| osmr/imgclsmob |
2,399 |
|
0 |
9 |
over 4 years ago |
67 |
September 21, 2021 |
6 |
mit |
Python |
| Sandbox for training deep learning networks |
| HRNet/HRFormer |
392 |
|
0 |
0 |
over 3 years ago |
0 |
|
16 |
mit |
Python |
| This is an official implementation of our NeurIPS 2021 paper "HRFormer: High-Resolution Transformer for Dense Prediction". |
| dronefreak/human-action-classification |
106 |
|
0 |
0 |
over 4 years ago |
0 |
|
3 |
mit |
Python |
| This repository allows you to classify 40 different human actions. Pose detection, estimation and classification is also performed. Poses are classified into sitting, upright and lying down. |
| jing-vision/lightnet |
100 |
|
0 |
0 |
almost 4 years ago |
0 |
|
3 |
mit |
Python |
| Lightweight turnkey solution for AI |
| jrobchin/phormatics |
79 |
|
0 |
0 |
about 5 years ago |
0 |
|
6 |
|
Jupyter Notebook |
| Using A.I. and computer vision to build a virtual personal fitness trainer. (Most Startup-Viable Hack - HackNYU2018) |
| cansik/deep-vision-processing |
74 |
|
0 |
0 |
over 3 years ago |
0 |
|
6 |
|
Java |
| Deep computer-vision algorithms for the Processing framework. |
| ViTAE-Transformer/QFormer |
73 |
|
0 |
0 |
about 2 years ago |
0 |
|
1 |
mit |
Python |
| The official repo for [Arxiv'23] "Vision Transformer with Quadrangle Attention" |
| jhu-lcsr/sp_segmenter |
32 |
|
0 |
0 |
over 8 years ago |
0 |
|
3 |
other |
C++ |
| Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package. |
| NVIDIA-AI-IOT/trt_pose_hand |
24 |
|
0 |
0 |
about 5 years ago |
0 |
|
3 |
mit |
Jupyter Notebook |
| Real-time hand pose estimation and gesture classification using TensorRT |
| JHUVisionLab/multi-modal-regression |
21 |
|
0 |
0 |
over 7 years ago |
0 |
|
0 |
mit |
Python |
| Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation |
