Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/fjchange/awesome-video-anomaly-detection
Papers for Video Anomaly Detection, released codes collection, Performance Comparision.
https://github.com/fjchange/awesome-video-anomaly-detection
List: awesome-video-anomaly-detection
abnormal-events anomalies awesome deep-learning detection novelty-detection papers surveillance-videos video-anomaly-detection
Last synced: about 2 months ago
JSON representation
Papers for Video Anomaly Detection, released codes collection, Performance Comparision.
- Host: GitHub
- URL: https://github.com/fjchange/awesome-video-anomaly-detection
- Owner: fjchange
- Created: 2019-09-19T07:19:34.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2022-09-20T09:40:04.000Z (almost 2 years ago)
- Last Synced: 2024-05-22T22:01:09.553Z (4 months ago)
- Topics: abnormal-events, anomalies, awesome, deep-learning, detection, novelty-detection, papers, surveillance-videos, video-anomaly-detection
- Homepage:
- Size: 135 KB
- Stars: 559
- Watchers: 31
- Forks: 96
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-machine-learning-resources - **[List - video-anomaly-detection?style=social) (Table of Contents)
- ultimate-awesome - awesome-video-anomaly-detection - Papers for Video Anomaly Detection, released codes collection, Performance Comparision. (Other Lists / PowerShell Lists)
README
# awesome-video-anomaly-detection [](https://github.com/sindresorhus/awesome)
Papers for Video Anomaly Detection, released codes collections.
Any addition or bug please open an issue, pull requests or e-mail me by `[email protected] `
## Recent Updated
- AAAI 2022
- CVPR 2022
## Datasets
0. UMN [`Download link`](http://mha.cs.umn.edu/)
1. UCSD [`Download link`](http://www.svcl.ucsd.edu/projects/anomaly/dataset.html)
2. Subway Entrance/Exit [`Download link`](http://vision.eecs.yorku.ca/research/anomalous-behaviour-data/)
3. CUHK Avenue [`Download link`](http://www.cse.cuhk.edu.hk/leojia/projects/detectabnormal/dataset.html)
- HD-Avenue [Skeleton-based](#01902)
4. ShanghaiTech [`Download link`](https://svip-lab.github.io/dataset/campus_dataset.html)
- HD-ShanghaiTech [Skeleton-based](#01902)
5. UCF-Crime (Weakly Supervised)
- UCFCrime2Local (subset of UCF-Crime but with spatial annotations.) [`Download_link`](http://imagelab.ing.unimore.it/UCFCrime2Local), [Ano-Locality](#21902)
- Spatial Temporal Annotations [`Download_link`](https://github.com/xuzero/UCFCrime_BoundingBox_Annotation) [Background-Bias](#21901)
6. Traffic-Train
7. Belleview
8. Street Scene (WACV 2020) [Street Scenes](#02001), [`Download link`](https://www.merl.com/demos/video-anomaly-detection)
9. IITB-Corridor (WACV 2020) [Rodrigurs.etl](#02002)
10. XD-Violence (ECCV 2020) [XD-Violence](#12003)[`Download link`](https://roc-ng.github.io/XD-Violence/)
11. ADOC (ACCV 2020) [ADOC](#02012)[`Download_link`](http://qil.uh.edu/main/datasets/)
12. UBnormal (CVPR 2022) [UBnormal] [`Project Link`](https://github.com/lilygeorgescu/UBnormal) `Open-Set`
__The Datasets belowed are about Traffic Accidents Anticipating in Dashcam videos or Surveillance videos__
1. CADP [(CarCrash Accidents Detection and Prediction)](https://github.com/ankitshah009/CarCrash_forecasting_and_detection)
2. DAD [paper](https://yuxng.github.io/chan_accv16.pdf), [`Download link`](https://aliensunmin.github.io/project/dashcam/)
3. A3D [paper](https://arxiv.org/abs/1903.00618?), [`Download link`](https://github.com/MoonBlvd/tad-IROS2019)
4. DADA [`Download link`](https://github.com/JWFangit/LOTVS-DADA)
