Related papers: Identifying Earth-impacting asteroids using an art…
Human-Object Interaction (HOI) detection is a longstanding computer vision problem concerned with predicting the interaction between humans and objects. Current HOI models rely on a vocabulary of interactions at training and inference time,…
This chapter is on the security assessment of artificial intelligence (AI) and neural network (NN) accelerators in the face of fault injection attacks. More specifically, it discusses the assets on these platforms and compares them with…
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being…
We introduce NEOviz, an interactive visualization system designed to assist planetary defense experts in the visual analysis of the movements of near-Earth objects in the Solar System that might prove hazardous to Earth. Asteroids are often…
Detecting human-object interaction (HOI) has long been limited by the amount of supervised data available. Recent approaches address this issue by pre-training according to pseudo-labels, which align object regions with HOI triplets parsed…
Asteroids can be considered as sources of contamination of point sources and also sources of confusion noise, depending whether their presence is detected in the image or their flux is under the detection limit. We estimate that at low…
Human-Object Interaction (HOI) detection aims to learn how human interacts with surrounding objects. Previous HOI detection frameworks simultaneously detect human, objects and their corresponding interactions by using a predictor. Using…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
Developing a rapid, but also reliable and efficient, method for classifying the seismic damage potential of buildings constructed in countries with regions of high seismicity is always at the forefront of modern scientific research. Such a…
The asteroidal main belt is crossed by a web of mean-motion and secular resonances, that occur when there is a commensurability between fundamental frequencies of the asteroids and planets. Traditionally, these objects were identified by…
We have conducted a detailed simulation of LSST's ability to link near-Earth and main belt asteroid detections into orbits. The key elements of the study were a high-fidelity detection model and the presence of false detections in the form…
We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on `HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these…
This study evaluates the performance of several machine learning models for predicting hazardous near-Earth objects (NEOs) through a binary classification framework, including data scaling, power transformation, and cross-validation. Six…
Technology has advanced to the point that it is possible to image the entire sky every night and process the data in real time. The sky is hardly static: many interesting phenomena occur, including variable stationary objects such as stars…
As of mid-2026, 11 objects have been discovered prior to impacting the Earth, with warning times between 2 - 20 hours. Using real metre-sized Earth impactors from the last decade, we ask the question: ``If the Vera C. Rubin Observatory's…
In recent years, understanding asteroids has shifted from light worlds to geological worlds by exploring modern spacecraft and advanced radar and telescopic surveys. However, flyby in 2029 will be an opportunity to conduct an internal…
The human brain can recognize objects hidden in even severely degraded images after observing them for a while, which is known as a type of Eureka effect, possibly associated with human creativity. A previous psychological study suggests…
Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research…
The proliferation of IoT devices which can be more easily compromised than desktop computers has led to an increase in the occurrence of IoT based botnet attacks. In order to mitigate this new threat there is a need to develop new methods…
Threat modelling is the process of identifying potential vulnerabilities in a system and prioritising them. Existing threat modelling tools focus primarily on technical systems and are not as well suited to interpersonal threats. In this…