Article
Engineering, Electrical & Electronic
Mu Chen, Pengfei Liu, Huaici Zhao
Summary: The object detection task in autonomous driving scenario relies on complex visual sensor systems. An improvement has been made for efficient 3D object detection task using a monocular sensor with geometric constraints. A Geometric Appearance Awareness (GAA) module is proposed to improve orientation estimation, while a Sample-aware Feature Fusion (SFF) head is designed for 3D dimension regression. The proposed method achieves significant improvements in the 3D object detection task on the KITTI dataset.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Xiang Ming, Fangyun Wei, Ting Zhang, Dong Chen, Fang Wen, Nanning Zhen
Summary: This paper examines the performance of single-layer detectors based on deep learning in detecting multi-scale objects and concludes that the balance of training samples at different scales is crucial. The authors propose a group sampling method and demonstrate its effectiveness through extensive experiments. The research also shows that the method is applicable to other tasks and detection pipelines.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Engineering, Electrical & Electronic
Jing Zhang, Rui Zhao, Zhenwei Shi, Ning Zhang, Xinzhong Zhu
Summary: In order to improve the performance of hyperspectral target detectors, it is necessary to have an accurate and consistent prior target spectrum. Existing algorithms assume a highly reliable prior target spectrum, but in practice, labels may not always be precise and different pixels of the same object may have different spectra. The proposed Bayesian constrained energy minimization (B-CEM) method infers the posterior distribution of the true target spectrum based on the prior target spectrum, using the Dirichlet distribution to approximate the true target spectrum in hyperspectral images. Experimental results show the effectiveness of the B-CEM method when dealing with noisy or inconsistent known target spectra, proving the necessity of approximating the true target spectrum. The distributional estimate achieves better performance than using the known target spectrum directly.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Tao Xu, Xian Sun, Wenhui Diao, Liangjin Zhao, Kun Fu, Hongqi Wang
Summary: The study introduces an efficient feature aligned single-shot detector to address the feature misalignment issue in object detection, achieving promising experimental results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Hongrui Zhang, Shaocheng Qu, Huan Li, Wenjun Xu, Xiaona Du
Summary: This paper introduces a motion-appearance-aware network (MAAN) for learning robust feature representations, and proposes a fusion module that extracts information at multiple time scales, facilitates global communication and local guidance, and develops strategies for obtaining uniform and consistent moving objects.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Geochemistry & Geophysics
Lukui Shi, Linyi Kuang, Xia Xu, Bin Pan, Zhenwei Shi
Summary: In this study, we propose a feature pyramid-based remote sensing object detector called Centerness-Aware Network (CANet), which captures the symmetrical shape of objects in remote sensing images. CANet integrates Multiscale Centerness Descriptor (MSCD), Centerness Detection Head (CDH), and Feature Selective Module (FSM) into the feature pyramid to extract and utilize features around the center region. Experiments show that CANet is competitive with some state-of-the-art detection networks.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Hao Wang, Qilong Wang, Hongzhi Zhang, Jian Yang, Wangmeng Zuo
Summary: Well-annotated training samples are crucial for achieving high performance in object detection, but collecting massive samples is laborious and costly. Cut-paste based methods have shown potential to augment training samples, but ensuring quality of synthetic images remains a challenge. This paper proposes a novel Constrained Online Cut-Paste (COCP) method to effectively and efficiently augment training data for improving object detection performance. The method switches instances of the same class from various image pairs in each training mini-batch, ensuring context coherence and implementing constraints based on geometric consistency and sample diversity to enhance the quality of synthetic images. The experiments demonstrate that COCP outperforms existing methods and can be applied across different datasets and detectors with clear performance gains.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Geochemistry & Geophysics
Dong Liang, Qixiang Geng, Zongqi Wei, Dmitry A. Vorontsov, Ekaterina L. Kim, Mingqiang Wei, Huiyu Zhou
Summary: In this article, the authors propose a novel training sample generator called DEA-Net for small object detection. The method leverages a sample discriminator and multi-task joint training to improve the performance of the model. Extensive experiments demonstrate that the proposed method achieves state-of-the-art results on aerial datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Ibrahim Soliman Mohamed, Lim Kim Chuan
Summary: Multi-object tracking is an important field in computer vision that plays a critical role in video analysis in various applications. This study proposes a novel approach to improve the performance of object detection and tracking by extracting appearance features. Additionally, a new training framework is introduced to reduce the human labeling effort and increase the adoption rate in real-world applications.