5. DoTA [`Download_link`](https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly)
6. Iowa DOT [`Download_link`](https://www.aicitychallenge.org/2018-ai-city-challenge/)
1. Driver_Anomaly [Project_link](https://github.com/okankop/Driver-Anomaly-Detection)
-----
## Unsupervised
### 2016
1. [Conv-AE] [Learning Temporal Regularity in Video Sequences](https://openaccess.thecvf.com/content_cvpr_2016/papers/Hasan_Learning_Temporal_Regularity_CVPR_2016_paper.pdf), `CVPR 16`. [Code](https://github.com/iwyoo/TemporalRegularityDetector-tensorflow/blob/master/model.py)
### 2017
1. [Hinami.etl] [Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge](http://openaccess.thecvf.com/content_ICCV_2017/papers/Hinami_Joint_Detection_and_ICCV_2017_paper.pdf), `ICCV 2017`. (Explainable VAD)
2. [Stacked-RNN] [A revisit of sparse coding based anomaly detection in stacked rnn framework](http://openaccess.thecvf.com/content_ICCV_2017/papers/Luo_A_Revisit_of_ICCV_2017_paper.pdf), `ICCV 2017`. [code](https://github.com/StevenLiuWen/sRNN_TSC_Anomaly_Detection)
3. [ConvLSTM-AE] [Remembering history with convolutional LSTM for anomaly detection](https://ieeexplore.ieee.org/abstract/document/8019325), `ICME 2017`.[Code](https://github.com/zachluo/convlstm_anomaly_detection)
4. [Conv3D-AE] [Spatio-Temporal AutoEncoder for Video Anomaly Detection](https://dl.acm.org/doi/abs/10.1145/3123266.3123451),`ACM MM 17`.
5. [Unmasking] [Unmasking the abnormal events in video](http://openaccess.thecvf.com/content_ICCV_2017/papers/Ionescu_Unmasking_the_Abnormal_ICCV_2017_paper.pdf), `ICCV 17`.
6. [DeepAppearance] [Deep appearance features for abnormal behavior detection in video](https://www.researchgate.net/profile/Radu_Tudor_Ionescu/publication/320361315_Deep_Appearance_Features_for_Abnormal_Behavior_Detection_in_Video/links/5a469e9fa6fdcce1971b7258/Deep-Appearance-Features-for-Abnormal-Behavior-Detection-in-Video.pdf)
### 2018
1. [FramePred] [Future Frame Prediction for Anomaly Detection -- A New Baseline](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Future_Frame_Prediction_CVPR_2018_paper.pdf), `CVPR 2018`. [code](https://github.com/StevenLiuWen/ano_pred_cvpr2018)
2. [ALOOC] [Adversarially Learned One-Class Classifier for Novelty Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sabokrou_Adversarially_Learned_One-Class_CVPR_2018_paper.pdf), `CVPR 2018`. [code](https://github.com/khalooei/ALOCC-CVPR2018)
3. [Detecting Abnormality Without Knowing Normality: A Two-stage Approach for Unsupervised Video Abnormal Event Detection](https://dl.acm.org/doi/10.1145/3240508.3240615), `ACM MM 18`.
### 2019
1. [Mem-AE] [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](http://openaccess.thecvf.com/content_ICCV_2019/papers/Gong_Memorizing_Normality_to_Detect_Anomaly_Memory-Augmented_Deep_Autoencoder_for_Unsupervised_ICCV_2019_paper.pdf), `ICCV 2019`.[code](https://github.com/donggong1/memae-anomaly-detection)
2. [Skeleton-based] [Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos](http://openaccess.thecvf.com/content_CVPR_2019/papers/Morais_Learning_Regularity_in_Skeleton_Trajectories_for_Anomaly_Detection_in_Videos_CVPR_2019_paper.pdf), `CVPR 2019`.[code](https://github.com/RomeroBarata/skeleton_based_anomaly_detection)
3. [Object-Centric] [Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection](http://openaccess.thecvf.com/content_CVPR_2019/papers/Ionescu_Object-Centric_Auto-Encoders_and_Dummy_Anomalies_for_Abnormal_Event_Detection_in_CVPR_2019_paper.pdf), `CVPR 2019`.
