| 1. |
- Acsintoae, Andra, et al.
(författare)
-
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
- 2022
-
Ingår i: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022). - : IEEE COMPUTER SOC. - 9781665469463 - 9781665469470 ; , s. 20111-20121
-
Konferensbidrag (refereegranskat)abstract
- Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal and abnormal events. In this scenario, anomaly detection is an open-set problem. However, some studies assimilate anomaly detection to action recognition. This is a closed-set scenario that fails to test the capability of systems at detecting new anomaly types. To this end, we propose UBnormal, a new supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, we introduce abnormal events annotated at the pixel level at training time, for the first time enabling the use of fully-supervised learning methods for abnormal event detection. To preserve the typical open-set formulation, we make sure to include dis-joint sets of anomaly types in our training and test collections of videos. To our knowledge, UBnormal is the first video anomaly detection benchmark to allow a fair head-to-head comparison between one-class open-set models and supervised closed-set models, as shown in our experiments. Moreover, we provide empirical evidence showing that UB-normal can enhance the performance of a state-of-the-art anomaly detection framework on two prominent data sets, Avenue and ShanghaiTech. Our benchmark is freely available at https://github.com/lilygeorgescu/UBnormal.
|
|
| 2. |
- Coroaba, Adina, et al.
(författare)
-
Probing the supramolecular features via π–π interaction of a di-iminopyrene-di-benzo-18-crown-6-ether compound : experimental and theoretical study
- 2020
-
Ingår i: RSC Advances. - : Royal Society of Chemistry (RSC). - 2046-2069. ; 10:63, s. 38304-38315
-
Tidskriftsartikel (refereegranskat)abstract
- A novel DPyDB-CN-18C6 compound was synthesised by linking a pyrene moiety to each phenyl group of dibenzo-18-crown-6-ether, the crown ether, through –HCN– bonds and characterized by FTIR, 1H-NMR, 13C-NMR, TGA, and DSC techniques. The quantitative 13C-NMR analysis revealed the presence of two position isomers. The electronic structure of the DPyDB-CN-18C6 molecule was characterized by UV-vis and fluorescence spectroscopies in four solvents with different polarities to observe particular behavior of isomers, as well as to demonstrate a possible non-bonding chemical association (such as ground- and excited-state associations, namely, to probe if there were forming dimers/excimers). The interpretation of the electronic structure was realized through QM calculations. The TD-CAM-B3LYP functional, at the 6-311+G(d,p) basis set, indicated the presence of predominant π → π* and mixed π → π* + n → π* transitions, in line with the UV-vis experimental data. Even though DPyDB-CN-18C6 computational studies revealed a π-extended conjugation effect with predominantly π → π* transitions, thorough fluorescence analysis was observed a weak emission, as an effect of PET and ACQ. In particular, the WAXD analysis of powder and thin films obtained from n-hexane, 1,2-dichloroethane, and ethanol indicated an amorphous organization, whereas from toluene a smectic ordering was obtained. These results were correlated with MD simulation, and it was observed that the molecular geometry of DPyDB-CN-18C6 molecule played a defining role in the pyrene stacking arrangement.
|
|
| 3. |
- Ma, Xiaoliang, Docent, et al.
(författare)
-
METRIC : Toward a Drone-based Cyber-Physical Traffic Management System
- 2022
-
Ingår i: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 3324-3329
-
Konferensbidrag (refereegranskat)abstract
- Drone-based system has a big potential to be applied for traffic monitoring and other advanced applications in Intelligent Transport Systems (ITS). This paper introduces our latest efforts of digitalising road traffic by various types of sensing systems, among which visual detection by drones provides a promising technical solution. A platform, called METRIC, is under recent development to carry out real-time traffic measurement and prediction using drone-based data collection. The current system is designed as a cyber-physical system (CPS) with essential functions aiming for visual traffic detection and analysis, real-time traffic estimation and prediction as well as decision supports based on simulation. In addition to the computer vision functions developed in the earlier stage, this paper also presents the CPS system architecture and the current implementation of the drone front-end system and a simulation-based system being used for further drone operations.
|
|