Article
Engineering, Civil
Wei Chen, Jie Zhao, Wan-Lei Zhao, Song-Yuan Wu
Summary: This paper proposes a single-stage monocular 3D object detection model that integrates an instance-segmentation head into the model training, allowing the model to be aware of the visible shape of a target object and avoid interference from irrelevant regions surrounding the target objects.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xiaoli Yang, Min Zhao, Shuaikai Shi, Jie Chen
Summary: This paper proposes a nonlinear detector formulation by generalizing the conventional constrained energy minimization method and designs novel nonlinear detectors with two deep neural network structures. Experimental results show that the proposed method outperforms other competing hyperspectral target detection algorithms.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Xin Li, Shenqi Lai, Xueming Qian
Summary: This paper proposes a simple yet efficient face detection method called DBCFace, which solves the face detection problem using a dual branch fully convolutional framework without extra anchor design and NMS. Extensive experiments show that DBCFace achieves comparable performance to state-of-the-art methods with faster speed.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Lu Zhang, Zhiyong Liu, Xiangyu Zhu, Zhan Song, Xu Yang, Zhen Lei, Hong Qiao
Summary: The article proposes a multimodal detector named AR-CNN to tackle the position shift problem, including RF alignment module, RoI jitter strategy, and feature fusion method. Extensive experiments demonstrate the effectiveness and robustness of the method in 2-D and 3-D object detection, RGB-T, and RGB-D datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Chao Xu, Jiangning Zhang, Mengmeng Wang, Guanzhong Tian, Yong Liu
Summary: This paper proposes a Multi-level Spatial-Temporal (MST) feature aggregation framework to address the challenges in video object detection. The framework fully exploits spatial-temporal features at frame level, proposal level, and instance level, and introduces a Deformable Feature Alignment (DAlign) module to improve pixel-level spatial alignment for feature aggregation.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Geochemistry & Geophysics
Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, Junwei Han
Summary: This article proposes a novel anchor-free oriented proposal generator (AOPG) to address issues in oriented object detection caused by the use of horizontal boxes. The effectiveness of AOPG is demonstrated through extensive experiments, and a new dataset, DIOR-R, is released to alleviate the problem of data insufficiency.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Rheumatology
Terence W. O'Neill, Matthew J. Parkes, Nasimah Maricar, Elizabeth J. Marjanovic, Richard Hodgson, Andrew D. Gait, Timothy F. Cootes, Charles E. Hutchinson, David T. Felson
ANNALS OF THE RHEUMATIC DISEASES
(2016)
Correction
Orthopedics
A. D. Gait, R. Hodgson, M. J. Parkes, C. E. Hutchinson, T. W. O'Neill, N. Maricar, E. J. Marjanovic, T. F. Cootes, D. T. Felson
OSTEOARTHRITIS AND CARTILAGE
(2017)
Article
Rheumatology
Luca Minciullo, Matthew J. Parkes, David T. Felson, Timothy F. Cootes
ANNALS OF THE RHEUMATIC DISEASES
(2018)
Article
Multidisciplinary Sciences
John A. Shepherd, Bennett K. Ng', Bo Fan, Ann V. Schwartz, Peggy Cawthon, Steven R. Cummings, Stephen Kritchevsky, Michael Nevitt, Adam Santanasto, Timothy F. Cootes
Article
Multidisciplinary Sciences
Claudia Lindner, Ching-Wei Wang, Cheng-Ta Huang, Chung-Hsing Li, Sheng-Wei Chang, Tim F. Cootes
SCIENTIFIC REPORTS
(2016)
Article
Radiology, Nuclear Medicine & Medical Imaging
