Detecting Rare Events Using a One-Class Classifier Based on Diffusion Autoencoders
Abstract/Contents
- Abstract
- Existing video anomaly detection methods frequently use image models, extrapolated to frame-level, to detect anomalies in video data. These methods have shown reasonable success on standard benchmark datasets; however, such techniques largely rely on hand-crafted features or pre-determined assumptions about the dataset. For example, they may limit anomalies to specific types, such as person-centric or object-centric, or presume that frame-level information can capture the anomalies present in the dataset. In this paper, we introduce an approach using Diffusion Autoencoders (DiffAEs) for video anomaly detection.
Description
| Type of resource | text |
|---|---|
| Publication date | September 11, 2023 |
Creators/Contributors
| Author | Prakash, Eva |
|---|
Subjects
| Subject | anomalydetection |
|---|---|
| Genre | Text |
| Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International license (CC BY-NC).
Preferred citation
- Preferred citation
- Prakash, E. (2023). Detecting Rare Events Using a One-Class Classifier Based on Diffusion Autoencoders. Stanford Digital Repository. Available at https://purl.stanford.edu/tg080zf7035. https://doi.org/10.25740/tg080zf7035.
Collection
Undergraduate Theses, School of Engineering
View other items in this collection in SearchWorksContact information
- Contact
- eprakash@stanford.edu
Also listed in
Loading usage metrics...