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

1,595 Results Found

  • Article
  • Open Access
2 Citations
4,502 Views
18 Pages

3 July 2024

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point cloud...

(This article belongs to the Topic Computer Vision and Image Processing, 2nd Edition)
  • Article
  • Open Access
6 Citations
2,832 Views
22 Pages

5 April 2025

This study investigates the job competencies and training needs of net-zero sustainability management personnel in Taiwan, in response to increasing climate change and ESG-related challenges. Using the Importance-Performance Analysis (IPA) method, th...

  • Article
  • Open Access
4 Citations
1,506 Views
24 Pages

Zero-Shot Social Media Crisis Classification: A Training-Free Multimodal Approach

  • Franziska Schwarz,
  • Klaus Dieter Schwarz,
  • Daniel Arias Aranda,
  • Kendrick Bollens and ,
  • Navaneeth Shivananjappa,
  • Reiner Creutzburg and
  • Vesna Dimitrova
  • + 2 authors+ 0 author

25 February 2026

Rapid classification of social media content during humanitarian crises is essential for effective disaster relief; however, traditional approaches require extensive annotated training data, which are often unavailable during new disasters. This pape...

(This article belongs to the Special Issue New Advances in Cybersecurity Technology and Cybersecurity Management)
  • Article
  • Open Access
6 Citations
4,332 Views
18 Pages

12 August 2021

Brain–computer interfaces (BCIs) facilitate communication for people who cannot move their own body. A BCI system requires a lengthy calibration phase to produce a reasonable classifier. To reduce the duration of the calibration phase, it is natural...

(This article belongs to the Special Issue Brain–Computer Interfaces (BCI) and Application in Healthy and Daily Life Activities)
  • Article
  • Open Access
558 Views
36 Pages

28 September 2026

Generating accurately annotated training data remains a major bottleneck for deploying computer-vision-based sorting systems in heterogeneous waste streams. This work evaluates whether general-purpose zero-shot object detectors can reduce annotation...

(This article belongs to the Section Data Science for Chemistry, Energy and Materials)
  • Article
  • Open Access
2,997 Views
17 Pages

In the domain of artificial neural networks, it is important to know what their representation, classification and generalization capabilities are. There is also a need for time and resource-efficient training algorithms. Here, a new zero-error train...

  • Article
  • Open Access
4 Citations
4,885 Views
18 Pages

5 April 2024

Booming population and tourism have increased congestion, collisions, climate-harming emissions, and transport inequities in The Okanagan Valley, Canada. Surveys suggest that over 30% of residents would shift from cars back to public transit and inte...

(This article belongs to the Special Issue Inter-urban Zero-Emission Rail Technology: Analyses of Emerging Passenger and Freight Transportation System Retrofits)
  • Article
  • Open Access
480 Views
36 Pages

Trained Still Wins: Narrowing the Gap to Zero-Shot Video Anomaly Detection

  • Preet Kanwal,
  • Shylaja S. S and
  • Prasad B. Honnavalli

14 September 2026

Video anomaly detection has two very different answers to the question of how a detector should acquire its notion of “normal” for a given camera: adapt its parameters to hours of normal footage recorded by that exact camera, or perform n...

  • Article
  • Open Access
15 Citations
5,512 Views
18 Pages

30 January 2023

Chinese characters carry a wealth of morphological and semantic information; therefore, zero-shot Chinese character recognition with the morphology of Chinese characters has drawn significant attention. The previous methods are mainly based on radica...

(This article belongs to the Special Issue Innovative Technologies in Image Processing for Robot Vision)
  • Article
  • Open Access
29 Citations
7,556 Views
16 Pages

Vision-Language Models for Zero-Shot Classification of Remote Sensing Images

  • Mohamad Mahmoud Al Rahhal,
  • Yakoub Bazi,
  • Hebah Elgibreen and
  • Mansour Zuair

17 November 2023

Zero-shot classification presents a challenge since it necessitates a model to categorize images belonging to classes it has not encountered during its training phase. Previous research in the field of remote sensing (RS) has explored this task by tr...

(This article belongs to the Section Environmental Sciences)
  • Article
  • Open Access
24 Citations
4,947 Views
19 Pages

17 November 2023

The Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using...

