ioekg's Projects
3D ResNets for Action Recognition (CVPR 2018)
A list of ICs and IPs for AI, Machine Learning and Deep Learning.
A curated list of background subtraction related papers and resources
Background subtraction using deep learning method.
Pytorch porting of C3D network, with Sports1M weights
Simple C3D (3D convolutional Network) in Pytorch
The first open source fingerprint browser.
A technical report on convolution arithmetic in the context of deep learning
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC
A PyTorch Implementation of MobileNetv2+DeepLabv3
Implementation of DropBlock in Pytorch
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding
FgSegNet_v2: "Learning Multi-scale Features for Foreground Segmentation.” by Long Ang LIM and Hacer YALIM KELES
Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
learning how to use github
Config files for my GitHub profile.
Guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Python implementation of Medoidshift and Quickshift algorithms
Impementation of MobileNetV2 in pytorch
把用ucasthesis模板撰写的毕业论文转化为知网可以识别的word文件
pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported
DeepLab-ResNet rebuilt in Pytorch
DeepLab v3+ model in PyTorch. Support different backbones.
A PyTorch implementation of MobileNet V2 architecture and pretrained model.
Semantic Segmentation Architectures Implemented in PyTorch
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
Pytorch C3D feature extractor
A clustering algorithm that first finds the high-density regions (cluster-cores) of the data and then clusters the remaining points by hill-climbing. Such seedings act as more stable and expressive cluster-cores than the singleton modes found by popular algorithm such as mean shift. (https://arxiv.org/abs/1805.07909)