Pinned Repositories
Datasets_ClimateVisions
This repo contains the data used in "Towards Understanding Climate Change Perceptions: A Social Media Dataset"
GCBM
Official repo for arxiv paper: Aligning Visual and Semantic Interpretability through Visually Grounded Concept Bottleneck Models
LSHR_LSHT
MinkowskiEngine
MP4VisualFrameDetection
Official repo for WACV '25: I Spy With My Little Eye - A Minimum Cost Multicut Investigation of Dataset Frames
openclip_multieval
An open source implementation of CLIP. Besides accuracy, precision, recall and F1 are reported. Also acc @ 3, acc @ 5 and confusion matrices
Pixel-Power
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Siegelsammlung-Nordhausen-Harz
This repository contains all code written & used in the context of the project Siegelsammlung Nordhausen/Harz.
Thesis_HYW
KathPra's Repositories
KathPra/Datasets_ClimateVisions
This repo contains the data used in "Towards Understanding Climate Change Perceptions: A Social Media Dataset"
KathPra/LSHR_LSHT
KathPra/GCBM
Official repo for arxiv paper: Aligning Visual and Semantic Interpretability through Visually Grounded Concept Bottleneck Models
KathPra/Pixel-Power
KathPra/Siegelsammlung-Nordhausen-Harz
This repository contains all code written & used in the context of the project Siegelsammlung Nordhausen/Harz.
KathPra/MinkowskiEngine
KathPra/MP4VisualFrameDetection
Official repo for WACV '25: I Spy With My Little Eye - A Minimum Cost Multicut Investigation of Dataset Frames
KathPra/openclip_multieval
An open source implementation of CLIP. Besides accuracy, precision, recall and F1 are reported. Also acc @ 3, acc @ 5 and confusion matrices
KathPra/pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
KathPra/Thesis_HYW
KathPra/webcamdino
Using the Dinov2 environment, this code builds on the inference pipeline to extract images in realtime and process videos in almost real-time.