Skip to Content
You are currently on the new version of our website. Access the old version .

49 Results Found

  • Article
  • Open Access
1 Citations
3,148 Views
22 Pages

5 August 2023

Recent advanced systems in the speech recognition domain use large Transformer neural networks that have been pretrained on massive speech data. General methods in the deep learning area have been frequently shared across various domains, and the Tra...

(This article belongs to the Special Issue Computational Intelligence and Human–Computer Interaction: Modern Methods and Applications, 2nd Edition)
  • Article
  • Open Access
2 Citations
5,366 Views
17 Pages

Patch-Wise-Based Self-Supervised Learning for Anomaly Detection on Multivariate Time Series Data

  • Seungmin Oh,
  • Le Hoang Anh,
  • Dang Thanh Vu,
  • Gwang Hyun Yu and ,
  • Minsoo Hahn and
  • Jinsul Kim
  • + 1 author+ 0 author

17 December 2024

Multivariate time series anomaly detection is a crucial technology to prevent unexpected errors from causing critical impacts. Effective anomaly detection in such data requires accurately capturing temporal patterns and ensuring the availability of a...

(This article belongs to the Special Issue Recent Advances in Time Series Analysis)
  • Article
  • Open Access
1 Citations
3,466 Views
14 Pages

20 September 2023

Fine-grained image recognition aims to classify fine subcategories belonging to the same parent category, such as vehicle model or bird species classification. This is an inherently challenging task because a classifier must capture subtle interclass...

(This article belongs to the Special Issue Advances in Neural Networks and Deep Learning)
  • Article
  • Open Access
1 Citations
3,098 Views
15 Pages

9 February 2023

Traditional learning-based multi-view stereo (MVS) methods usually need to find the correct depth value from a large number of depth candidates, which leads to huge memory consumption and slow inference. To address these problems, we propose a probab...

(This article belongs to the Topic Computer Vision and Image Processing)
  • Article
  • Open Access
24 Citations
6,736 Views
32 Pages

27 July 2023

A significant amount of research has investigated automating medical diagnosis using deep learning. However, because medical data are collected through diagnostic tests, deep learning methods used in existing studies have had a disadvantage in that t...

  • Article
  • Open Access
17 Citations
4,680 Views
23 Pages

18 November 2022

In recent years, supervised learning, represented by deep learning, has shown good performance in remote sensing image scene classification with its powerful feature learning ability. However, this method requires large-scale and high-quality handcra...

(This article belongs to the Special Issue Remote Sensing Image Processing with Transformers)
  • Article
  • Open Access
24 Citations
5,676 Views
18 Pages

Self-Supervised Point Set Local Descriptors for Point Cloud Registration

  • Yijun Yuan,
  • Dorit Borrmann,
  • Jiawei Hou,
  • Yuexin Ma and ,
  • Andreas Nüchter and
  • Sören Schwertfeger
  • + 1 author+ 0 author

12 January 2021

Descriptors play an important role in point cloud registration. The current state-of-the-art resorts to the high regression capability of deep learning. However, recent deep learning-based descriptors require different levels of annotation and select...

(This article belongs to the Special Issue Computer Vision for 3D Perception and Applications)
  • Article
  • Open Access
428 Views
25 Pages

23 September 2026

Self-supervised learning provides an effective way to reduce the dependence on manual annotations in remote sensing scene classification. However, existing self-supervised methods often emphasize either global semantic invariance or local structural...

(This article belongs to the Special Issue Deep Learning-Based Analysis of High-Resolution Remote Sensing Images: Registration, Fusion, and Change Detection)
  • Article
  • Open Access
1 Citations
3,974 Views
13 Pages

A Masked Self-Supervised Pretraining Method for Face Parsing

  • Zhuang Li,
  • Leilei Cao,
  • Hongbin Wang and
  • Lihong Xu

10 June 2022

Face Parsing aims to partition the face into different semantic parts, which can be applied into many downstream tasks, e.g., face mask up, face swapping, and face animation. With the popularity of cameras, it is easier to acquire facial images. Howe...