4. [Appearance-Motion Correspondence] [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](http://openaccess.thecvf.com/content_ICCV_2019/papers/Nguyen_Anomaly_Detection_in_Video_Sequence_With_Appearance-Motion_Correspondence_ICCV_2019_paper.pdf), `ICCV 2019`.[code](https://github.com/nguyetn89/Anomaly_detection_ICCV2019)
5. [AnoPCN][AnoPCN: Video Anomaly Detection via Deep Predictive Coding Network](https://people.cs.clemson.edu/~jzwang/20018630/mm2019/p1805-ye.pdf), ACM MM 2019.
### 2020
1. [Street-Scene] [Street Scene: A new dataset and evaluation protocol for video anomaly detection](http://openaccess.thecvf.com/content_WACV_2020/papers/Ramachandra_Street_Scene_A_new_dataset_and_evaluation_protocol_for_video_WACV_2020_paper.pdf), `WACV 2020`.
2. [Rodrigurs.etl]) [Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection](http://openaccess.thecvf.com/content_WACV_2020/papers/Rodrigues_Multi-timescale_Trajectory_Prediction_for_Abnormal_Human_Activity_Detection_WACV_2020_paper.pdf), `WACV 2020`.
3. [GEPC] [Graph Embedded Pose Clustering for Anomaly Detection](https://arxiv.org/pdf/1912.11850.pdf), `CVPR 2020`.[code](https://github.com/amirmk89/gepc)
4. [Self-trained] [Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection](https://arxiv.org/pdf/2003.06780.pdf), `CVPR 2020`.
5. [MNAD] [Learning Memory-guided Normality for Anomaly Detection](https://arxiv.org/pdf/2003.13228.pdf), `CVPR 2020`. [code](https://cvlab.yonsei.ac.kr/projects/MNAD)
6. [Continual-AD]] [Continual Learning for Anomaly Detection in Surveillance Videos](https://arxiv.org/pdf/2004.07941),`CVPR 2020 Worksop.`
7. [OGNet] [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](http://openaccess.thecvf.com/content_CVPR_2020/papers/Zaheer_Old_Is_Gold_Redefining_the_Adversarially_Learned_One-Class_Classifier_Training_CVPR_2020_paper.pdf), `CVPR 2020`. [code](https://github.com/xaggi/OGNet)
8. [Any-Shot] [Any-Shot Sequential Anomaly Detection in Surveillance Videos](http://openaccess.thecvf.com/content_CVPRW_2020/papers/w54/Doshi_Any-Shot_Sequential_Anomaly_Detection_in_Surveillance_Videos_CVPRW_2020_paper.pdf),`CVPR 2020 workshop`.
9. [Few-Shot][Few-Shot Scene-Adaptive Anomaly Detection](https://arxiv.org/pdf/2007.07843.pdf)`ECCV 2020 Spotlight` [code](https://github.com/yiweilu3/Few-shot-Scene-adaptive-Anomaly-Detection)
10. [CDAE][Clustering-driven Deep Autoencoder for Video Anomaly Detection](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600324.pdf)`ECCV 2020`
11. [VEC][Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events](https://arxiv.org/abs/2008.11988)`ACM MM 2020 Oral` [code](https://github.com/yuguangnudt/VEC_VAD)
12. [ADOC][A Day on Campus - An Anomaly Detection Dataset for Events in a Single Camera] `ACCV 2020`
13. [CAC][Cluster Attention Contrast for Video Anomaly Detection](http://web.pkusz.edu.cn/adsp/files/2020/08/Cluster_Attention_Contrast_for_Video_Anomaly_Detection.pdf) `ACM MM 2020`
14. [STC-Graph][Scene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos](https://dl.acm.org/doi/pdf/10.1145/3394171.3413887) `ACM MM 2020`
### 2021
1. [AMCM][Appearance-Motion Memory Consistency Network for Video Anomaly Detection](https://www.aaai.org/AAAI21Papers/AAAI-4120.CaiR.pdf) `AAAI 2021`
2. [SSMT,Self-Supervised-Multi-Task][Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://arxiv.org/pdf/2011.07491.pdf) `CVPR 2021`
3. [HF2-VAD][A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://arxiv.org/pdf/2108.06852.pdf)`ICCV 2021 Oral`
4. [ROADMAP][Robust Unsupervised Video Anomaly Detection by Multipath Frame Prediction](https://arxiv.org/pdf/2011.02763)`TNNLS 2021`
