Home

Awesome

Cascaded Human-Object Interaction Recognition

This repository contains the PyTorch implementation for CVPR 2020 Paper "Cascaded Human-Object Interaction Recognition" by Tianfei Zhou, Wenguan Wang, Siyuan Qi, Haibin Ling, Jianbing Shen.

Our proposed method reached the 1st place in ICCV-2019 Person in Context Challenge (PIC19 Challenge), on both Human-Object Interaction in the Wild (HOIW) and Person in Context (PIC) tracks.

Prerequisites

This implementation is based on mmdetection. Please follow INSTALL.md for installation.

Prepare Dataset

For now, we only provide pre-trained weights for PIC v2.0 and HOIW datasets. Please download these two datasets first.

Please download converted json files from google drive, and put them in the top-most directory.

Download pre-trained weights

Download from Google Drive.

Results on PIC and HOIW datasets are also provided.

Testing

  1. Run testing on the validation set of PIC v2.0

python tools/test_pic.py configs/pic_v2.0/htc_rel_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e_train_rel_dcn_semantichead.py pic_latest.pth --json_out det_result.json

  1. Run testing on the validation set of HOIW

python tools/test_hoiw.py configs/hoiw/cascade_rcnn_x101_64x4d_fpn_1x_4gpu_rel.py hoiw_latest.pth --json_out det_result.json --hoiw_out hoiw_result.json

Citation

@inproceedings{zhou2020cascaded,
  title={Cascaded human-object interaction recognition},
  author={Zhou, Tianfei and Wang, Wenguan and Qi, Siyuan and Ling, Haibin and Shen, Jianbing},
  booktitle=CVPR,
  pages={4263--4272},
  year={2020}
}