BFBin Fu

Bin Fu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bin Fu has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    SAM-Med3D: A Vision Foundation Model for General-Purpose Segmentation on Volumetric Medical Images

    by Haoyu Wang, Sizheng Guo, Jin Ye, Zhongying Deng, Junlong Cheng, Tianbin Li, Jianpin Chen, Yanzhou Su, Ziyan Huang, Yiqing Shen, et al.

    Existing volumetric medical image segmentation models are typically task-specific, excelling at specific targets but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this article, we introduce segment anything model (SAM)-Med3D, a vision foundation model (VFM) for general-purpose segmentation on volumetric medical images. Given only a few 3-D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and preprocess a large-scale 3-D medical image segmentation dataset, SA-Med3D-140K, from 70 public datasets and 8K licensed private cases from hospitals. This dataset includes 22K 3-D images and 143K corresponding masks. SAM-Med3D, a promptable segmentation model characterized by its fully learnable 3-D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation demonstrates the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pretrained model. Our approach illustrates that substantial medical resources can be harnessed to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at: https://github.com/uni-medical/SAM-Med3D


  • Open Access

    Deformation Robust Text Spotting with Geometric Prior

    by Xixuan Hao, Aozhong Zhang, Xianze Meng, Bin Fu

    The goal of text spotting is to perform text detection and recognition in an end-to-end manner. Although the diversity of luminosity and orientation in scene texts has been widely studied, the font diversity and shape variance of the same character are ignored in recent works, since most characters in natural images are rendered in standard fonts. To solve this problem, we present a Chinese Artistic Dataset, termed as ARText, which contains 33,000 artistic images with rich shape deformation and font diversity. Based on this database, we develop a deformation robust text spotting method (DR TextSpotter) to solve the recognition problem of complex deformation of characters in different fonts. Specifically, we propose a geometric prior module to highlight the important features based on the unsupervised landmark detection sub-network. A graph convolution network is further constructed to fuse the character features and landmark features, and then performs semantic reasoning to enhance the discrimination for different characters. The experiments are conducted on ARText and IC19-ReCTS datasets. Our results demonstrate the effectiveness of our proposed method.

  • Learning Task-Aligned Mask Query for Instance Segmentation

    by Bin Fu, Hongliang He, Pengxu Wei, Jie Chen

    Recently, query-based instance segmentation methods have achieved comparable performance to previous state-of-the-art methods. However, the query lacks the learning of the consistency between classification and segmentation tasks, which may lead to misalignment between classification score and mask quality (i.e., mask IoU) and can not result in a reliable ranking for predictions. In this work, we propose a novel instance segmentation method, termed AlignMask, which effectively learns task-aligned mask queries for instance end-toend. Specifically, we propose Aligned Query Learning (AQL) to learn task-aligned features for pixel embedding and transformer decoder, which helps segmentation quality estimation of the mask query. We also use Aligned Label Assignment to explicitly align the optimization goals for classification score and mask quality of the query. Extensive experiments on MSCOCO show that our proposed AlignMask achieves competitive performance with state-of-the-art models.


  • Open Access

    Learning Variational Motion Prior for Video-based Motion Capture

    by Xin Chen, Zhuo Su, Lingbo Yang, Pei Cheng, Lan Xu, Bin Fu, Gang Yu

    Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with challenging cases involving self-occlusion and complex poses due to the lack of effective motion prior modeling. In this paper, we present a novel variational motion prior (VMP) learning approach for video-based motion capture to resolve the above issue. Instead of directly building the correspondence between the video and motion domain, We propose to learn a generic latent space for capturing the prior distribution of all natural motions, which serve as the basis for subsequent video-based motion capture tasks. To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality. Afterward, a separate video encoder is attached to the pretrained motion generator for end-to-end fine-tuning over task-specific video datasets. Compared to existing motion prior models, our VMP model serves as a motion rectifier that can effectively reduce temporal jittering and failure modes in frame-wise pose estimation, leading to temporally stable and visually realistic motion capture results. Furthermore, our VMP-based framework models motion at sequence level and can directly generate motion clips in the forward pass, achieving real-time motion capture during inference. Extensive experiments over both public datasets and in-the-wild videos have demonstrated the efficacy and generalization capability of our framework.

