Papers › MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in...

MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos

8 Oct 2024arXiv:2410.05900archive 2025-07-28

Yiling Zhang, Erkut Akdag, Egor Bondarev, Peter H. N. de With

Detection of anomaly events is relevant for public safety and requires a combination of fine-grained motion information and contextual events at variable time-scales. To this end, we propose a Multi-Timescale Feature Learning (MTFL) method to enhance the representation of anomaly features. Short, medium, and long temporal tubelets are employed to extract spatio-temporal video features using a Video Swin Transformer. Experimental results demonstrate that MTFL outperforms state-of-the-art methods on the UCF-Crime dataset, achieving an anomaly detection performance 89.78% AUC. Moreover, it performs complementary to SotA with 95.32% AUC on the ShanghaiTech and 84.57% AP on the XD-Violence dataset. Furthermore, we generate an extended dataset of the UCF-Crime for development and evaluation on a wider range of anomalies, namely Video Anomaly Detection Dataset (VADD), involving 2,591 videos in 18 classes with extensive coverage of realistic anomalies.

Paper PDF Code

Code

erktkdg/MTFL officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly Detection Anomaly Detection In Surveillance Videos Supervised Anomaly Detection Video Anomaly Detection Weakly-supervised Anomaly Detection

Datasets

Introduced by this paper, per the archive.

VADD

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Anomaly Detection In Surveillance Videos	ShanghaiTech Weakly Supervised	MTFL (VST, finetuned on VADD)	AUC-ROC	95.70	#7 of 12	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	ShanghaiTech Weakly Supervised	MTFL (VST)	AUC-ROC	95.32	#8 of 12	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	UCF-Crime	MTFL (VST, finetuned on VADD)	ROC AUC	89.78	#2 of 21	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	UCF-Crime	MTFL (VST)	ROC AUC	87.16	#5 of 21	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	VADD	MTFL (VST, finetuned on VADD)	ROC AUC	88.42	#1 of 1	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	XD-Violence	MTFL (VST)	AP	84.57	#7 of 17	Archive leaderboard	report
Anomaly Detection In Surveillance Videos	XD-Violence	MTFL (VST, finetuned on VADD)	AP	79.40	#13 of 17	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Stochastic Depth Swin Transformer Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections