MoCoDAD
MoCoDAD copied to clipboard
aleflabo
The official PyTorch implementation of the IEEE/CVF International Conference on Computer Vision (ICCV) '23 paper Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectio...
Hi,thank you for your open source of your great work! I trained the MoCoDAD model on the Avenue dataset using the readme file, and then run the Evaluation ,The accuracy...
hey, thanks for great work i m using pretrained model, and i want to use visualize.ipynb and it needs some files about anomaly scores which supposed to be in ./data/ubnormal/saved_clip_scores....
For the file "generate_annotations.ipynb" in the folder "_annotations", Could you provide the code for generating the ground truth for UBnormal dataset? I cannot generate a correct csv file for this...
I put a video in the file "./shared_memory/data/" and the code for tracking is modified as "%load_ext autoreload %autoreload 2 %cd ./AlphaPose import shlex import os from tqdm import tqdm...
For "UBnormal import shlex import os from tqdm import tqdm import datetime from glob import glob from natsort import natsorted for scene_path in natsorted(glob('../shared_memory/data/*')): scene = os.path.basename(scene_path) print(scene) for clip...
Dear author, thank you for your open source work. I encountered the following problem when I ran the training code I and tried to get visual results using wandb and...
Thank you for sharing the code. I see the Visualization code "vis.py". I would like to ask what the input of the 'visualize' function is, how to obtain this input...