5. [AEP][Abnormal Event Detection and Localization via Adversarial Event Prediction](https://ieeexplore.ieee.org/abstract/document/9346050/) `TNNLS 2021`
### 2022
1. [Casual][A Causal Inference Look At Unsupervised Video Anomaly Detection](https://www.aaai.org/AAAI22Papers/AAAI-37.LinX.pdf)`AAAI 2022`
2. [BDPN][Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly Detection](https://www.aaai.org/AAAI22Papers/AAAI-470.ChenC.pdf)`AAAI 2022`
3. [GCL][Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://arxiv.org/pdf/2203.03962.pdf)`CVPR 2022`
## Weakly-Supervised
### 2018
1. [Sultani.etl] [Real-world Anomaly Detection in Surveillance Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sultani_Real-World_Anomaly_Detection_CVPR_2018_paper.pdf), `CVPR 2018` [code](https://github.com/WaqasSultani/AnomalyDetectionCVPR2018)
### 2019
1. [GCN-Anomaly] [Graph Convolutional Label Noise Cleaner:Train a Plug-and-play Action Classifier for Anomaly Detection](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhong_Graph_Convolutional_Label_Noise_Cleaner_Train_a_Plug-And-Play_Action_Classifier_CVPR_2019_paper.pdf),` CVPR 2019`,
[code](https://github.com/jx-zhong-for-academic-purpose/GCN-Anomaly-Detection)
2. [MLEP] [Margin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies](https://pdfs.semanticscholar.org/e878/6acbfabaf4938c9c8e2d3a15e0f110a1ec7f.pdf), `IJCAI 2019`[code](https://github.com/svip-lab/MLEP).
3. [IBL] [Temporal Convolutional Network with Complementary Inner Bag Loss For Weakly Supervised Anomaly Detection](https://ieeexplore.ieee.org/abstract/document/8803657/). `ICIP 19`.
4. [Motion-Aware] [Motion-Aware Feature for Improved Video Anomaly Detection](https://arxiv.org/pdf/1907.10211). `BMVC 19`.
### 2020
1. [Siamese] [Learning a distance function with a Siamese network to localize anomalies in videos](https://arxiv.org/abs/2001.09189), `WACV 2020`.
2. [AR-Net] [Weakly Supervised Video Anomaly Detection via Center-Guided Discrimative Learning](https://ieeexplore.ieee.org/document/9102722),` ICME 2020`.[code](https://github.com/wanboyang/Anomaly_AR_Net_ICME_2020)
3. ['XD-Violence'] [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://arxiv.org/pdf/2007.04687.pdf) `ECCV 2020`
4. [CLAWS] [CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123670358.pdf) `ECCV 2020`
### 2021
1. [MIST] [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://arxiv.org/abs/2104.01633) `CVPR 2021` [Project Page](https://kiwi-fung.win/2021/04/28/MIST/)
2. [RTFM] [Weakly-supervised Video Anomaly Detection with Contrastive Learning of
Long and Short-range Temporal Features](https://arxiv.org/pdf/2101.10030.pdf) `ICCV 2021`[Code](https://github.com/tianyu0207/RTFM)
3. [STAD][Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video](https://arxiv.org/pdf/2108.03825) `IJCAI 2021`
4. [WSAL][Localizing Anomalies From Weakly-Labeled Videos](https://arxiv.org/pdf/2008.08944)`TIP 2021` [Code](https://github.com/ktr-hubrt/WSAL)
5. [CRFD][Learning Causal Temporal Relation and Feature Discrimination for Anomaly Detection](https://ieeexplore.ieee.org/abstract/document/9369126/)`TIP 2021`
### 2022
1. [MSL][Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection](https://www.aaai.org/AAAI22Papers/AAAI-6637.LiS.pdf)`AAAI 2022`
## Supervised
### 2019
1. [Background-Bias][Exploring Background-bias for Anomaly Detection in Surveillance Videos](https://dl.acm.org/doi/abs/10.1145/3343031.3350998), `ACM MM 19`.
2. [Ano-Locality][Anomaly locality in video suveillance](https://arxiv.org/pdf/1901.10364).
