Hawk: Learning to Understand Open-World Video Anomalies (paper).

(pretrained.pth) The pretraining stage involves pre-training on the WebVid dataset to acquire a general understanding of video content.
(finetune.pth) The fine-tuning stage focuses on video anomaly understanding by our own dataset.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Jiaqi-hkust/hawk

Unable to build the model tree, the base model loops to the model itself. Learn more.

Dataset used to train Jiaqi-hkust/hawk