hawk
hawk copied to clipboard
Hawk: Learning to Understand Open-World Video Anomalies
[NeurIPS 2024] Hawk: Learning to Understand Open-World Video Anomalies
This is the official repository for Hawk.
Jiaqi Tang^, Hao Lu^, Ruizheng Wu, Xiaogang Xu, Ke Ma, Cheng Fang,
Bin Guo, Jiangbo Lu, Qifeng Chen and Ying-Cong Chen*
^: Equal contribution. *: Corresponding Author.

π Motivation - Have eyes like a Hawk!
-
π© Current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction.
-
π© Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios.
π’ Updates
- β Step 26, 2024 - Hawk is accepted by NeurIPS 2024.
- β July 29, 2024 - We release the dataset of Hawk. Check this Google Cloud link for DOWNLOAD.
βΆοΈ Getting Started
πͺ Installation
πΎ Dataset Preparation
-
DOWNLOAD all video datasets for their original sources.
-
Google Drive Link to DOWNLOAD our annotations.
-
Data Structure: each folder contains one annotation file (e.g. CUHK Avenue, DoTA, etc.). The
All_Mix
directory contains all of the datasets in training and testing. -
The dataset is organized as follows:
data βββ All_Mix β βββ all_videos_all.json β βββ all_videos_test.json β βββ all_videos_train.json β βββ CUHK_Avenue β βββ Avenue.json βββ DoTA β βββ DoTA.json βββ Ped1 β βββ ... βββ ... βββ UCF_Crime βββ ...
NoteοΌthe data path should be redefined.
π° Pretrained Model
π¨ Configuration
β³ Testing
π₯οΈ Training
β‘ Performance
π Citations
The following is a BibTeX reference:
@inproceedings{tang2024hawk,
title={Hawk: Learning to Understand Open-World Video Anomalies},
author={Jiaqi Tang and Hao Lu and Ruizheng Wu and Xiaogang Xu and Ke Ma and Cheng Fang and Bin Guo and Jiangbo Lu and Qifeng Chen and Ying-Cong Chen},
booktitle={Hawk: Learning to Understand Open-World Video Anomalies},
year={2024}
}
π§ Connecting with Us?
If you have any questions, please feel free to send email to [email protected]
.