## Others
### 2020
1. [Few-Shot][Few-Shot Scene-Adaptive Anomaly Detection](https://arxiv.org/pdf/2007.07843) `ECCV 2020`[code](https://github.com/yiweilu3/Few-shot-Scene-adaptive-Anomaly-Detection)
------
## Reviews / Surveys
1. An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos, J. Image, 2018.[page](https://beedotkiran.github.io/VideoAnomaly.html)
2. DEEP LEARNING FOR ANOMALY DETECTION: A SURVEY, [paper](https://arxiv.org/pdf/1901.03407.pdf)
3. Video Anomaly Detection for Smart Surveillance [paper](https://arxiv.org/pdf/2004.00222.pdf)
4. A survey of single-scene video anomaly detection, `TPAMI 2020` [paper](https://arxiv.org/pdf/2004.05993.pdf).
## Books
1. Outlier Analysis. Charu C. Aggarwal
## Specific Scene
------
Generally, anomaly detection in recent researches are based on the datasets from pedestrian (likes UCSD, Avenue, ShanghaiTech, etc.)， or UCF-Crime (real-world anomaly).
However some focus on specific scene as follows.
### Traffic
CVPR workshop, AI City Challenge series.
#### First-Person Traffic
Unsupervised Traffic Accident Detection in First-Person Videos, IROS 2019.
#### Driving
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos. [github](https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly)
### Old-man Fall Down
### Fighting/Violence
1. Localization Guided Fight Action Detection in Surveillance Videos. ICME 2019.
2.
### Social/ Group Anomaly
1. Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks, Neurips 2019.
## Related Topics:
1. Video Representation (Unsupervised Video Representation, reconstruction, prediction etc.)
2. Object Detection
3. Pedestrian Detection
4. Skeleton Detection
5. Graph Neural Networks
6. GAN
7. Action Recognition / Temporal Action Localization
8. Metric Learning
9. Label Noise Learning
10. Cross-Modal/ Multi-Modal
11. Dictionary Learning
12. One-Class Classification / Novelty Detection / Out-of-Disturibution Detection
13. Action Recognition.
- Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events. ACM MM 2020 workshop.
## Performance Evaluation Methods
1. AUC
2. PR-AUC
3. Score Gap
4. False Alarm Rate on Normal with 0.5 as threshold (Weakly supervised, proposed in CVPR 18)
As discussed in Issue [#12](https://github.com/fjchange/awesome-video-anomaly-detection/issues/12), the reported results below will be ``Micro-AUC”, if the paper provide ``Macro-AUC", which will be tagged with `*`.
## Performance Comparison on UCF-Crime
| Model | Reported on Convference/Journal | Supervised | Feature | Encoder-based | 32 Segments | AUC (%) | [email protected] on Normal (%) |
| --------------------------------------------------- | ------------------------------- | ---------- | -------- | ------- | ----------- | ------- | --------------------- |
| [Sultani.etl](#11801) | CVPR 18 | Weakly | C3D RGB | X | √ | 75.41 | 1.9 |
| [IBL](#11903) | ICIP 19 | Weakly | C3D RGB | X | √ | 78.66 | - |
| [Motion-Aware](#11904) | BMVC 19 | Weakly | PWC Flow | X | √ | 79.0 | - |