(This article belongs to the Special Issue Machine Learning and Statistical Modeling with Applications in Real-World Data and Artificial Intelligence)
  • Article
  • Open Access
3 Citations
3,000 Views
43 Pages

Glaucoma is a serious eye condition that damages the optic nerve and affects the transmission of visual information to the brain. It is the second leading cause of blindness worldwide. With deep learning, CAD systems have shown promising results in d...

(This article belongs to the Special Issue Advancing Healthcare Through Intelligent Clinical Decision Support Systems: Techniques, Applications, and Future Directions)
  • Article
  • Open Access
31 Citations
5,908 Views
16 Pages

AutoRet: A Self-Supervised Spatial Recurrent Network for Content-Based Image Retrieval

  • Muhammad Mostafa Monowar,
  • Md. Abdul Hamid,
  • Abu Quwsar Ohi,
  • Madini O. Alassafi and
  • M. F. Mridha

11 March 2022

Image retrieval techniques are becoming famous due to the vast availability of multimedia data. The present image retrieval system performs excellently on labeled data. However, often, data labeling becomes costly and sometimes impossible. Therefore,...

  • Article
  • Open Access
3 Citations
3,642 Views
20 Pages

SIM-MultiDepth: Self-Supervised Indoor Monocular Multi-Frame Depth Estimation Based on Texture-Aware Masking

  • Xiaotong Guo,
  • Huijie Zhao,
  • Shuwei Shao,
  • Xudong Li and ,
  • Baochang Zhang and
  • Na Li
  • + 1 author+ 0 author

19 June 2024

Self-supervised monocular depth estimation methods have become the focus of research since ground truth data are not required. Current single-image-based works only leverage appearance-based features, thus achieving a limited performance. Deep learni...

(This article belongs to the Special Issue Photogrammetry Meets AI)
  • Article
  • Open Access
1 Citations
1,337 Views
15 Pages

This study proposes an automated system using deep learning-based object detection to identify implant systems, leveraging recent progress in self-supervised learning, specifically masked image modeling (MIM). We advocate for self-pre-training, empha...

(This article belongs to the Section Medical Imaging)
  • Article
  • Open Access
469 Views
28 Pages

4 August 2026

Self-Supervised Learning (SSL) has attracted increasing attention in remote sensing image understanding because it can learn transferable representations from unlabeled images. However, two issues remain insufficiently examined in collaborative SSL f...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
71 Citations
10,350 Views
38 Pages

9 June 2020

Traditional change detection (CD) methods operate in the simple image domain or hand-crafted features, which has less robustness to the inconsistencies (e.g., brightness and noise distribution, etc.) between bitemporal satellite images. Recently, dee...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
22 Citations
5,854 Views
22 Pages

Improving Data-Efficiency and Robustness of Medical Imaging Segmentation Using Inpainting-Based Self-Supervised Learning

  • Jeffrey Dominic,
  • Nandita Bhaskhar,
  • Arjun D. Desai,
  • Andrew Schmidt and ,
  • Elka Rubin,
  • Beliz Gunel,
  • Garry E. Gold,
  • Brian A. Hargreaves,
  • Leon Lenchik and
  • Akshay S. Chaudhari
  • + 6 authors+ 1 author

We systematically evaluate the training methodology and efficacy of two inpainting-based pretext tasks of context prediction and context restoration for medical image segmentation using self-supervised learning (SSL). Multiple versions of self-superv...

(This article belongs to the Special Issue AI in MRI: Frontiers and Applications)
  • Article
  • Open Access
2 Citations
1,309 Views
18 Pages

Self-Supervised Cloud Classification with Patch Rotation Tasks (SSCC-PR)

  • Wuyang Yan,
  • Xiong Xiong,
  • Xinyuan Xia,
  • Yanchao Zhang and
  • Xiaojie Guo

16 August 2025

Solar irradiance, which is closely influenced by cloud cover, significantly affects photovoltaic (PV) power generation efficiency. To improve cloud type recognition without relying on labeled data tasks, this paper proposes a self-supervised cloud cl...

