TeG fuses three temporal scales of Video Swin Transformer features with cross/self-attention, reporting 87.16% AUC on UCF-Crime and 84.57% AP on XD-Violence.
In: Proceedings of the IEEE/CVF inter- national conference on computer vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TeG: Temporal-Granularity Method for Anomaly Detection with Attention in Smart City Surveillance
TeG fuses three temporal scales of Video Swin Transformer features with cross/self-attention, reporting 87.16% AUC on UCF-Crime and 84.57% AP on XD-Violence.