Thomas A. Perry, Andrew Gait, Terence W. O'Neill, Matthew J. Parkes, Richard Hodgson, Michael J. Callaghan, Nigel K. Arden, David T. Felson, Timothy F. Cootes
MAGNETIC RESONANCE IN MEDICINE
(2019)
Article
Multidisciplinary Sciences
R. Storchi, J. Rodgers, M. Gracey, F. P. Martial, J. Wynne, S. Ryan, C. J. Twining, T. F. Cootes, R. Killick, R. J. Lucas
SCIENTIFIC REPORTS
(2019)
Article
Biochemistry & Molecular Biology
Riccardo Storchi, Nina Milosavljevic, Annette E. Allen, Antonio G. Zippo, Aayushi Agnihotri, Timothy F. Cootes, Robert J. Lucas
Article
Computer Science, Artificial Intelligence
Xinghui Dong, Chris J. Taylor, Tim F. Cootes
Summary: This study introduces an unsupervised local deep feature learning method based on image segmentation, aiming to extract useful features from images. By utilizing pseudo-labels and training algorithms with deep convolutional neural networks, the proposed unsupervised method achieves performance close to supervised learning.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Endocrinology & Metabolism
Benjamin G. Faber, Raja Ebsim, Fiona R. Saunders, Monika Frysz, Claudia Lindner, Jennifer S. Gregory, Richard M. Aspden, Nicholas C. Harvey, George Davey Smith, Timothy Cootes, Jonathan H. Tobias
Summary: This study investigated the relationship between radiographic hip osteoarthritis (rHOA) and hip pain using a novel method. The results showed that 2-dimensional osteophyte area was significantly associated with hip pain, while minimum joint space width (mJSW) was not. Furthermore, osteophyte areas at different locations were independently associated with hip pain, potentially reflecting distinct biomechanical pathways.
Article
Automation & Control Systems
Xinghui Dong, Christopher J. Taylor, Tim F. Cootes
Summary: In the aerospace manufacturing industry, an automatic inspection system has been developed to identify defects in linear thin welds, aiming to reduce the workload for human inspectors. Experimental results show that the system can accurately locate welds and detect 80% of defects. Additionally, the system produces promising results on publicly available data sets.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Orthopedics
B. E. Zucker, R. Ebsim, C. Lindner, S. Hardcastle, T. Cootes, J. H. Tobias, M. R. Whitehouse, C. L. Gregson, B. G. Faber, A. E. Hartley
Summary: The study found an association between cam morphology and radiographic hip osteoarthritis in individuals with high bone mass, but no association between cam morphology and incident osteoarthritis. High bone mass and cam morphology confer risks of osteoarthritis through distinct pathways.
BMC MUSCULOSKELETAL DISORDERS
(2022)
Article
Automation & Control Systems
Xinghui Dong, Christopher J. Taylor, Tim F. Cootes
Summary: This study proposes a multitask deep one-class CNN for defect classification, eliminating the need for abnormal images and annotated data during training, and utilizing feature representation learning from normal images. The approach outperforms counterparts trained using a two-stage method in defect detection, achieving results nearly as good as the supervised method without using annotated data. The promising results are attributed to the advantages of multitask learning.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2022)
Proceedings Paper
Engineering, Biomedical
Luca Minciullo, Jessie Thomson, Timothy F. Cootes
MEDICAL IMAGING 2017: COMPUTER-AIDED DIAGNOSIS
(2017)
Proceedings Paper
Computer Science, Theory & Methods
Raja Ebsim, Jawad Naqvi, Tim Cootes
COMPUTER ASSISTED AND ROBOTIC ENDOSCOPY AND CLINICAL IMAGE-BASED PROCEDURES
(2017)
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)