Xing Liu's repositories
speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
accessmath-icfhr2018
Lecture Video Summarization by Extracting Handwritten Content from Whiteboards
Light-ASD
The repository for IEEE CVPR 2023 (A Light Weight Model for Active Speaker Detection)
yolov7-face
yolov7 face detection with landmark
TalkNet-ASD
ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'
mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
DocEnTR
DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
pan_pp.pytorch
Official implementations of PSENet, PAN and PAN++.
HAT
Arxiv2022 - Activating More Pixels in Image Super-Resolution Transformer
voxceleb_trainer
In defence of metric learning for speaker recognition
SPELL
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)
mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
FOTS.PyTorch
FOTS Pytorch Implementation
robin
RObust document image BINarization
ECAPA-TDNN
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
DB
A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
ssd.pytorch
A PyTorch Implementation of Single Shot MultiBox Detector
TextFuseNet
A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".
PAN.pytorch
A unofficial pytorch implementation of PAN(PSENet2): Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
active-speakers-context
Code for the Active Speakers in Context Paper (CVPR2020)
pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
Transfer-Learning-in-keras---custom-data
Implementing Transfer Learning for custom data using VGG-16 and Resnet-50
VGG16_feature_computation
c++ class to get the output of a pre-trained VGG16 network