  • Proceeding Paper
  • Open Access
1 Citations
1,420 Views
11 Pages

Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging

  • Priyanka Pawar,
  • Anagha Kulkarni,
  • Bhavana Pansare,
  • Prajakta Pawar and ,
  • Prachi Bahekar and
  • Madhavi Kapre
  • + 1 author+ 0 author

Depigmented patches are the result of vitiligo, a skin condition brought on by the slow breakdown of melanocytes. High variability, complex lesion morphology, and subtle differences between affected and unaffected skin make accurate diagnosis difficu...

(This article belongs to the Proceedings of First International Conference on Computational Intelligence and Soft Computing (CISCom 2025))
  • Article
  • Open Access
1 Citations
651 Views
26 Pages

Deep Multimodal Phenotyping and Sensor Fusion for Preharvest Cotton Quality Assessment and Agricultural Economic Decision Support

  • Jingwen Luo,
  • Xintong Wang,
  • Shiguo Zhang,
  • Jiahe Zhang and ,
  • Ruobing Feng,
  • Xiuting Shu and
  • Shuo Yan
  • + 2 authors+ 0 author

15 July 2026

Cotton fiber quality is shaped during boll development, boll opening, fluffing, and harvesting, but current assessment still relies largely on manual field inspection and postharvest laboratory testing. This limits timely harvest scheduling and plot-...

(This article belongs to the Special Issue Intelligent Sensing and Digital Signal Processing in Smart Data)
  • Article
  • Open Access
9 Citations
9,050 Views
21 Pages

19 August 2024

Industrial anomaly detection is constrained by the scarcity of anomaly samples, limiting the applicability of supervised learning methods. Many studies have focused on anomaly detection by generating anomaly images and adopting self-supervised learni...

(This article belongs to the Special Issue State-of-the-Art of Computer Vision and Pattern Recognition)
  • Article
  • Open Access
10 Citations
3,771 Views
32 Pages

4 February 2022

Synthetic aperture radar (SAR) image change detection (CD) aims to automatically recognize changes over the same geographic region by comparing prechange and postchange SAR images. However, the detection performance is usually subject to several rest...

(This article belongs to the Special Issue Image Change Detection Research in Remote Sensing)
  • Article
  • Open Access
405 Views
13 Pages

29 June 2026

Self-supervised learning can reduce the dependence of 3D medical image analysis on expensive voxel-level annotations, but masked image modeling remains inefficient when uniform random masking is applied to volumetric data with large redundant backgro...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Technical Note
  • Open Access
22 Citations
6,493 Views
18 Pages

27 September 2022

This paper provides insights into the interpretation beyond simply combining self-supervised learning (SSL) with remote sensing (RS). Inspired by the improved representation ability brought by SSL in natural image understanding, we aim to explore and...

(This article belongs to the Special Issue Computational Intelligence for Remote Sensing Image Analysis and Applications)
  • Article
  • Open Access
5 Citations
2,735 Views
18 Pages

Partial Transfer Learning from Patch Transformer to Variate-Based Linear Forecasting Model

  • Le Hoang Anh,
  • Dang Thanh Vu,
  • Seungmin Oh,
  • Gwang-Hyun Yu and ,
  • Nguyen Bui Ngoc Han,
  • Hyoung-Gook Kim,
  • Jin-Sul Kim and
  • Jin-Young Kim
  • + 3 authors+ 0 author

21 December 2024

Transformer-based time series forecasting models use patch tokens for temporal patterns and variate tokens to learn covariates’ dependencies. While patch tokens inherently facilitate self-supervised learning, variate tokens are more suitable fo...

(This article belongs to the Special Issue Tiny Machine Learning for Energy Applications)
  • Article
  • Open Access
11 Citations
3,742 Views
12 Pages

Masked Image Modeling Meets Self-Distillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides

  • Haoyue Zhang,
  • Sushant Patkar,
  • Rosina Lis,
  • Maria J. Merino and ,
  • Peter A. Pinto,
  • Peter L. Choyke,
  • Baris Turkbey and
  • Stephanie Harmon
  • + 3 authors+ 0 author

21 November 2024

Detailed evaluation of prostate cancer glands is an essential yet labor-intensive step in grading prostate cancer. Gland segmentation can serve as a valuable preliminary step for machine-learning-based downstream tasks, such as Gleason grading, patie...

