[IEEE TIP] Vision Transformers for Single Image Dehazing

[CVPR 2025] Official implementation of "Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity"

Official implementation of "Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM"

Code for the paper "Benchmarking Object Detectors with COCO: A New Path Forward."

Implementation for One step Learning, One step Review

optimizer & lr scheduler & loss function collections in PyTorch