/STTran

Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021

Primary LanguageJupyter NotebookMIT LicenseMIT

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

Pytorch Implementation of our paper Spatial-Temporal Transformer for Dynamic Scene Graph Generation accepted by ICCV2021. We propose a Transformer-based model STTran to generate dynamic scene graphs of the given video. STTran can detect the visual relationships in each frame.

GitHub Logo

About the code We run the code on a single RTX2080ti for both training and testing. We borrowed some code from Yang's repository and Zellers' repository.

Usage

We use python=3.6, pytorch=1.1 and torchvision=0.3 in our code. First, clone the repository:

git clone https://github.com/yrcong/STTran.git

We borrow some compiled code for bbox operations.

cd lib/draw_rectangles
python setup.py build_ext --inplace
cd ..
cd fpn/box_intersections_cpu
python setup.py build_ext --inplace

For the object detector part, please follow the compilation from https://github.com/jwyang/faster-rcnn.pytorch We provide a pretrained FasterRCNN model for Action Genome. Please download here and put it in

fasterRCNN/models/faster_rcnn_ag.pth

Dataset

We use the dataset Action Genome to train/evaluate our method. Please process the downloaded dataset with the Toolkit. The directories of the dataset should look like:

|-- action_genome
    |-- annotations   #gt annotations
    |-- frames        #sampled frames
    |-- videos        #original videos

In the experiments for SGCLS/SGDET, we only keep bounding boxes with short edges larger than 16 pixels. Please download the file object_bbox_and_relationship_filtersmall.pkl and put it in the dataloader

Train

You can train the STTran with train.py. We trained the model on a RTX 2080ti:

  • For PredCLS:
python train.py -mode predcls -datasize large -data_path $DATAPATH 
  • For SGCLS:
python train.py -mode sgcls -datasize large -data_path $DATAPATH 
  • For SGDET:
python train.py -mode sgdet -datasize large -data_path $DATAPATH 

Evaluation

You can evaluate the STTran with test.py.

python test.py -m predcls -datasize large -data_path $DATAPATH -model_path $MODELPATH
python test.py -m sgcls -datasize large -data_path $DATAPATH -model_path $MODELPATH
python test.py -m sgdet -datasize large -data_path $DATAPATH -model_path $MODELPATH

Citation

If our work is helpful for your research, please cite our publication:

@inproceedings{cong2021spatial,
  title={Spatial-Temporal Transformer for Dynamic Scene Graph Generation},
  author={Cong, Yuren and Liao, Wentong and Ackermann, Hanno and Rosenhahn, Bodo and Yang, Michael Ying},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year={2021}
  url={https://arxiv.org/abs/2107.12309}
}

Help

When you have any question/idea about the code/paper. Please comment in Github or send us Email. We will reply as soon as possible.