  • Region-Aware Arbitrary-Shaped Text Detection With Progressive Fusion

    by Qitong Wang, Bin Fu, Ming Li, Junjun He, Xi Peng, Yu Qiao

    Segmentation-based text detectors are flexible to capture arbitrary-shaped text regions. Due to large geometry variance, it is necessary to construct effective and robust representations to identify text regions with various shapes and scales. In this paper, we focus on designing effective multi-scale contextual features for locating text instances. Specially, we develop a Region Context Module (RCM) to summarize the semantic response and adaptively extract text-region-aware information in a limited local area. To construct complementary multi-scale contextual representations, multiple RCM branches with different scales are employed and integrated via Progressive Fusion Module (PFM). Our proposed RCM and PFM serve as the plug-and-play modules which can be incorporated into existing scene text detection platforms to further boost detection performance. Extensive experiments show that our methods achieve state-of-the-art performances on Total-Text, SCUT-CTW1500 and MSRA-TD500 datasets. The code with models will become publicly available at https://github.com/wqtwjt1996/RP-Text.


  • Dual Relation Network for Scene Text Recognition

    by Ming Li, Bin Fu, Han Chen, Junjun He, Yu Qiao

    Local visual and long-range contextual features yield two complementary cues for human reading text in natural scene. Existing scene text recognition methods mainly extract local features in low level features and then model long-range dependencies in high level, this sequential pipeline may be sub-optimal to construct complete and effective representation. Except for high level features, long-range contextual relation is of importance in low level features as well since it can help separate different characters based on the intervals between characters and thus enhance the features in character area. To address this issue, we develop a dual relation module to extract complementary features in a parallel manner for scene text recognition. Dual relation module consists of a local visual branch and a long-range contextual branch from low level to high level. The local visual branch employs a topological-aware operation to model intra-character characteristic and extract discriminative features of different characters. Meanwhile, the long-range contextual branch utilizes a simple but effective strategy to incorporate inter-character relations into feature maps. Our dual relation module is a plug-and-play block which can be easily incorporated into modern deep architectures. Experimental results demonstrate that our methods achieved top performance on several standard benchmarks. Code and models will become publicly available in the future.


  • Character-Aware Sampling and Rectification for Scene Text Recognition

    by Ming Li, Bin Fu, Zhengfu Zhang, Yu Qiao

    Curved scene text recognition is a challenging task due to large shape and texture variance. Previous methods address this challenge by extracting and rectifying text line with equidistantly sampling, which ignore character level information and lead to distorted characters. To address this issue, this paper proposes a Character-Aware Sampling and Rectification (CASR) module, which rectifies irregular text instance according to the location and orientation information of each individual character. Specifically, CASR regards each character as a basic unit and predicts the character-level attributes for sampling and rectification. Our module not only exploits detailed character information to obtain better rectification of text line, but also employs character-level supervision in training process. In addition, CASR provides a plug-and-play module which can be easily incorporated to existing text recognition pipeline. Extensive experiments on several benchmarks demonstrate that our method obtains more accurate rectified text instances and achieves promising performance.


  • 5G Core Network Framework Based on Artificial Intelligence

    by Shiyu Zhou, Xiqing Liu, Dengsheng Fu, Xinzhou Cheng, Bin Fu, Zhenqiao Zhao

    The fifth generation mobile communication (5G) core network refers to the service-based architecture, which poses a great challenge to the traditional operation and maintenance. Network artificial intelligence is an important direction of technology development. Based on researching progress of the related standards about network intelligence, this paper proposes a novel intelligent operation architecture of 5G core network, and introduces the key features. Then we study intelligent application scenarios, and discuss the opportunities and challenges of realizing intelligent 5G network.


  • AMP-based Detector for Uplink OFDM-IDMA with Carrier Frequency Offset

    by Ranran He, Jiesi Kang, Yue Xiao, Bin Fu

    In this paper, we propose an efficient approximate message passing (AMP) based detector for uplink orthogonal frequency division multiplexing-interleave division multiple access (OFDM-IDMA) systems. Analysis and simulation results show that the proposed detector is capable of providing lower computational complexity and better bit error rate (BER) performance than the conventional elementary signal estimator (ESE) conceived for IDMA systems. Furthermore, the carrier frequency offset (CFO) between the transmitter and the receiver in the uplink OFDM-IDMA is considered for practical systems. Based on the proposed AMP detector, an effective detection scheme is further proposed to mitigate the influence of CFO.

  • Base Station Selection for Cache-enabled Wireless Networks

    by Yucheng Liao, Ruimeng Gan, Yue Xiao, Ping Yang, Bin Fu

    Caching contents in the small base station (SBS) is expected as a class of promising techniques in an effort to mitigate the congestion problem for future cellular networks. In this paper, we consider a heterogeneous cellular network with storage capable SBSs, and focus our attention on the SBS selection problem, in order to achieve balanced cost including incurred serving cost and users' experienced delay. The numerical results show that the location of SBS has an impact on the delay and servicing cost, which should be carefully decided in system design.