Cleaned up reference implementation of BIER: Boosting Independent Embeddings Robustly.
Caffe implementation of multiple popular object detection frameworks
[ICLR2021] CT-Net: Channel Tensorization Network for Video Classification
Natural Image Matting via Guided Contextual Attention
Open MMLab Detection Toolbox
Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"
Faster R-CNN features for Instance Search
Semi-Supervised Learning, Object Detection, ICCV2021
Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)