dam-anomaly-detection

[AVSS21 Oral] A framework consisting of Dissimilarity Attention Module (DAM) to discriminate the anomaly instances from normal ones both at feature level and score level. In order to decide instances to be normal or anomaly, DAM takes local spatio-temporal (i.e. clips within a video) dissimilarities into account rather than the global temporal context of a video.

https://github.com/snehashismajhi/dam-anomaly-detection

Last synced: 6 months ago · JSON representation ·

Repository

[AVSS21 Oral] A framework consisting of Dissimilarity Attention Module (DAM) to discriminate the anomaly instances from normal ones both at feature level and score level. In order to decide instances to be normal or anomaly, DAM takes local spatio-temporal (i.e. clips within a video) dissimilarities into account rather than the global temporal context of a video.

Basic Info

Host: GitHub
Owner: snehashismajhi
Language: Python
Default Branch: main
Homepage:
Size: 530 KB

Statistics

Stars: 6
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created over 4 years ago · Last pushed over 3 years ago

Metadata Files

Readme Citation

README.md

Dissimilarity-Attention-Module-for-Weakly-supervised-Video-Anomaly Detection

Video anomaly detection under weak supervision is complicated due to the difficulties in identifying the anomaly and normal instances during training, hence, resulting in non-optimal margin of separation. In this paper, we propose a framework consisting of Dissimilarity Attention Module (DAM) to discriminate the anomaly instances from normal ones both at feature level and score level. In order to decide instances to be normal or anomaly, DAM takes local spatio-temporal (i.e. clips within a video) dissimilarities into account rather than the global temporal context of a video. This allows the framework to detect anomalies in real-time (i.e. online) scenarios without the need of extra window buffer time. Further more, we adopt two-variants of DAM for learning the dissimilarity between the successive video clips. The proposed framework along with DAM is validated on two large scale anomaly detection datasets i.e. UCF-Crime and ShanghaiTech, outperforming the online state-of-the-art approaches by 1.5% and 3.4% respectively.

Proposed Framework

Prposed Framework

DAM: Dissimilarity Attention Module

DAM

State-of-the-art Performance Comparision on UCF-Crime Dataset

SOTA

Citing DAM

@inproceedings{9663810, author={Majhi, Snehashis and Das, Srijan and Brémond, François}, booktitle={2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)}, title={DAM: Dissimilarity Attention Module for Weakly-supervised Video Anomaly Detection}, year={2021}, volume={}, number={}, pages={1-8}, doi={10.1109/AVSS52988.2021.9663810}}

Owner

Name: Snehashis Majhi
Login: snehashismajhi
Kind: user
Location: Valbonne
Company: INRIA Sophia Antipolis France

Website: https://www.linkedin.com/in/snehashis-majhi-49211a13a/
Repositories: 1
Profile: https://github.com/snehashismajhi

R&D Engineer || INRIA Sophia Antipolis France || Spatio-Temporal Activity Recognition Systems (STARS) Team

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this work, please cite it as below."
authors:
- family-names: "Majhi"
  given-names: "Snehashis"
title: "DAM-Anomaly-Detection"
version: 1.0.0
date-released: 2022-02-13
url: "https://github.com/snehashismajhi/DAM-Anomaly-Detection"
preferred-citation:
  type: data
  authors:
  - family-names: "Majhi"
    given-names: "Snehashis"
  - family-names: "Das"
    given-names: "Srijan"
  - family-names: "Brémond"
    given-names: "François"
  doi: "10.1109/AVSS52988.2021.9663810"
  Conference: "2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"
  title: "DAM: Dissimilarity Attention Module for Weakly-supervised Video Anomaly Detection"
  year: 2021

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science