This model is a fine-tuned version of
CLIP4Clip,
customized for CCTV anomaly detection tasks (smoking, fall, vandalism, arson, theft, etc.).
This model fine-tunes the CLIP4Clip architecture for multimodal video-text retrieval,
adapting it to detect and retrieve abnormal behaviors in unmanned CCTV environments.
The model uses a dual-encoder CLIP backbone with an additional cross-attention encoder for fusion.
1import torch
2from transformers import CLIPModel
3
4model = CLIPModel.from_pretrained("taett/omni")
5model.eval()
