Related papers: Validation of Advanced EM Models for UXO Discrimin…
Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This dominance stems from the limited scalability of existing…
This paper proposes a novel edge computing enabled real-time video analysis system for intelligent visual devices. The proposed system consists of a tracking-assisted object detection module (TAODM) and a region of interesting module…
Object Detection on the mobile system is a challenge in terms of everything. Nowadays, many object detection models have been designed, and most of them concentrate on precision. However, the computation burden of those models on mobile…
We design a Universal Automatic Elbow Detector (UAED) for deciding the effective number of components in model selection problems. The relationship with the information criteria widely employed in the literature is also discussed. The…
This article addresses the problem of multi-object tracking by using a non-deterministic model of target behaviors with hard constraints. To capture the evolution of target features as well as their locations, we permit objects to lie in a…
Rutherford backscattering and particle induced x-ray emission have been utilized to precisely characterize targets used in nuclear fission experiments. The method allows for a fast and non destructive determination of target thickness,…
This paper presents a preliminary study of an efficient object tracking approach, comparing the performance of two different 3D point cloud sensory sources: LiDAR and stereo cameras, which have significant price differences. In this…
This paper introduces extremum seeking (ES) algorithms designed to achieve perfect tracking of arbitrary time-varying extremum. In contrast to classical ES approaches that employ constant frequencies and controller gains, our algorithms…
Face anti-spoofing researches are widely used in face recognition and has received more attention from industry and academics. In this paper, we propose the EulerNet, a new temporal feature fusion network in which the differential filter…
Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to arbitrary patient pose and mesh resolution variation. Existing task-specific mesh and point-cloud methods are not…
Inverse problems describe the task of recovering an underlying signal of interest given observables. Typically, the observables are related via some non-linear forward model applied to the underlying unknown signal. Inverting the non-linear…
Radio Frequency (RF) sensing is attracting interest in research, standardization, and industry, especially for its potential in Internet of Things (IoT) applications. By leveraging the properties of the ElectroMagnetic (EM) waves used in…
Advances in machine learning have boosted the use of Earth observation data for climate change research. Yet, the interpretability of machine-learned representations remains a challenge, particularly in understanding forests' biophysical…
This paper addresses the problem of real-time detection and tracking of a non-cooperative target in the challenging scenario with almost no a-priori information about target birth, death, dynamics and detection probability. Furthermore,…
Relative state estimation using exteroceptive sensors suffers from limitations of the field of view (FOV) and false detection, that the proprioceptive sensor (IMU) data are usually engaged to compensate. Recently ego-motion constraint…
Latent variable models are a fundamental modeling tool in machine learning applications, but they present significant computational and analytical challenges. The popular EM algorithm and its variants, is a much used algorithmic tool; yet…
We present a study on the efficacy of adversarial training on transformer neural network models, with respect to the task of detecting check-worthy claims. In this work, we introduce the first adversarially-regularized, transformer-based…
In this study, we introduce ExBEHRT, an extended version of BEHRT (BERT applied to electronic health records), and apply different algorithms to interpret its results. While BEHRT considers only diagnoses and patient age, we extend the…
This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…
The Expectation Maximisation (EM) algorithm is widely used to optimise non-convex likelihood functions with latent variables. Many authors modified its simple design to fit more specific situations. For instance, the Expectation (E) step…