(This article belongs to the Special Issue Artificial Intelligence and Complex Systems Analysis in Transportation and Maintenance)
  • Article
  • Open Access
63 Views
23 Pages

Exploring Text-Guided Wildlife Counting in Aerial Imagery Without Additional Training

  • Muming Zhao,
  • Zhongzheng Wang,
  • Xinyang Wang,
  • Fu Xu and
  • Xiaohui Cui

13 November 2026

Reliable wildlife counts support population assessment and conservation planning, while aerial imagery enables surveys over large or inaccessible areas. Most automated counting systems are developed for predefined animal categories and require retrai...

(This article belongs to the Topic Wildlife Intelligent Monitoring: Advancing Conservation Through Visual and Acoustic Monitoring Technologies)
  • Article
  • Open Access
59 Views
23 Pages

Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow

  • Guowen Zhu,
  • Xiancong Zhang,
  • Qingguo Xiao,
  • Jianda Cheng and
  • Hamim Mustafiz Zim

9 November 2026

Zero-shot image style transfer has recently attracted increasing attention, as it enables style manipulation without additional model optimization or parameter tuning. However, most existing approaches still rely on latent inversion, where introduced...

(This article belongs to the Special Issue Recent Progress and Challenges in Computer Vision and Machine Learning)
  • Article
  • Open Access
21 Citations
4,873 Views
14 Pages

Research on the Influence of Pantograph Catenary Contact Loss Arcs and Zero-Crossing Stage on Electromagnetic Disturbance in High-Speed Railway

  • Yixuan Yang,
  • Hefei Cao,
  • Mingzhi Zhang,
  • Zhiguo Su and ,
  • Man Hu,
  • Mengzhe Jin and
  • Shanghe Liu
  • + 2 authors+ 0 author

26 December 2023

During train travel, various factors, such as body vibration, uneven contact lines, and hard spots on carbon sliding plates and over electric neutral zones, often lead to brief separation between the pantograph and the contact line, i.e., the pantogr...

(This article belongs to the Section F: Electrical Engineering)
  • Article
  • Open Access
9 Citations
10,337 Views
35 Pages

Multimodal Data Fusion for Tabular and Textual Data: Zero-Shot, Few-Shot, and Fine-Tuning of Generative Pre-Trained Transformer Models

  • Shadi Jaradat,
  • Mohammed Elhenawy,
  • Richi Nayak,
  • Alexander Paz and ,
  • Huthaifa I. Ashqar and
  • Sebastien Glaser
  • + 1 author+ 0 author

7 April 2025

In traffic safety analysis, previous research has often focused on tabular data or textual crash narratives in isolation, neglecting the potential benefits of a hybrid multimodal approach. This study introduces the Multimodal Data Fusion (MDF) framew...

(This article belongs to the Section AI Systems: Theory and Applications)
  • Article
  • Open Access
1 Citations
3,165 Views
23 Pages

Reinforcement learning agents are highly susceptible to adversarial attacks that can severely compromise their performance. Although adversarial training is a common countermeasure, most existing research focuses on defending against single-type atta...

  • Article
  • Open Access
7 Citations
3,122 Views
13 Pages

Monocular 3D Tooltip Tracking in Robotic Surgery—Building a Multi-Stage Pipeline

  • Sanjeev Narasimhan,
  • Mehmet Kerem Turkcan,
  • Mattia Ballo,
  • Sarah Choksi and ,
  • Filippo Filicori and
  • Zoran Kostic
  • + 1 author+ 0 author

Tracking the precise movement of surgical tools is essential for enabling automated analysis, providing feedback, and enhancing safety in robotic-assisted surgery. Accurate 3D tracking of surgical tooltips is challenging to implement when using monoc...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
2 Citations
2,767 Views
14 Pages

19 March 2024

The lockdown during the pandemic questioned the learning and working conditions but underlined crucially the teaching pedagogy and new essential teachers’ roles and competencies, and on the whole, the operational framework of education for qual...

(This article belongs to the Special Issue School Management and Effectiveness)
  • Article
  • Open Access
1 Citations
3,293 Views
16 Pages

Zero-Shot Image Caption Inference System Based on Pretrained Models

  • Xiaochen Zhang,
  • Jiayi Shen,
  • Yuyan Wang,
  • Jiacong Xiao and
  • Jin Li

28 September 2024

Recently, zero-shot image captioning (ZSIC) has gained significant attention, given its potential to describe unseen objects in images. This is important for real-world applications such as human–computer interaction, intelligent education, and...

