Related papers: Towards Privacy-Supporting Fall Detection via Deep…
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…
Human pose estimation is critical for applications such as rehabilitation, sports analytics, and AR/VR systems. However, rapid motion and low-light conditions often introduce motion blur, significantly degrading pose estimation due to the…
Cross-spectral biometrics, such as matching imagery of faces or persons from visible (RGB) and infrared (IR) bands, have rapidly advanced over the last decade due to increasing sensitivity, size, quality, and ubiquity of IR focal plane…
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on…
The labor-intensive nature of medical data annotation presents a significant challenge for respiratory disease diagnosis, resulting in a scarcity of high-quality labeled datasets in resource-constrained settings. Moreover, patient privacy…
Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…
The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of…
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are…
2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. However,…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
Differential privacy (DP) is considered as the gold standard for data privacy. While the problem of answering simple queries and functions under DP guarantees has been thoroughly addressed in recent years, the problem of releasing…
A fall is an abnormal activity that occurs rarely; however, missing to identify falls can have serious health and safety implications on an individual. Due to the rarity of occurrence of falls, there may be insufficient or no training data…
Consumer-level depth cameras and depth sensors embedded in mobile devices enable numerous applications, such as AR games and face identification. However, the quality of the captured depth is sometimes insufficient for 3D reconstruction,…
Multi-Dimensional time series classification and prediction has been widely used in many fields, such as disease prevention, fault diagnosis and action recognition. However, the traditional method needs manual intervention and inference,…
Automatic methods for detecting presentation attacks are essential to ensure the reliable use of facial recognition technology. Most of the methods available in the literature for presentation attack detection (PAD) fails in generalizing to…
Driver distraction remains a leading cause of road traffic accidents, contributing to thousands of fatalities annually across the globe. While deep learning-based driver activity recognition methods have shown promise in detecting such…
Temporal action detection aims to predict the time intervals and the classes of action instances in the video. Despite the promising performance, existing two-stream models exhibit slow inference speed due to their reliance on…
Due to the limited availability of paired multi-modal data, multi-modal trackers are typically built by adopting pre-trained RGB models with parameter-efficient fine-tuning modules. However, these fine-tuning methods overlook advanced…
Action monitoring in a home environment provides important information for health monitoring and may serve as input into a smart home environment. Visual analysis using cameras can recognise actions in a complex scene, such as someones…
Unintentional falls can cause severe injuries and even death, especially if no immediate assistance is given. The aim of Fall Detection Systems (FDSs) is to detect an occurring fall. This information can be used to trigger the necessary…