Skip to content
View AnonymousCKNN's full-sized avatar

Block or report AnonymousCKNN

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AnonymousCKNN/README.md

Cleansed k-nearest neighbor (CKNN)

Anonymous Submission #4835 to ICCV 2023.

Installation

Step 1. Install libraries

Step 2. Download files

Step 3. Untar all *.tar.xz files and place properly

  • File structure should be like below.
AnonymousCKNN
├── features
│   ├── avenue
│   │   ├── test
│   │   └── train
│   ├── ped2
│   │   ├── test
│   │   └── train
│   └── shanghaitech
│       ├── test
│       └── train
├── meta
│   ├── frame_labels_avenue.npy
│   ├── frame_labels_ped2.npy
│   ├── frame_labels_shanghaitech.npy
│   ├── test_bboxes_avenue.npy
│   ├── test_bboxes_ped2.npy
│   ├── test_bboxes_shanghaitech.npy
│   ├── test_lengths_avenue.npy
│   ├── test_lengths_ped2.npy
│   ├── test_lengths_shanghaitech.npy
│   ├── train_bboxes_avenue.npy
│   ├── train_bboxes_ped2.npy
│   └── train_bboxes_shanghaitech.npy
├── patches
│   ├── avenue
│   │   ├── test
│   │   └── train
│   ├── ped2
│   │   ├── test
│   │   └── train
│   └── shanghaitech
│       ├── test
│       └── train
...

Step 4. Generate pseudo anomaly scores

./run1_pseudo_anomaly_scores.sh avenue

Step 5. Evaluate on each dataset

./run2_evaluate.sh avenue

Popular repositories Loading

  1. AnonymousCKNN AnonymousCKNN Public

    Python