| [GCN-Anomaly](#11901) | CVPR 19 | Weakly | TSN RGB | √ | X | 82.12 | 0.1 |
| [ST-Graph](#02014) | ACM MM 20 | Un | - | √ | X | 72.7 | |
| [Background-Bias](#21901) | ACM MM 19 | Fully | NLN RGB | √ | X | 82.0 | - |
| [CLAWS](#12004) | ECCV 20 | Weakly | C3D RGB | √ | X | 83.03 | - |
| [MIST](#12101) | CVPR 21 | Weakly | I3D RGB | √ | X | 82.30 | 0.13 |
| [RTFM](#12102) | ICCV 21 | Weakly | I3D RGB | X | √ | 84.03 | - |
| [WSAL](#12104) | TIP 21 | Weakly | I3D RGB | X | √ | 85.38 | - |
| [CRFD](#12105) | TIP 21 | Weakly | I3D RGB | X | √ | 84.89 | - |
| [MSL](#12201) | AAAI 22 | Weakly | C3D RGB | √ | X | 82.85 | - |
| [MSL](#12202) | AAAI 22 | Weakly | I3D RGB | √ | X | 85.30 | - |
| [MSL](#12201) | AAAI 22 | Weakly | VideoSwin-RGB | √ | X | 85.62 | - |
| [GCL](#12203) | CVPR 22 | Weakly | ResNext | √ | X | 79.84 | - |
| [GCL](#12203) | CVPR 22 | Un | ResNext | √ | X | 71.04 | - |
## Performance Comparison on ShanghaiTech
| Model | Reported on Conference/Journal | Supervision | Feature | Encoder-based | AUC(%) | [email protected] (%) |
| ------------------------------------------------- | ------------------------------ | ----------------------------- | ------------------ | ------- | ------ | ----------- |
| [Conv-AE](#01601) | CVPR 16 | Un | - | √ | 60.85 | - |
| [stacked-RNN](#01702) | ICCV 17 | Un | - | √ | 68.0 | - |
| [FramePred](#01801) | CVPR 18 | Un | - | √ | 72.8 | - |
| [FramePred*](#11902) | IJCAI 19 | Un | - | √ | 73.4 | - |
| [Mem-AE](#01901) | ICCV 19 | Un | - | √ | 71.2 | - |
| [MNAD](#02005) | CVPR 20 | Un | - | √ | 70.5 | - |
| [VEC](#02011) | ACM MM 20 | Un | - | √ | 74.8 | - |
| [ST-Graph](#02014) | ACM MM 20 | Un | - | √ | 74.7 | - |
| [CAC](#02013) | ACM MM 20 | Un | - | √ | 79.3 | |
| [AMMC](#02101) | AAAI 21 | Un | - | √ | 73.7 | - |
| [SSMT](#02102) | CVPR 21 | Un | - | √ | 82.4 | - |
| [HF2-VAD](#02103) | ICCV 21 | Un | - | √ | 76.2 | - |
| [ROADMAP](#02104) | TNNLS 21 | Un | - | √ | 76.6 | - |
| [BDPN](#02202) | AAAI 22 | Un | - | √ | 78.1 | - |
| [MLEP](#11902) | IJCAI 19 | 10% test vids with Video Anno | - | √ | 75.6 | - |
| [MLEP](#11902) | IJCAI 19 | 10% test vids with Frame Anno | - | √ | 76.8 | - |
| [Sultani.etl](#12002) | ICME 2020 | Weakly (Re-Organized Dataset) | C3D-RGB | X | 86.3 | 0.15 |
| [IBL](#12002) | ICME 2020 | Weakly (Re-Organized Dataset) | I3D-RGB | X | 82.5 | 0.10 |
| [GCN-Anomaly](#11901) | CVPR 19 | Weakly (Re-Organized Dataset) | C3D-RGB | √ | 76.44 | - |
| [GCN-Anomaly](#11901) | CVPR 19 | Weakly (Re-Organized Dataset) | TSN-Flow | √ | 84.13 | - |
| [GCN-Anomaly](#11901) | CVPR 19 | Weakly (Re-Organized Dataset) | TSN-RGB | √ | 84.44 | - |
| [AR-Net](#12002) | ICME 20 | Weakly (Re-Organized Dataset) | I3D-RGB & I3D Flow | X | 91.24 | 0.10 |
| [CLAWS](#12004) | ECCV 20 | Weakly (Re-Organized Dataset) | C3D-RGB | √ | 89.67 | |
| [MIST](#12101) | CVPR 21 | Weakly (Re-Organized Dataset) | I3D-RGB | √ | 94.83 | 0.05 |
| [RTFM](#12102) | ICCV 21 | Weakly (Re-Organized Dataset) | I3D-RGB | X | 97.21 | - |
