FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212899624> ?p ?o ?g. }

• W3212899624 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." @default.
• W3212899624 created "2021-11-22" @default.
• W3212899624 creator A5012173946 @default.
• W3212899624 creator A5018046137 @default.
• W3212899624 creator A5031359013 @default.
• W3212899624 creator A5053878590 @default.
• W3212899624 creator A5065862728 @default.
• W3212899624 creator A5079112987 @default.
• W3212899624 creator A5080823547 @default.
• W3212899624 creator A5081017623 @default.
• W3212899624 date "2022-06-01" @default.
• W3212899624 modified "2023-10-13" @default.
• W3212899624 title "UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection" @default.
• W3212899624 cites W1522734439 @default.
• W3212899624 cites W1957718552 @default.
• W3212899624 cites W1967456674 @default.
• W3212899624 cites W2012931101 @default.
• W3212899624 cites W2015461918 @default.
• W3212899624 cites W2021659075 @default.
• W3212899624 cites W2122361470 @default.
• W3212899624 cites W2138092272 @default.
• W3212899624 cites W2163612318 @default.
• W3212899624 cites W2164261375 @default.
• W3212899624 cites W2164489414 @default.
• W3212899624 cites W2220258027 @default.
• W3212899624 cites W2254513182 @default.
• W3212899624 cites W2341058432 @default.
• W3212899624 cites W2523332653 @default.
• W3212899624 cites W2540481276 @default.
• W3212899624 cites W2587789887 @default.
• W3212899624 cites W2763384612 @default.
• W3212899624 cites W2777342313 @default.
• W3212899624 cites W2901114541 @default.
• W3212899624 cites W2904013130 @default.
• W3212899624 cites W2921491036 @default.
• W3212899624 cites W2962793481 @default.
• W3212899624 cites W2963111876 @default.
• W3212899624 cites W2963610939 @default.
• W3212899624 cites W2963795951 @default.
• W3212899624 cites W2964232409 @default.
• W3212899624 cites W2964331599 @default.
• W3212899624 cites W2972156365 @default.
• W3212899624 cites W2981638912 @default.
• W3212899624 cites W2981741013 @default.
• W3212899624 cites W2987146532 @default.
• W3212899624 cites W2987228832 @default.
• W3212899624 cites W3015608037 @default.
• W3212899624 cites W3017679580 @default.
• W3212899624 cites W3022606336 @default.
• W3212899624 cites W3024238458 @default.
• W3212899624 cites W3034292309 @default.
• W3212899624 cites W3035240825 @default.
• W3212899624 cites W3035699237 @default.
• W3212899624 cites W3035802502 @default.
• W3212899624 cites W3042642865 @default.
• W3212899624 cites W3082213779 @default.
• W3212899624 cites W3090744585 @default.
• W3212899624 cites W3092920241 @default.
• W3212899624 cites W3093119843 @default.
• W3212899624 cites W3096857588 @default.
• W3212899624 cites W3103592385 @default.
• W3212899624 cites W3110474347 @default.
• W3212899624 cites W3134961575 @default.
• W3212899624 cites W3136793533 @default.
• W3212899624 cites W3138834599 @default.
• W3212899624 cites W3168600998 @default.
• W3212899624 cites W3168984673 @default.
• W3212899624 cites W3184731081 @default.
• W3212899624 cites W3185010842 @default.
• W3212899624 cites W3190318906 @default.
• W3212899624 cites W3192880336 @default.
• W3212899624 cites W3194047006 @default.
• W3212899624 cites W3202590754 @default.
• W3212899624 cites W3202896130 @default.
• W3212899624 cites W3207605004 @default.
• W3212899624 cites W4214751560 @default.
• W3212899624 doi "https://doi.org/10.1109/cvpr52688.2022.01951" @default.
• W3212899624 hasPublicationYear "2022" @default.
• W3212899624 type Work @default.
• W3212899624 sameAs 3212899624 @default.
• W3212899624 citedByCount "12" @default.
• W3212899624 countsByYear W32128996242022 @default.
• W3212899624 countsByYear W32128996242023 @default.
• W3212899624 crossrefType "proceedings-article" @default.
• W3212899624 hasAuthorship W3212899624A5012173946 @default.
• W3212899624 hasAuthorship W3212899624A5018046137 @default.
• W3212899624 hasAuthorship W3212899624A5031359013 @default.
• W3212899624 hasAuthorship W3212899624A5053878590 @default.
• W3212899624 hasAuthorship W3212899624A5065862728 @default.
• W3212899624 hasAuthorship W3212899624A5079112987 @default.
• W3212899624 hasAuthorship W3212899624A5080823547 @default.
• W3212899624 hasAuthorship W3212899624A5081017623 @default.
• W3212899624 hasBestOaLocation W32128996242 @default.
• W3212899624 hasConcept C118615104 @default.
• W3212899624 hasConcept C119857082 @default.
• W3212899624 hasConcept C121332964 @default.
• W3212899624 hasConcept C12267149 @default.
• W3212899624 hasConcept C124101348 @default.
• W3212899624 hasConcept C12997251 @default.
• W3212899624 hasConcept C13280743 @default.

• next