(This article belongs to the Section Electronic Multimedia)
  • Article
  • Open Access
5 Citations
3,412 Views
32 Pages

28 November 2023

Emotion recognition is a vital task within Natural Language Processing (NLP) that involves automatically identifying emotions from text. As the need for specialized and nuanced emotion recognition models increases, the challenge of fine-grained emoti...

(This article belongs to the Special Issue Applications, Challenges and Future Direction of Natural Language Processing Based on Deep Learning)
  • Article
  • Open Access
1 Citations
1,935 Views
15 Pages

2 June 2023

Under the Chinese “Zero-COVID” policy, many laborers were forced out of work. Participating in educational compensation can effectively help unemployed laborers achieve re-employment. This paper selected Jining, Shandong Province, as the...

(This article belongs to the Special Issue Professional Competency Development and Talent Cultivation Strategies for Sustainable Education in the Post-Pandemic Era)
  • Article
  • Open Access
341 Views
29 Pages

Zero-Sum Game-Based Finite-Time Robust Formation Tracking Control for Multi-Agent UAV Systems

  • Yuan Wang,
  • Mingqian Yang,
  • Zelong Yu,
  • Hanming Xu and ,
  • Rentong Xue,
  • Yixiang Cai and
  • Yu Zhang
  • + 2 authors+ 0 author

31 August 2026

This paper develops a distributed control framework for leader–follower formation tracking in multi-agent unmanned aerial vehicle (UAV) systems. Feedforward compensation converts the networked tracking task into local error stabilization proble...

(This article belongs to the Special Issue Cooperative Perception, Planning, and Control of Heterogeneous UAVs)
  • Feature Paper
  • Article
  • Open Access
3 Citations
3,067 Views
20 Pages

18 July 2024

The data used during training in any given application space are directly tied to the performance of the system once deployed. While there are many other factors that are attributed to producing high-performance models based on the Neural Scaling Law...

  • Article
  • Open Access
14 Citations
10,177 Views
20 Pages

Anomaly Detection and Classification in Predictive Maintenance Tasks with Zero Initial Training

  • Filippo Morselli,
  • Luca Bedogni,
  • Umberto Mirani,
  • Michele Fantoni and
  • Simone Galasso

9 October 2021

The Fourth Industrial Revolution has led to the adoption of novel technologies and methodologies in factories, making these more efficient and productive. Among the new services which are changing industry, there are those based on machine learning a...

(This article belongs to the Special Issue Industrial IoT as IT and OT Convergence: Challenges and Opportunities)
  • Article
  • Open Access
2 Citations
7,970 Views
16 Pages

Acute Effect of the “Zero Point” Method on Muscle Thickness and Muscle Damage in Trained Men

  • Thiago B. Trindade,
  • Ragami C. Alves,
  • Nuno Manuel Frade de Sousa,
  • Charles Lopes and ,
  • Bruno Magalhães de Castro,
  • Thiago S. Rosa and
  • Jonato Prestes
  • + 2 authors+ 0 author

22 December 2023

The “zero point” method allows for lower intensities for an exercise session without impairing the total training volume. This study aimed to compare the effects of the “zero point” versus the traditional method on muscle responses and muscle damage...

  • Article
  • Open Access
5 Citations
3,413 Views
17 Pages

11 August 2019

The Energy Performance Building Directive (EPBD) introduced the requirement for all Member States to include the concept of Nearly Zero Energy Buildings (NZEBs) in their national plans. However, this challenge requires upgrading professional skills i...

(This article belongs to the Collection Graduate Employment and Sustainability in a Global and Changing Labour Market: Challenges and Opportunities for Higher Education)
  • Article
  • Open Access
1 Citations
1,028 Views
31 Pages

7 August 2026

Waste management on university campuses is complicated by the constant change in packaging types, which existing waste-sorting systems cannot recognise unless they are retrained. Open-vocabulary object detectors can identify objects from text descrip...

(This article belongs to the Section AI in Autonomous Systems)
  • Article
  • Open Access
4 Citations
2,898 Views
24 Pages

Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application

  • Petros Gkertzos,
  • Johannes Gerritzen,
  • Constantinos Tsakonas,
  • Stefanos H. Panagiotou and ,
  • Athanasios Kotzakolios,
  • Ioannis Katsidimas,
  • Andreas Hornig,
  • Siavash Ghiasvand,
  • Maik Gude and
  • Sotiris Nikoletseas
  • + 6 authors+ 1 author

Modern impact monitoring systems combine multiple inputs with machine learning (ML) models for impact detection, localization, and event assessment. Their accuracy relies on large, event-representative datasets, used for algorithmic development and M...

