Work

Street Scene: A new dataset and evaluation protocol for video anomaly detection

Year: 2020
Type: conference-paper
Abstract: Progress in video anomaly detection research is currently slowed by small datasets that lack a wide variety of activities as well as flawed evaluation criteria. This paper aims to help move this research effort forward by introducing a large and varied new dataset called Street Scene, as well as two new evaluation criteria that provide a better estimate of how an algorithm will perform in practice. In addition to the new dataset and evaluation criteria, we present two variations of a novel baseline video anomaly detection algorithm and show they are much more accurate on Street Scene than two well known algorithms from the literature.
Language: English
Open Access status: green
OpenAlex ID: W2913669686
FWCI: 8.318
Cites: 41
Cited by: 266
Related to: 10