# Weakly-supervised Joint Anomaly Detection and Classification

arXiv: https://arxiv.org/abs/2108.08996 · HTML: https://mlsanity.com/paper/2108.08996/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 20 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [Street Scene: A new dataset and evaluation protocol for video anomaly detection](https://mlsanity.com/paper/1902.05872/) (2019)
- [GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection](https://mlsanity.com/paper/1908.05884/) (2019)
- [Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos](https://mlsanity.com/paper/1703.10664/) (2017)
- [Motion-Aware Feature for Improved Video Anomaly Detection](https://mlsanity.com/paper/1907.10211/) (2019)
- [3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos](https://mlsanity.com/paper/2002.01132/) (2020)

## Built on by (most cited first, 7 of 7)

- [Delving into CLIP latent space for Video Anomaly Recognition](https://mlsanity.com/paper/2310.02835/) (2023)
- [Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection](https://mlsanity.com/paper/2301.07923/) (2023)
- [RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2511.13204/) (2025)
- [SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions](https://mlsanity.com/paper/2207.11838/) (2022)
- [Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection](https://mlsanity.com/paper/2505.13123/) (2025)
- [FrameShield: Adversarially Robust Video Anomaly Detection](https://mlsanity.com/paper/2510.21532/) (2025)
- [General-Purpose Multi-Modal OOD Detection Framework](https://mlsanity.com/paper/2307.13069/) (2023)

## Abstract (arXiv)

Anomaly activities such as robbery, explosion, accidents, etc. need immediate actions for preventing loss of human life and property in real world surveillance systems. Although the recent automation in surveillance systems are capable of detecting the anomalies, but they still need human efforts for categorizing the anomalies and taking necessary preventive actions. This is due to the lack of methodology performing both anomaly detection and classification for real world scenarios. Thinking of a fully automatized surveillance system, which is capable of both detecting and classifying the anomalies that need immediate actions, a joint anomaly detection and classification method is a pressing need. The task of joint detection and classification of anomalies becomes challenging due to the unavailability of dense annotated videos pertaining to anomalous classes, which is a crucial factor for training modern deep architecture. Furthermore, doing it through manual human effort seems impossible. Thus, we propose a method that jointly handles the anomaly detection and classification in a single framework by adopting a weakly-supervised learning paradigm. In weakly-supervised learning instead of dense temporal annotations, only video-level labels are sufficient for learning. The proposed model is validated on a large-scale publicly available UCF-Crime dataset, achieving state-of-the-art results.