Academic Articles & Research Papers

Real-Time Fire Detection From Video Surveillance Cameras: Where Are We Now?

Automatic fire detection in video surveillance is a critical capability for safeguarding industrial sites, public infrastructures, and natural environments. Although recent advances in deep learning have substantially improved early fire de...

Spatially Aware Fusion in 3D Convolutional Autoencoders for Video Anomaly Detection

Surveillance videos are crucial for crime prevention and public safety, yet the challenge of defining abnormal events hinders their effectiveness, limiting the applicability of supervised methods. This paper introduces an unsupervised end-t...

Video Processing Using Deep Learning Techniques: A Systematic Literature Review

Studies show lots of advanced research on various data types such as image, speech, and text using deep learning techniques, but nowadays, research on video processing is also an emerging field of computer vision. Several surveys are presen...

A Video Frame Prediction Method Based on Latent-Space Autoregressive Modeling

Video prediction is a fundamental task in computer vision with broad applications in intelligent robotics, autonomous driving, and related fields. However, existing methods often struggle to simultaneously model long-term temporal dependenc...

Computer Vision for Human-Machine Interaction

Advances in the field of computer vision are leading to radical changes in the way we interact with computers. At the time of this book's publication in 1998, it would soon be possible to enable a computer linked to a video camera to detect...

Florence: A New Foundation Model for Computer Vision

Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on d...

Evaluating Adversarial Robustness of No-Reference Image and Video Quality Assessment Models with Frequency-Masked Gradient Orthogonalization Adversarial Attack

Neural-network-based models have made considerable progress in many computer vision areas over recent years. However, many works have exposed their vulnerability to malicious input data manipulation—that is, to adversarial attacks. Although...

Approaches to Improve the Quality of Person Re-Identification for Practical Use

The idea of the person re-identification (Re-ID) task is to find the person depicted in the query image among other images obtained from different cameras. Algorithms solving this task have important practical applications, such as illegal ...

A Lightweight Reconstruction Model via a Neural Network for a Video Super-Resolution Model

Super-resolution in image and video processing has been a challenge in computer vision, with its progression creating substantial societal ramifications. More specifically, video super-resolution methodologies aim to restore spatial details...

Per-Sample Multiple Kernel Approach for Visual Concept Learning

Learning visual concepts from images is an important yet challenging problem in computer vision and multimedia research areas. Multiple kernel learning (MKL) methods have shown great advantages in visual concept learning. As a visual concep...

Nature-based virtual backgrounds reduce mirror anxiety, hyper-gaze, and videoconference fatigue.

Comparing teacher-made and AI-assisted teaching videos for thyroid eye disease: an exploratory study.

Online visual tracking by integrating spatio‐temporal cues

The performance of online visual trackers has improved significantly, but designing an effective appearance‐adaptive model is still a challenging task because of the accumulation of errors during the model updating with newly obtained resul...

Monitoring pedestrian walking dynamics under environmental and policy influences in urban spaces

Abstract Understanding how environmental conditions and policy interventions jointly shape pedestrian mobility is essential for designing resilient, adaptive, and human-centered urban spaces. This study presents a computer-vision framework ...

Survey on Videos Data Augmentation for Deep Learning Models

In most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult ...

Computer Vision Face Tracking For Use in a Perceptual User Interface

As a first step towards a perceptual user interface, a computer vision color tracking algorithm is developed and applied towards tracking human faces. Computer vision algorithms that are intended to form part of a perceptual user interface ...

Gendered affective representations in AI-assisted music videos: a qualitative multimethod study.

Automated detection of bicycle helmets using deep learning

Bicycle helmets are a main measure for injury prevention in case of a crash and are a central variable in transport safety studies. Despite this, helmet use data is only collected sporadically, as the observation of helmet use in traffic by...

Deep learning based identification and tracking of railway bogie parts

The Train Rolling-Stock Examination (TRSE) is a safety examination process that physically examines the bogie parts of a moving train, typically at speeds over 30 km/h. Currently, this inspection process is done manually by railway personne...

The psychological impact of the Metaverse

Abstract The Metaverse is no revolution, but another step in the evolution of the internet. Today we can observe various 3D virtual worlds with different focuses and purposes, like meeting spaces, education, or classic gaming. Most of these...