ViGA: Video moment retrieval via Glance Annotation
This is the official repository of the paper "Video Moment Retrieval from Text Queries via Single Frame Annotation" published in SIGIR 2022.
https://arxiv.org/abs/2204.09409
Dependencies
This project has been tested on the following conda environment.
$ conda create --name viga python=3.7
$ source activate viga
(viga)$ conda install pytorch=1.10.0 cudatoolkit=11.3.1
(viga)$ pip install numpy scipy pyyaml tqdm
Data preparation
This repository contains our glance annotations already. To replicate our work, one should prepare extra data and finally get the following structure.
ckpt/ our pre-trained model, available at https://drive.google.com/file/d/1S4e8XmIpiVFJKSSJ4Tig4qN0yaCwiVLs/view?usp=sharing
data/
+-- activitynetcaptions/
| +-- c3d/
| +-- annotations/
| | +-- glance/
| | | +-- train.json
| | | +-- val_1.json
| | | +-- val_2.json
| | +-- train.json downloaded
| | +-- val_1.json downloaded
| | +-- val_2.json downloaded
+-- charadessta/
| +-- i3d/
| +-- c3d/
| +-- vgg/
| +-- annotations/
| | +-- glance/
| | | +-- charades_sta_train.txt
| | | +-- charades_sta_test.txt
| | +-- charades_sta_train.txt downloaded
| | +-- charades_sta_test.txt downloaded
| | +-- Charades_v1_train.csv downloaded
| | +-- Charades_v1_test.csv downloaded
+-- tacos/
| +-- c3d/
| +-- annotations/
| | +-- glance/
| | | +-- train.json
| | | +-- test.json
| | | +-- val.json
| | +-- train.json downloaded
| | +-- test.json downloaded
| | +-- val.json downloaded
glove.840B.300d.txt downloaded from https://nlp.stanford.edu/data/glove.840B.300d.zip
1. ActivityNet Captions
c3d feature
Downloaded from http://activity-net.org/challenges/2016/download.html. We extracted the features from sub_activitynet_v1-3.c3d.hdf5 as individual files.
Folder contains 19994 vid.npys, each of shape (T, 500).
annotation
Downloaded from https://cs.stanford.edu/people/ranjaykrishna/densevid/
2. Charades-STA
c3d feature
We extracted this by ourselves, due to the lack of storage resource we are currently not able to make this feature publicly available.
Folder contains 9848 vid.npys, each of shape (T, 4096).
i3d feature
Downloaded from https://github.com/JonghwanMun/LGI4temporalgrounding. This is the features extracted from I3D (finetuned on Charades). We processed them by trimming off unnecessary dimensions.
Folder contains 9848 vid.npys, each of shape (T, 1024).
vgg feature
Downloaded from https://github.com/microsoft/2D-TAN. We processed the data by converting the downloaded version vgg_rgb_features.hdf5 into numpy arrays.
Folder contains 6672 vid.npys, each of shape (T, 4096).
annotation
Downloaded from https://github.com/jiyanggao/TALL
3. TACoS
c3dfeature
Downloaded from https://github.com/microsoft/2D-TAN. We extracted the features from tall_c3d_features.hdf5 as individual files.
Folder contains 127 vid.npys, each of shape (T, 4096).
annotation
Downloaded from https://github.com/microsoft/2D-TAN
2. Run
Our models were trained using the following commands.
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.train --task activitynetcaptions
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.train --task charadessta
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.train --task tacos
Our trained models were evaluated using the following commands.
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.eval --exp ckpt/activitynetcaptions
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.eval --exp ckpt/charadessta_c3d
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.eval --exp ckpt/charadessta_i3d
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.eval --exp ckpt/charadessta_vgg
(viga)$ CUDA_VISIBLE_DEVICES=0 python -m src.experiment.eval --exp ckpt/tacos
51 Dec 15, 2022
183 Dec 28, 2022
112 Nov 25, 2022
3 Jan 28, 2022
1 Dec 08, 2021
429 Dec 31, 2022
580 Jan 09, 2023
1 Dec 11, 2021
96 Dec 20, 2022
49 Nov 09, 2022
6 Sep 08, 2022
232 Nov 21, 2022
29 Nov 09, 2022
20 Apr 07, 2022
6 Oct 10, 2022
1 Feb 12, 2022
181 Jan 02, 2023
165 Dec 21, 2022
1 Nov 02, 2022
45 Sep 21, 2022