  • Article
  • Open Access
14 Citations
4,753 Views
24 Pages

18 October 2021

This paper addresses the issue of incorporating rail transport into an urban delivery system. Its main purpose was to identify the possibilities of utilising rail transport in a Zero-emission Urban Delivery System (ZUDS) by applying Light Freight Rai...

(This article belongs to the Special Issue High Efficiency Electric Freight Vehicle)
  • Article
  • Open Access
1 Citations
566 Views
27 Pages

Current building energy benchmarking relies on annual Energy Use Intensity (EUI), which cannot detect temporal operational anomalies—such as after-hours equipment operation or irregular scheduling—that represent actionable efficiency oppo...

(This article belongs to the Section Building Energy, Physics, Environment, and Systems)
  • Article
  • Open Access
1 Citations
2,091 Views
25 Pages

Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresse...

(This article belongs to the Special Issue Advances of Artificial Intelligence and Vision Applications, 2nd Edition)
  • Article
  • Open Access
8 Citations
3,337 Views
22 Pages

Ensuring Explainability and Dimensionality Reduction in a Multidimensional HSI World for Early XAI-Diagnostics of Plant Stress

  • Maxim Lysov,
  • Konstantin Pukhkiy,
  • Evgeny Vasiliev,
  • Alexandra Getmanskaya and
  • Vadim Turlapov

15 May 2023

This work is mostly devoted to the search for effective solutions to the problem of early diagnosis of plant stress (given an example of wheat and its drought stress), which would be based on explainable artificial intelligence (XAI). The main idea i...

(This article belongs to the Special Issue Uncertainty in Large Neural Systems: Validation, Explanation and Correction of Multidimensional Intelligence in a Multidimensional World)
  • Article
  • Open Access
1,122 Views
19 Pages

26 February 2025

Prior elicitation is an important issue in both subjective and objective Bayesian frameworks, where prior distributions impose certain information on parameters before data are observed. Caution is warranted when utilizing noninformative priors for h...

(This article belongs to the Section D1: Probability and Statistics)
  • Article
  • Open Access
1,849 Views
18 Pages

Low-light object detection remains challenging because insufficient illumination obscures visual features and increases the discrepancy between training and testing conditions. Existing approaches often rely on detector redesign, image enhancement, o...

(This article belongs to the Section Computer Vision and Pattern Recognition)
  • Article
  • Open Access
4 Citations
1,569 Views
23 Pages

Evaluating the environmental perception of urban parks is highly significant for optimizing urban planning. To address the limitations of traditional evaluation methods, a multimodal deep learning framework that integrates pre-training and reinforcem...

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

1 October 2026

Generative Artificial Intelligence (GenAI) is driving a fundamental paradigm shift in architectural design, transitioning from deterministic drafting to algorithmic curation. While the Architecture, Engineering, and Construction (AEC) sector rapidly...

(This article belongs to the Topic Architectural Education)
  • Article
  • Open Access
11 Citations
7,625 Views
16 Pages

Computer games have been regarded as an important field of artificial intelligence (AI) for a long time. The AlphaZero structure has been successful in the game of Go, beating the top professional human players and becoming the baseline method in com...

(This article belongs to the Special Issue Applications of Computational Intelligence)
  • Article
  • Open Access
12 Citations
3,361 Views
12 Pages

Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes). A well-known problem in Deep Learning (DL) is the requirement fo...

  • Article
  • Open Access
3,241 Views
30 Pages

BoxesZero: An Efficient and Computationally Frugal Dots-and-Boxes Agent

  • Xuefen Niu,
  • Qirui Liu,
  • Wei Chen,
  • Yujiao Zheng and
  • Zhanggen Jin

9 March 2025

In recent years, deep reinforcement learning (DRL) has made significant progress in the field of games. A prime example is AlphaZero, which, despite the formidable capabilities showcased, deters many from exploring its potential because of its demand...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
33 Citations
8,592 Views
21 Pages

The Effectiveness of Zero-Day Attacks Data Samples Generated via GANs on Deep Learning Classifiers

  • Nikolaos Peppes,
  • Theodoros Alexakis,
  • Evgenia Adamopoulou and
  • Konstantinos Demestichas

12 January 2023

Digitization of most of the services that people use in their everyday life has, among others, led to increased needs for cybersecurity. As digital tools increase day by day and new software and hardware launch out-of-the box, detection of known exis...