(This article belongs to the Section Methods and Technologies Development)
  • Article
  • Open Access
2 Citations
2,615 Views
17 Pages

Self-Supervised Learning and Multi-Sensor Fusion for Alpine Wetland Vegetation Mapping: Bayinbuluke, China

  • Muhammad Murtaza Zaka,
  • Alim Samat,
  • Jilili Abuduwaili,
  • Enzhao Zhu and ,
  • Arslan Akhtar and
  • Wenbo Li
  • + 1 author+ 0 author

13 October 2025

Accurate mapping of wetland vegetation is essential for ecological monitoring and conservation, yet it remains challenging due to the spatial heterogeneity of wetlands, the scarcity of ground-truth data, and the spread of invasive species. Invasive p...

(This article belongs to the Section Plant Modeling)
  • Article
  • Open Access
1 Citations
1,319 Views
37 Pages

5 May 2026

Video Anomaly Detection (VAD) is commonly formulated as a one-class classification task. Global motion, with temporal variations across most pixels within an object-centric region, e.g., walking, is typically regular, whereas localized motion, e.g.,...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
8 Citations
4,079 Views
20 Pages

3 October 2021

Random noise is unavoidable in seismic data acquisition due to anthropogenic impacts or environmental influences. Therefore, random noise suppression is a fundamental procedure in seismic signal processing. Herein, a deep denoising convolutional auto...

(This article belongs to the Special Issue New Methods and Technologies for Mineral Geological and Geophysical Exploration in China)
  • Article
  • Open Access
4 Citations
3,442 Views
15 Pages

16 May 2025

Skeleton representation learning offers substantial advantages for action recognition by encoding intricate motion details and spatial–temporal dependencies among joints. However, fully supervised approaches necessitate large amounts of annotat...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
12 Citations
4,808 Views
17 Pages

4 September 2023

This paper introduces a novel approach for self-supervised monocular depth estimation. The model is trained on stereo–image (left–right pair) data and incorporates carefully designed perceptual image quality assessment-based loss function...

(This article belongs to the Special Issue Advances in Computer Vision and Deep Learning and Its Applications)
  • Article
  • Open Access
1 Citations
2,481 Views
21 Pages

27 March 2023

High-dynamic-range (HDR) image synthesis is a technology developed to accurately reproduce the actual scene of an image on a display by extending the dynamic range of an image. Multi-exposure fusion (MEF) technology, which synthesizes multiple low-dy...

(This article belongs to the Special Issue Application of Machine Learning in Image Processing and Computer Vision)
  • Article
  • Open Access
10 Citations
4,780 Views
17 Pages

Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images

  • Yiqing Liu,
  • Qiming He,
  • Hufei Duan,
  • Huijuan Shi and ,
  • Anjia Han and
  • Yonghong He
  • + 1 author+ 0 author

13 August 2022

Tumor segmentation is a fundamental task in histopathological image analysis. Creating accurate pixel-wise annotations for such segmentation tasks in a fully-supervised training framework requires significant effort. To reduce the burden of manual an...

(This article belongs to the Special Issue Deep Learning for Pathology Detection and Diagnosis in Medical Imaging)
  • Article
  • Open Access
2 Citations
2,201 Views
32 Pages

Self-supervised learning (SSL) has gained significant attention in the past decade for its capacity to utilize non-annotated datasets to learn meaningful data representations. In the medical domain, the challenge of constructing large annotated datas...

(This article belongs to the Special Issue Deep Learning Methods and Application for Bioinformatics and Healthcare)
  • Article
  • Open Access
3 Citations
4,158 Views
14 Pages

30 October 2022

Solid developments have been seen in deep-learning-based pose estimation, but few works have explored performance in dense crowds, such as a classroom scene; furthermore, no specific knowledge is considered in the design of image augmentation for pos...

