Awesome

Video Re-localization

by Yang Feng, Lin Ma, Wei Liu, Tong Zhang, Jiebo Luo

Introduction

Video Re-localization aims to accurately localize a segment in a reference video such that the segment semantically corresponds to a query video. For more details, please refer to our paper.

alt text

Citation

@InProceedings{feng2018video,
  author = {Feng, Yang and Ma, Lin and Liu, Wei and Zhang, Tong and Luo, 
  Jiebo},
  title = {Video Re-localization},
  booktitle = {ECCV},
  year = {2018}
}

Requirements

sudo apt install python-opencv
pip install tensorflow-gpu==1.13.1

Dataset

Download the ActivityNet features at link. You will get activitynet_v1-3.part-00 to activitynet_v1-3.part-05.
Merge and unzip the files. You'll get sub_activitynet_v1-3.c3d.hdf5.
```
cat activitynet_v1-3.part-0* > temp.zip
unzip temp.zip
```

Get the code and split the features.

git clone https://github.com/fengyang0317/video_reloc.git
cd video_reloc
ln -s /path/to/sub_activitynet_v1-3.c3d.hdf5 data/
python split_feat.py

[Optional] Download the all the videos into data/videos and get the number of frames in each video.
```
python get_frame_num.py
```
Generate the dataset json.
```
python create_dataset.py
```

Model

Train the model.
```
python match.py --data_dir data
```
Eval the model. The results may be slightly different from the values reported in the paper.
```
python eval.py --data_dir data --ckpt_path saving/model.ckpt-(best val ckpt)
```