(This article belongs to the Special Issue Network Security and IoT Security)
  • Article
  • Open Access
3 Citations
4,416 Views
18 Pages

2 August 2019

Traditional supervised learning is dependent on the label of the training data, so there is a limitation that the class label which is not included in the training data cannot be recognized properly. Therefore, zero-shot learning, which can recognize...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
8 Citations
5,431 Views
17 Pages

Analysis of the Railway Accident-Related Damages in South Korea

  • Man Sik Park,
  • Jin Ki Eom,
  • Jungsoon Choi and
  • Tae-Young Heo

8 December 2020

Railway accidents are critical issues characterized by a large number of injuries and fatalities per accident due to massive public transport systems. This study proposes a new approach for evaluating the damages resulting from railway accidents usin...

  • Article
  • Open Access
1,375 Views
17 Pages

A 3D-Printed Home-Based Arthroscopic Simulator Improves Basic Surgical Skills: A Prospective Comparative Multicentre Study

  • Marco Montemagno,
  • Luigi Zaffarana,
  • Flora Maria Chiara Panvini,
  • Ludovico Lucenti and ,
  • Alessandra Di Nora,
  • Egidio Avarotti,
  • Angelo Di Giunta,
  • Gianluca Testa and
  • Vito Pavone
  • + 4 authors+ 0 author

Objectives: Arthroscopic surgery requires complex visuospatial coordination and psychomotor skills, which are traditionally acquired through mentorship and cadaveric training. High-fidelity simulators are effective but often costly and inaccessible....

(This article belongs to the Special Issue Current Horizons in Orthopaedic Surgery: Innovations, Outcomes, and Complication Management)
  • Article
  • Open Access
6 Citations
3,372 Views
18 Pages

15 November 2024

Path planning for robots based on reinforcement learning encounters challenges in integrating semantic information about environments into the training process. In unseen or complex environmental information, agents often perform sub-optimally and re...

(This article belongs to the Section Actuators for Surface Vehicles)
  • Article
  • Open Access
3,342 Views
18 Pages

10 March 2025

The Contrastive Language–Image Pretraining (CLIP) model has demonstrated remarkable zero-shot capabilities through contrastive learning on large-scale text-image datasets, sparking interest in developing continuous learning methods to extend it...

  • Article
  • Open Access
5 Citations
3,742 Views
14 Pages

15 August 2023

Zero-shot semantic segmentation (ZS3), the process of classifying unseen classes without explicit training samples, poses a significant challenge. Despite notable progress made by pre-trained vision-language models, they have a problem of “supe...

(This article belongs to the Special Issue Advances in Swarm Intelligence, Data Science and Their Applications, 2nd Edition)
  • Article
  • Open Access
49 Citations
10,704 Views
24 Pages

29 December 2018

Biometric verification systems have become prevalent in the modern world with the wide usage of smartphones. These systems heavily rely on storing the sensitive biometric data on the cloud. Due to the fact that biometric data like fingerprint and iri...

  • Feature Paper
  • Article
  • Open Access
2,313 Views
23 Pages

9 November 2022

The multilingual neural machine translation (NMT) model can handle translation between more than one language pair. From the perspective of industrial applications, the modularized multilingual NMT model (M2 model) that only shares modules between th...

(This article belongs to the Special Issue Artificial Neural Networks: Design and Applications)
  • Article
  • Open Access
1 Citations
2,347 Views
21 Pages

Spectral De-Aliasing Method of Micro-Motion Signals Based on a Complex-Valued U-Net Network

  • Ming Long,
  • Jun Yang,
  • Saiqiang Xia,
  • Mingjiu Lv and ,
  • Bolin Cheng and
  • Wenfeng Chen
  • + 1 author+ 0 author

31 August 2023

Spectrum aliasing occurs in signal echoes when the sampling frequency does not comply with the Nyquist Sampling Theorem. In this scenario, the extraction of micro-motion parameters becomes challenging. This paper proposes a spectral de-aliasing metho...

(This article belongs to the Special Issue Doppler Radar: Signal, Data and Applications)
  • Article
  • Open Access
1,125 Views
17 Pages

11 August 2025

Traditional machine learning methods only classify the instances whose classes are seen during training. In practice, many applications require to recognize the classes unknown in the training stage. In order to tackle this kind of challenging task,...

(This article belongs to the Section A: Computer Science)

of 32