(This article belongs to the Special Issue Deep Learning Applications for Pose Estimation and Human Action Recognition)
  • Article
  • Open Access
1 Citations
4,018 Views
18 Pages

Unsupervised 3D Reconstruction with Multi-Measure and High-Resolution Loss

  • Yijie Zheng,
  • Jianxin Luo,
  • Weiwei Chen,
  • Yanyan Zhang and ,
  • Haixun Sun and
  • Zhisong Pan
  • + 1 author+ 0 author

23 December 2022

Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize th...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
5 Citations
2,155 Views
25 Pages

Topology-Aware Multi-View Street Scene Image Matching for Cross-Daylight Conditions Integrating Geometric Constraints and Semantic Consistency

  • Haiqing He,
  • Wenbo Xiong,
  • Fuyang Zhou,
  • Zile He and ,
  • Tao Zhang and
  • Zhiyuan Sheng
  • + 1 author+ 0 author

While deep learning-based image matching methods excel at extracting high-level semantic features from remote sensing data, their performance degrades significantly under cross-daylight conditions and wide-baseline geometric distortions, particularly...

(This article belongs to the Topic 3D Computer Vision and Smart Building and City, 3rd Edition)
  • Article
  • Open Access
625 Views
29 Pages

DGR-MAE: Posterior Semantic Correction Masked Autoencoder for Fine-Grained Aircraft Recognition Under Cloud Occlusion

  • Cong Liu,
  • Quanwei Gao,
  • Chenxi Song,
  • Bo Ouyang and ,
  • Ruyu Wang and
  • Hongtao Fan
  • + 1 author+ 0 author

4 June 2026

Fine-grained aircraft recognition in optical remote sensing imagery remains highly challenging under cloud occlusion, as visibility degradation causes structural information loss and weakens discriminative representation learning. To address this iss...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
12 Citations
3,241 Views
17 Pages

11 September 2024

Recently, transformers have demonstrated notable improvements in natural advanced visual tasks. In the field of computer vision, transformer networks are beginning to supplant conventional convolutional neural networks (CNNs) due to their global rece...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
6 Citations
3,636 Views
16 Pages

Multimodal Contrastive Learning for Remote Sensing Image Feature Extraction Based on Relaxed Positive Samples

  • Zhenshi Zhang,
  • Qiujun Li,
  • Wenxuan Jing,
  • Guangjun He and ,
  • Lili Zhu and
  • Shijuan Gao
  • + 1 author+ 0 author

3 December 2024

Traditional multimodal contrastive learning brings text and its corresponding image closer together as a positive pair, where the text typically consists of fixed sentence structures or specific descriptive statements, and the image features are gene...

(This article belongs to the Section Remote Sensors)
  • Article
  • Open Access
2 Citations
970 Views
26 Pages

Pseudo-Sample Generation and Self-Supervised Framework for Infrared Dim and Small Target Detection

  • Jinxin Guo,
  • Weida Zhan,
  • Dehua Huo,
  • Depeng Zhu and ,
  • Yu Chen,
  • Yichun Jiang and
  • Xiaoyu Xu
  • + 2 authors+ 0 author

28 November 2025

Infrared dim and small target detection is crucial for long-range sensing. However, its deep representation learning is severely constrained by the scarcity of accurately annotated real data, and related research remains underdeveloped. Existing data...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
3 Citations
2,301 Views
32 Pages

A Leakage-Aware Multimodal Machine Learning Framework for Nutrition Supply–Demand Forecasting Using Temporal and Spatial Data Fusion

  • Abdullah,
  • Muhammad Ateeb Ather,
  • Jose Luis Oropeza Rodriguez,
  • Carlos Guzmán Sánchez-Mejorada and ,
  • Miguel Jesús Torres Ruiz and
  • Rolando Quintero Tellez
  • + 1 author+ 0 author

Accurate forecasting of nutrition supply–demand dynamics is essential for reducing resource wastage and improving equitable allocation. However, this task remains challenging due to heterogeneous data sources, cold-start regions, and the risk o...

