Gedamu's Projects
skl_to_image, Train/testsplit, copy and other app codes
Implementing Attention Augmented Convolutional Networks using Pytorch
Skeleton-based Action Recognition
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)
Bottleneck Transformers for Visual Recognition
"Unified Deep Supervised Domain Adaptation and Generalization" (ICCV 2017)
UESTC RGB-D Varying-view action database. This multi-view action database is captured by Kinect v2.0 with modality of RGB video, 3D skeleton sequences and depth map sequences.
Cross-Modal Relation-Aware Networks for Audio-Visual Event Localization, ACM MM 2020
pytorch implementation for Contrastive Adaptation Network
Yu Tian et al. "CR-GAN: Learning Complete Representations for Multi-view Generation", IJCAI 2018
CVPR 2020 论文开源项目合集
Code release for Discriminative Adversarial Domain Adaptation (AAAI2020).
for Simple experiment Train and Test human action Dataset
Basic pytorch, Autogrand , Neural Network, Action classification and other stuffs
Divergence-based domain adaptation works by minimizing some divergence criterion between the source and target data distributions
Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)
Graph Diffusion Convolution, as proposed in "Diffusion Improves Graph Learning" (NeurIPS 2019)
Config files for my GitHub profile.
Implementation of "Generate To Adapt: Aligning Domains using Generative Adversarial Networks"
Generating Human Skeletons with Mutual Actions
Generative Multi-View Human Action Recognition
Graph Distillation for Action Detection
A pytorch reimplementation of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.
Inverse Compositional Spatial Transformer Networks :performing_arts: (CVPR 2017 oral)
Models and examples built with TensorFlow