#
Starred repositories
A practice to handle multi-modal datasets in a unified way.
EdgeFace: Efficient Face Recognition Model for Edge Devices [TBIOM 2024] the winner of compact track of IJCB 2023 Efficient Face Recognition Competition
EdgeFace lightweight face recognition model
1
Updated Feb 5, 2024
Cross Modal Focal Loss for RGBD Face Anti-Spoofing
12
Updated Jul 12, 2021
Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles
3
Updated Feb 5, 2024
👀 Eye Tracking library easily implementable to your projects
Anti-Spoofing for Face Recognition task using the Deep Pixel-wise Binary Supervision Technique
An unofficial implementation of the paper "Deep Pixel-Wise Binary Supervision for Face Presentation Attack Detection" in Pytorch
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
Domain adaptation made easy. Fully featured, modular, and customizable.
Collection of PyTorch Lightning implementations of Generative Adversarial Network varieties presented in research papers.
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Badminton Pose Analysis for coaching and pose correction
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Repository for the Explainable Deep One-Class Classification paper
A collection of implementations of deep domain adaptation algorithms
🌲 A tool for converting PDF into hOCR with text, tables, and figures being recognized and preserved.
An unofficial userspace driver for HID++ Logitech devices
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
This is a Pytorch implementation of deep image blending
[CVPR 2020] G3AN: Disentangling Appearance and Motion for Video Generation
Learning One Class Representations for Presentation Attack Detection using Multi-channel Convolutional Neural Networks