(This article belongs to the Special Issue AI in Bioinformatics)
  • Article
  • Open Access
2 Citations
565 Views
42 Pages

Floor-Count Estimation from Street-Level Imagery in Reinforced-Concrete Urban Construction: A Multi-Temporal Benchmark from Kazakhstan

  • Gulnara Bektemyssova,
  • Abdul Razaque,
  • Arman Keresh,
  • Malika Ziyada and ,
  • Ayagoz Saparkhankyzy,
  • Saltanat Nuralykyzy and
  • Mussa Uatbayev
  • + 2 authors+ 0 author

Monitoring the vertical progress of reinforced-concrete buildings supports construction management, urban analytics, and seismic exposure classification, yet camera-based floor counting faces two obstacles: public datasets depict almost exclusively c...

(This article belongs to the Section Construction Management, and Computers & Digitization)
  • Article
  • Open Access
1,949 Views
30 Pages

30 July 2025

Video temporal grounding (VTG) aims to localize a semantically relevant temporal segment within an untrimmed video based on a natural language query. The task continues to face challenges arising from cross-modal semantic misalignment, which is large...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
1 Citations
1,993 Views
24 Pages

Semi-Supervised Hyperspectral Reconstruction from RGB Images via Spectrally Aware Mini-Patch Calibration

  • Runmu Su,
  • Haosong Huang,
  • Hai Wang,
  • Zhiliang Yan and ,
  • Jingang Zhang and
  • Yunfeng Nie
  • + 1 author+ 0 author

29 January 2026

Hyperspectral reconstruction (SR) refers to the computational process of generating high-dimensional hyperspectral images (HSI) from low-dimensional observations. However, the superior performance of most supervised learning-based reconstruction algo...

  • Article
  • Open Access
2 Citations
1,967 Views
21 Pages

With the rapid development of multimodal prompt learning in unsupervised domains, prompt tuning has demonstrated significant potential for dense counting tasks. However, existing supervised methods heavily rely on annotated data, limiting their gener...

  • Article
  • Open Access
5 Citations
3,774 Views
21 Pages

MIMO-Uformer: A Transformer-Based Image Deblurring Network for Vehicle Surveillance Scenarios

  • Jian Zhang,
  • Baoping Cheng,
  • Tengying Zhang,
  • Yongsheng Zhao and ,
  • Tao Fu,
  • Zijian Wu and
  • Xiaoming Tao
  • + 2 authors+ 0 author

31 October 2024

Motion blur is a common problem in the field of surveillance scenarios, and it obstructs the acquisition of valuable information. Thanks to the success of deep learning, a sequence of CNN-based architecture has been designed for image deblurring and...

  • Article
  • Open Access
1,361 Views
14 Pages

HE-DMDeception: Adversarial Attack Network for 3D Object Detection Based on Human Eye and Deep Learning Model Deception

  • Pin Zhang,
  • Yawen Liu,
  • Heng Liu,
  • Yichao Teng and ,
  • Jiazheng Ni,
  • Zhuansun Xiaobo and
  • Jiajia Wang
  • + 2 authors+ 0 author

7 October 2025

This paper presents HE-DMDeception, a novel adversarial attack network that integrates human visual deception with deep model deception to enhance the security of 3D object detection. Existing patch-based and camouflage methods can mislead deep learn...

  • Article
  • Open Access
2,714 Views
12 Pages

15 July 2022

Person re-identification (Re-ID) aims to retrieve a specific pedestrian across a multi-disjoint camera in a surveillance system. Most of the research is based on a strong assumption that images should contain a full human torso. However, it cannot be...

(This article belongs to the Special Issue Recent Advances in Granular Computing for Intelligent Data Analysis)
  • Article
  • Open Access
7 Citations
2,933 Views
24 Pages

6 March 2025

Recurrent blooms of Ulva prolifera (U. prolifera) in the South Yellow Sea (SYS) have become a significant ecological and socio-economic challenge, disrupting marine ecosystems, aquaculture, and coastal tourism. Traditional methods for detecting and m...