sequence cardiac magnetic resonance segmentation challenge 2019 (MS-CMRSeg 2019) and myocardial pathology segmentation challenge 2020 (MyoPS 2020). Test results obtained on MyoPS 2020 show that the average Dice coefficients of the proposed method on the segmentation tasks of Myo, LV and RV are 84. 70%, 86. 00%, and 86. 31%, respectively.

Details DOI

JBHI Journal 2022 Journal Article

Medical Image Fusion and Denoising Algorithm Based on a Decomposition Model of Hybrid Variation-Sparse Representation

Guofen Wang
Weisheng Li
Jiao Du
Bin Xiao
Xinbo Gao

Medical image fusion technology integrates the contents of medical images of different modalities, thereby assisting users of medical images to better understand their meaning. However, the fusion of medical images corrupted by noise remains a challenge. To solve the existing problems in medical image fusion and denoising algorithms related to excessive blur, unclean denoising, gradient information loss, and color distortion, a novel medical image fusion and denoising algorithm is proposed. First, a new image layer decomposition model based on hybrid variation-sparse representation and weighted Schatten p-norm is proposed. The alternating direction method of multipliers is used to update the structure, detail layer dictionary, and detail layer coefficient map of the input image while denoising. Subsequently, appropriate fusion rules are employed for the structure layers and detail layer coefficient maps. Finally, the fused image is restored using the fused structure layer, detail layer dictionary, and detail layer coefficient maps. A large number of experiments confirm the superiority of the proposed algorithm over other algorithms. The proposed medical image fusion and denoising algorithm can effectively remove noise while retaining the gradient information without color distortion.

Details DOI

JBHI Journal 2022 Journal Article

Rubik-Net: Learning Spatial Information via Rotation-Driven Convolutions for Brain Segmentation

Xiao Luan
Xinyu zheng
Weisheng Li
Linghui Liu
Yucheng Shu
Yi Guo

The accurate segmentation of brain tissue in Magnetic Resonance Image (MRI) slices is essential for assessing neurological conditions and brain diseases. However, it is challenging to segment MRI slices because of the low contrast between different brain tissues and the partial volume effect. 2-Dimensional (2-D) convolutional networks cannot handle such volumetric image data well because they overlook spatial information between MRI slices. Although 3-Dimensional (3-D) convolutions capture volumetric spatial information, they have not been fully exploited to enhance representative ability of deep networks; moreover, they may lead to overfitting with insufficient training data. In this paper, we propose a novel convolutional mechanism, termed Rubik convolution, to capture multi-dimensional information between MRI slices. Rubik convolution rotates the axis of a set of consecutive slices, enabling 2-D convolution kernels to extract features of each axial plane simultaneously. Next, feature maps are rotated back to fuse multidimensional information by the Max-View-Maps. Furthermore, we propose an efficient 2-D convolutional network, namely Rubik-Net, where the residual connections and the bottleneck structure are used to enhance information transmission and reduce the number of network parameters. The Rubik-Net shows promising results on iSeg2017, iSeg2019, IBSR and BrainWeb datasets in terms of segmentation accuracy. In particular, we achieved the best results in 95th percentile Hausdorff distance and average surface distance in cerebrospinal fluid segmentation on the most challenging iSeg2019 dataset. The experiments indicate that Rubik-Net improves the accuracy and efficiency of medical image segmentation. Moreover, Rubik convolution can be easily embedded into existing 2-D convolutional networks.

Details DOI

JBHI Journal 2020 Journal Article

Three-Layer Image Representation by an Enhanced Illumination-Based Image Fusion Method

Jiao Du
Weisheng Li
Hengliang Tan

The recently developed multiscale-based fusion methods can be improved with two approaches: an advanced image decomposition scheme and an advanced fusion rule. In this paper, three-layer image decomposition, enhanced illumination fusion rule-based method is proposed. The proposed method includes three steps. First, each input image is decomposed into its corresponding smooth, texture, and edge layers using defined local extrema and low-pass filters in the spatial domain. Second, three different strategies are applied as fusion rules for the three-layer representation. To preserve the illumination closely related to tumors, the illumination is corrected by applying a higher contrast to the decomposed image details, including the texture and edge inputs, such as those found in grayscale CT and MRI images. The final fused image is created by the addition of the normalized smooth, texture, and edge image layers. The experiments demonstrate that the proposed method performs better than the existing state-of-the-art fusion methods.

Details DOI