git clone https://github.com/DeLightCMU/ElaborativeRehearsal.git
cd ElaborativeRehearsal
export PYTHONPATH=$(pwd):${PYTHONPATH}

pip install -r requirements.txt

# download pretrained models
bash scripts/download_premodels.sh

bash scripts/extract_tsm_features.sh '0,1,2'

bash scripts/extract_object_features.sh '0,1,2'

# mtype: devise, ale, sje, dem, eszsl
mtype=devise
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_baselines.py zeroshot/configs/zsl_baseline_${mtype}_config.yaml ${mtype} --is_train
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_baselines.py zeroshot/configs/zsl_baseline_${mtype}_config.yaml ${mtype} --eval_set tst
# evaluate other splits
ksplit=1
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_baselines_eval_splits.py zeroshot/configs/zsl_baseline_${mtype}_config.yaml ${mtype} ${ksplit}

# gcn
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_kgraphs.py zeroshot/configs/zsl_baseline_kgraph_config.yaml --is_train
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_kgraphs.py zeroshot/configs/zsl_baseline_kgraph_config.yaml --eval_set tst

# TSM + ED class representation + AttnPool (2nd row in Table 4(b))
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_vse.py zeroshot/configs/zsl_vse_wordembed_config.yaml --is_train --resume_file datasets/Kinetics/zsl220/word.glove42b.th

# TSM + ED class representation + BERT (last row in Table 4(a) and Table 4(b))
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_vse.py zeroshot/configs/zsl_vse_config.yaml --is_train

# Obj + ED class representation + BERT + ER Loss (last row in Table 4(c))
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_cptembed.py zeroshot/configs/zsl_cpt_config.yaml --is_train

# ER-ZSAR Full Model
CUDA_VISIBLE_DEVICES=0 python zeroshot/driver/zsl_ervse.py zeroshot/configs/zsl_ervse_config.yaml --is_train

@proceeding{ChenHuang2021ER,
  title={Elaborative Rehearsal for Zero-shot Action Recognition},
  author={Shizhe Chen and Dong Huang},
  booktitle = {ICCV},
  year={2021}
}