| [CRFD](#12105) | TIP 21 | Weakly (Re-Organized Dataset) | I3D-RGB | X | 97.48 | - |
| [MSL](#12201) | AAAI 22 | Weakly (Re-Organized Dataset) | C3D-RGB | X | 94.81 | - |
| [MSL](#12201) | AAAI 22 | Weakly (Re-Organized Dataset) | I3D-RGB | X | 96.08 | - |
| [MSL](#12201) | AAAI 22 | Weakly (Re-Organized Dataset) | VideoSwin-RGB | X | 97.32 | - |
| [GCL](#12203) | CVPR 22 | Weakly (Re-Organized Dataset) | ResNext | X | 86.21 | - |
| [GCL](#12203) | CVPR 22 | Un | ResNext | X | 78.93 | - |
## Performance Comparison on Avenue
| Model | Reported on Conference/Journal | Supervision | Feature | End2End | AUC(%) |
| ------------------------------------------------------------ | ------------------------------ | ----------------------------- | ---------------------- | ------- | ------ |
| [Conv-AE](#01601) | CVPR 16 | Un | - | √ | 70.2 |
| [Conv-AE*](#01801) | CVPR 18 | Un | - | √ | 80.0 |
| [ConvLSTM-AE](#01703) | ICME 17 | Un | - | √ | 77.0 |
| [DeepAppearance](#01706) | ICAIP 17 | Un | - | √ | 84.6 |
| [Unmasking](#01705) | ICCV 17 | Un | 3D gradients+VGG conv5 | X | 80.6 |
| [stacked-RNN](#01702) | ICCV 17 | Un | - | √ | 81.7 |
| [FramePred](#01801) | CVPR 18 | Un | - | √ | 85.1 |
| [Mem-AE](#01901) | ICCV 19 | Un | - | √ | 83.3 |
| [Appearance-Motion Correspondence](#01904) | ICCV 19 | Un | - | √ | 86.9 |
| [FramePred*](#11902) | IJCAI 19 | Un | - | √ | 89.2 |
| [MNAD](#02005) | CVPR 20 | Un | - | √ | 88.5 |
| [VEC](#02011) | ACM MM 20 | Un | - | √ | 90.2 |
| [ST-Graph](#02014) | ACM MM 20 | Un | - | √ | 89.6 |
| [CAC](#02013) | ACM MM 20 | Un | - | √ | 87.0 |
| [AMMC](#02101) | AAAI 21 | Un | - | √ | 86.6 |
| [SSMT](#02102) | CVPR 21 | Un | - | √ | 91.5 |
| [HF2-VAD](#02103) | ICCV 21 | Un | - | √ | 91.1 |
| [ROADMAP](#02104) | TNNLS 21 | Un | - | √ | 88.3 |
| [AEP](#02105) | TNNLS 21 | Un | - | √ | 90.2 |
| [Causal](#02201) | AAAI 22 | Un | I3D-RGB | X | 90.3 |
| [BDPN](#02202) | AAAI 22 | Un | - | √ | 90.3 |
| [MLEP](#11902) | IJCAI 19 | 10% test vids with Video Anno | - | √ | 91.3 |
| [MLEP](#11902) | IJCAI 19 | 10% test vids with Frame Anno | - | √ | 92.8 |
## Performance Comparison on XD-Violence
| Model | Reported on Conference/Journal | Supervision | Feature | Encoder-based | 32 Segments | AP(%) |
| ----------------------------------------------------- | ------------------------------ | ------------------------ | ------------------- | ------- |-------------| ------ |
| [Sultani et al.](#11801) | ECCV 2020 (reported by Wu) | Weakly | I3D-RGB | X | √ | 73.20 |
| [Wu et al.](#12003) | ECCV 2020 | Weakly | C3D-RGB | X | X | 67.19 |
| [Wu et al.](#12003) | ECCV 2020 | Weakly | I3D-RGB+Audio | X | X | 78.64 |
| [RTFM](#12102) | ICCV 2021 | Weakly | I3D-RGB | X | √ | 77.81 |
| [CRFD](#12105) | TIP 2021 | Weakly | I3D-RGB | X | √ | 75.90 |
| [MSL](#12201) | AAAI 2022 | Weakly | C3D-RGB | X | X | 75.53 |
| [MSL](#12201) | AAAI 2022 | Weakly | I3D-RGB | X | X | 78.28 |
| [MSL](#12201) | AAAI 2022 | Weakly | VideoSwin-RGB | X | X | 78.59 |