PDVC

Official implementation for End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)

[paper] [valse论文速递(Chinese)]

This repo supports:

• two video captioning tasks: dense video captioning and video paragraph captioning
• two datasets: ActivityNet Captions and YouCook2
• video features containing C3D, TSN, and TSP.
• visualization of the generated captions of your own videos

Table of Contents:

• Updates
• Introduction
• Preparation
• Running PDVC on Your Own Videos
• Training and Validation
  • Download Video Features
  • Dense Video Captioning
  • Video Paragraph Captioning
• Performance
  • Dense video captioning
  • Video paragraph captioning
• Citation
• Acknowledgement

Updates

• (2021.11.19) add code for running PDVC on raw videos and visualize the generated captions (support Chinese and other non-English languages)
• (2021.11.19) add pretrained models with TSP features. It achieves 9.03 METEOR(2021) and 6.05 SODA_c, a very competitive results on ActivityNet Captions without self-critical sequence training.
• (2021.08.29) add TSN pretrained models and support YouCook2

Introduction

PDVC is a simple yet effective framework for end-to-end dense video captioning with parallel decoding (PDVC), by formulating the dense caption generation as a set prediction task. Without bells and whistles, extensive experiments on ActivityNet Captions and YouCook2 show that PDVC is capable of producing high-quality captioning results, surpassing the state-of-the-art methods when its localization accuracy is on par with them.

Preparation

Environment: Linux, GCC>=5.4, CUDA >= 9.2, Python>=3.7, PyTorch>=1.5.1

1. Clone the repo

git clone --recursive https://github.com/ttengwang/PDVC.git

2. Create vitual environment by conda

conda create -n PDVC python=3.7
source activate PDVC
conda install pytorch==1.7.1 torchvision==0.8.2 cudatoolkit=10.1 -c pytorch
conda install ffmpeg
pip install -r requirement.txt

3. Compile the deformable attention layer (requires GCC >= 5.4).

cd pdvc/ops
sh make.sh

Running PDVC on Your Own Videos

Download a pretrained model (GoogleDrive) with TSP features and put it into ./save. Then run:

video_folder=visualization/videos
output_folder=visualization/output
pdvc_model_path=save/anet_tsp_pdvc/model-best.pth
output_language=en
bash test_and_visualize.sh $video_folder $output_folder $pdvc_model_path $output_language

check the $output_folder, you will see a new video with embedded captions. Note that we generate non-English captions by translating the English captions by GoogleTranslate. To produce chinese captions, set output_language=zh-cn. For other language support, find the abbreviation of your language at this url, and you also may need to download a font supporting your language and put it into ./visualization.

Training and Validation

Download Video Features

cd data/anet/features
bash download_anet_c3d.sh
# bash download_anet_tsn.sh
# bash download_i3d_vggish_features.sh
# bash download_tsp_features.sh

Dense Video Captioning

1. PDVC with learnt proposals

# Training
config_path=cfgs/anet_c3d_pdvc.yml
python train.py --cfg_path ${config_path} --gpu_id ${GPU_ID}
# The script will evaluate the model for every epoch. The results and logs are saved in `./save`.

# Evaluation
eval_folder=anet_c3d_pdvc # specify the folder to be evaluated
python eval.py --eval_folder ${eval_folder} --eval_transformer_input_type queries --gpu_id ${GPU_ID}

2. PDVC with ground-truth proposals

# Training
config_path=cfgs/anet_c3d_pdvc.yml
python train.py --cfg_path ${config_path} --gpu_id ${GPU_ID}

# Evaluation
eval_folder=anet_c3d_pdvc_gt
python eval.py --eval_folder ${eval_folder} --eval_transformer_input_type gt_proposals --gpu_id ${GPU_ID}

Video Paragraph Captioning

1. PDVC with learnt proposals

# Training
config_path=cfgs/anet_c3d_pdvc.yml
python train.py --cfg_path ${config_path} --criteria_for_best_ckpt pc --gpu_id ${GPU_ID} 

# Evaluation
eval_folder=anet_c3d_pdvc # specify the folder to be evaluated
python eval.py --eval_folder ${eval_folder} --eval_transformer_input_type queries --gpu_id ${GPU_ID}

2. PDVC with ground-truth proposals

# Training
config_path=cfgs/anet_c3d_pdvc_gt.yml
python train.py --cfg_path ${config_path} --criteria_for_best_ckpt pc --gpu_id ${GPU_ID}

# Evaluation
eval_folder=anet_c3d_pdvc_gt
python eval.py --eval_folder ${eval_folder} --eval_transformer_input_type gt_proposals --gpu_id ${GPU_ID}

Performance

Dense video captioning

Notes:

• In the paper, we follow the most previous methods to use the evaluation toolkit in ActivityNet Challenge 2018. Note that the latest evluation tookit (METEOR2021) gives the same CIDEr/BLEU4 but a higher METEOR score.
• In the paper, we use an old version of SODA_c implementation, while here we use an updated version for convenience.

Video paragraph captioning

Notes:

• Paragraph-level scores are evaluated on the ActivityNet Entity ae-val set.

Citation

If you find this repo helpful, please consider citing:

@inproceedings{wang2021end,
  title={End-to-End Dense Video Captioning with Parallel Decoding},
  author={Wang, Teng and Zhang, Ruimao and Lu, Zhichao and Zheng, Feng and Cheng, Ran and Luo, Ping},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={6847--6857},
  year={2021}
}

@ARTICLE{wang2021echr,
  author={Wang, Teng and Zheng, Huicheng and Yu, Mingjing and Tian, Qian and Hu, Haifeng},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Event-Centric Hierarchical Representation for Dense Video Captioning}, 
  year={2021},
  volume={31},
  number={5},
  pages={1890-1900},
  doi={10.1109/TCSVT.2020.3014606}}

Acknowledgement

The implementation of Deformable Transformer is mainly based on Deformable DETR. The implementation of the captioning head is based on ImageCaptioning.pytorch. We thanks the authors for their efforts.