Implement pedestrian detection in complex scenarios such as low illumination, strong occlusion, and blur in underground coal mines.

Gated Differentiable Image Processing (GDIP) for Object Detection in Adverse Conditions | Accepted at ICRA 2023

🌕 [ICCV 2021] Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection. A self-supervised learning way for low-light image object detection.

Darknet/YOLO object detection framework

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

An unofficial implementation for "CoSeR: Bridging Image and Language for Cognitive Super-Resolution (CVPR 2024)"

[ACCV 2024] PyTorch Implementation of the Paper 'VideoPatchCore': Official Version

视频i3d特征的提取

I3D features extractor with resnet50 backbone

In this project i modify the base resnet 50 with Concatenated Feature Fusion layers, this alone increases precision over the base model by 4%