Kevin Ke-Yun Lin

caffe-cvprw15. :heart::coffee: Deep Learning of Binary Hash Codes for Fast Image Retrieval (CVPRW15)

CDCL-human-part-segmentation. Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)

Caffe-DeepBinaryCode. Supervised Semantics-preserving Deep Hashing (TPAMI18)

cvpr16-deepbit. Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks (CVPR16)

caffe-augmentation. :zap: Caffe real-time data augmentation on-the-fly!!

keras-openpose-reproduce. Keras implementation of Realtime Multi-Person Pose Estimation

ObjLeft. :handbag: Abandoned object detection for visual surveillance

ava-dataset-tool. Preprocessing tools for Google AVA Dataset

caffe-multilabel. C++

ABODA. Abandoned Object Dataset

METRO. Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

ObjLeft_demo. Abandoned Object Detection (demo code)

desc_learn. MATLAB

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

CSE517-language-models. Python

Pose2Mesh_RELEASE. Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

ViLT. Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

neural_renderer. "Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.