Results 71 to 80 of about 843 (158)

Explainable Dual‐Stream Attention Network for Image Forgery Detection and Localisation Using Contrastive Learning

IET Radar, Sonar &Navigation, Volume 19, Issue 1, January/December 2025.
The model aims to tackle the forgeries observed in manipulated images. A dual‐stream contrastive learning network (DSCL‐Net) that jointly exploits spatial (pixel‐level) and frequency (noise‐level) cues was developed. ABSTRACT Image forgery detection aims to identify tampered content and localise manipulated regions within images.
Maryam Munawar, Mourad Oussalah
wiley   +1 more source

Contactless Health Monitoring: An Overview of Video‐Based Techniques Utilising Machine/Deep Learning

IET Wireless Sensor Systems, Volume 15, Issue 1, January/December 2025.
This review article presents a comprehensive examination of contactless health monitoring techniques utilising machine learning (ML) and deep learning (DL) algorithms for the assessment of critical vital signs. ABSTRACT Vital signs are crucial indicators of an individual's physiological well‐being and represent one of the primary evaluations conducted ...
Alaa Hajr, Bahram Tarvirdizadeh, Khalil Alipour, Mohammad Ghamari   +3 more
wiley   +1 more source

The Role of Time in Facial Dynamics and Challenges in Automatic Emotion Recognition (2019–2024)

Human Behavior and Emerging Technologies, Volume 2025, Issue 1, 2025.
Based on a comprehensive literature review, this study highlights the critical role of the temporal dimension of facial dynamics in understanding facial expressions and improving the accuracy and robustness of automatic emotion recognition systems (machine‐FER).
Williams Contreras-Higuera, Lucrezia Crescenzi-Lanna, Mirko Duradoni   +2 more
wiley   +1 more source

Brain Tumour Detection Using VGG‐Based Feature Extraction With Modified DarkNet‐53 Model

International Journal of Biomedical Imaging, Volume 2025, Issue 1, 2025.
The objective of AI research and development is to create intelligent systems capable of performing tasks and reasoning like humans. Artificial intelligence extends beyond pattern recognition, planning, and problem‐solving, particularly in the realm of machine learning, where deep learning frameworks play a pivotal role. This study focuses on enhancing
S. Trisheela, Roshan Fernandes, Anisha P. Rodrigues, S. Supreeth, B. J. Ambika, Piyush Kumar Pareek, Rakesh Kumar Godi, G. Shruthi, Francisco Gallegos-Funes   +8 more
wiley   +1 more source

A Scalable and Generalised Deep Learning Framework for Anomaly Detection in Surveillance Videos

International Journal of Intelligent Systems, Volume 2025, Issue 1, 2025.
Anomaly detection in videos is challenging due to the complexity, noise, and diverse nature of activities such as violence, shoplifting, and vandalism. While deep learning (DL) has shown excellent performance in this area, existing approaches have struggled to apply DL models across different anomaly tasks without extensive retraining.
Sabah Abdulazeez Jebur, Laith Alzubaidi, Ahmed Saihood, Khalid A. Hussein, Haider Kadhim Hoomod, YuanTong Gu, Mohamadreza (Mohammad) Khosravi   +6 more
wiley   +1 more source

A Frequency-Separated 3D-CNN for Hyperspectral Image Super-Resolution

IEEE Access, 2020
Considering the limitations such as cost, it is of great significance to use super-resolution methods to improve image spatial quality in the field of hyperspectral remote sensing.
Liguo Wang, Tianyi Bi, Yao Shi
doaj   +1 more source

Rapid maize seed vigor classification using deep learning and hyperspectral imaging techniques

Smart Agricultural Technology
Utilizing conventional methods to assess the seed quality is typically destructive and time-consuming. This research aimed to develop a robust and efficient framework for classifying maize seed vigor using hyperspectral imaging and deep learning.
Papis Wongchaisuwat, Pongsan Chakranon, Achitpon Yinpin, Damrongvudhi Onwimol, Kris Wonggasem   +4 more
doaj   +1 more source

Dynamic BdSL Digit Recognition using Hybrid 3DCNN+BiLSTM Model

International Journal For Multidisciplinary Research
Sign language is used as a way of communication by deaf and mute individuals. However, due to the limited number of people who understand sign language, integrating them into society is challenging. Approximately 6.9% of Bangladesh's population and 5% of the world’s population suffer from speech impediments.
Ishat Salsabil Silvia -, Kamrul Hasan Talukder -   +1 more
openaire   +1 more source

DDC3N: Doppler-Driven Convolutional 3D Network for Human Action Recognition

IEEE Access
In deep learning (DL)–based human action recognition (HAR), considerable strides have been undertaken. Nevertheless, the precise classification of sports athletes’ actions still needs to be completed.
Mukhiddin Toshpulatov, Wookey Lee, Suan Lee, Hoyoung Yoon, U Kang Kang   +4 more
doaj   +1 more source

A deep learning-based reconstruction model for 3D sound speed field combining underwater vertical information

Frontiers in Marine Science
IntroductionThe sound speed in the ocean significantly influences the propagation characteristics of underwater acoustic signals. Rapid acquisition of underwater three-dimensional (3D) sound speed fields is essential for target detection, acoustic ...
Hongchen Li, Yuhang Liu, Ming Li, Penghao Wang, Yuhang Zhu, Kefeng Mao, Xi Chen   +6 more
doaj   +1 more source