Summaries for breakthrough research in contemporary deep learning. Arranged in chronological order
- Going Deeper with Convolutions (Inception Networks)
- Deep Residual Learning for Image Recognition (ResNets)
- Mask R-CNN
- YOLO
- SSD
More to come ---
- Fully Convolutional Networks
- Segnet
- Deeplab
- Mobilenets
- SqueezeNets
- ESPNets
- Learning Rich Features from RGB-D Images for Object Detection and Segmentation.
- Frustum Pointnets
- Voxelnets
- Review
- OpenPose
- Real-Time Human Motion Capture with Multiple Depth Cameras
- DensePose
- A simple yet effective baseline for 3d human pose estimation