Source code of our TPAMI'21 paper Dual Encoding for Video Retrieval by Text and CVPR'19 paper Dual Encoding for Zero-Example Video Retrieval.

Overview

Dual Encoding for Video Retrieval by Text

Source code of our TPAMI'21 paper Dual Encoding for Video Retrieval by Text and CVPR'19 paper Dual Encoding for Zero-Example Video Retrieval.

image

Table of Contents

Environments

  • Ubuntu 16.04
  • CUDA 10.1
  • Python 3.8
  • PyTorch 1.5.1

We used Anaconda to setup a deep learning workspace that supports PyTorch. Run the following script to install the required packages.

conda create --name ws_dual_py3 python=3.8
conda activate ws_dual_py3
git clone https://github.com/danieljf24/hybrid_space.git
cd hybrid_space
pip install -r requirements.txt
conda deactivate

Dual Encoding on MSRVTT10K

Required Data

Run the following script to download and extract MSR-VTT (msrvtt10k-resnext101_resnet152.tar.gz(4.3G)) dataset and a pre-trained word2vec (vec500flickr30m.tar.gz(3.0G). The data can also be downloaded from Baidu pan (url, password:p3p0) or Google drive (url). For more information about the dataset, please refer to here. The extracted data is placed in $HOME/VisualSearch/.

ROOTPATH=$HOME/VisualSearch
mkdir -p $ROOTPATH && cd $ROOTPATH

# download and extract dataset
wget http://8.210.46.84:8787/msrvtt10k-resnext101_resnet152.tar.gz
tar zxf msrvtt10k-resnext101_resnet152.tar.gz -C $ROOTPATH

# download and extract pre-trained word2vec
wget http://lixirong.net/data/w2vv-tmm2018/word2vec.tar.gz
tar zxf word2vec.tar.gz -C $ROOTPATH

Model Training and Evaluation

Run the following script to train and evaluate Dual Encoding network with hybrid space on the official partition of MSR-VTT. The video features are the concatenation of ResNeXt-101 and ResNet-152 features. The code of video feature extraction we used in the paper is available at here.

conda activate ws_dual_py3
./do_all.sh msrvtt10k hybrid resnext101-resnet152

Running the script will do the following things:

  1. Train Dual Encoding network with hybrid space and select a checkpoint that performs best on the validation set as the final model. Notice that we only save the best-performing checkpoint on the validation set to save disk space.
  2. Evaluate the final model on the test set. Note that the dataset has already included vocabulary and concept annotations. If you would like to generate vocabulary and concepts by yourself, run the script ./do_vocab_concept.sh msrvtt10k 1 $ROOTPATH.

If you would like to train Dual Encoding network with the latent space learning (Conference Version), please run the following scrip:

./do_all.sh msrvtt10k latent resnext101-resnet152 $ROOTPATH

To train the model on the Test1k-Miech partition and Test1k-Yu partition of MSR-VTT, please run the following scrip:

./do_all.sh msrvtt10kmiech hybrid resnext101-resnet152 $ROOTPATH
./do_all.sh msrvtt10kyu hybrid resnext101-resnet152 $ROOTPATH

Evaluation using Provided Checkpoints

The overview of pre-trained checkpoints on MSR-VTT is as follows.

Split Pre-trained Checkpoints
Official msrvtt10k_model_best.pth.tar(264M)
Test1k-Miech msrvtt10kmiech_model_best.pth.tar(267M)
Test1k-Yu msrvtt10kyu_model_best.pth.tar(267M)

Note that if you would like to evaluate using our trained checkpoints, please make sure to use the vocabulary and concept annotations that are provided in the msrvtt10k-resnext101_resnet152.tar.gz.

On the official split

Run the following script to download and evaluate our trained checkpoints on the official split of MSR-VTT. The trained checkpoints can also be downloaded from Baidu pan (url, password:p3p0).

MODELDIR=$HOME/VisualSearch/checkpoints
mkdir -p $MODELDIR

# download trained checkpoints
wegt -P $MODELDIR http://8.210.46.84:8787/checkpoints/msrvtt10k_model_best.pth.tar

# evaluate on the official split of MSR-VTT
CUDA_VISIBLE_DEVICES=0 python tester.py --testCollection msrvtt10k --logger_name $MODELDIR  --checkpoint_name msrvtt10k_model_best.pth.tar

On Test1k-Miech and Test1k-Yu splits

In order to evaluate on Test1k-Miech and Test1k-Yu splits, please run the following script.

MODELDIR=$HOME/VisualSearch/checkpoints

# download trained checkpoints on Test1k-Miech
wegt -P $MODELDIR http://8.210.46.84:8787/checkpoints/msrvtt10kmiech_model_best.pth.tar

# evaluate on Test1k-Miech of MSR-VTT
CUDA_VISIBLE_DEVICES=0 python tester.py --testCollection msrvtt10kmiech --logger_name $MODELDIR  --checkpoint_name msrvtt10kmiech_model_best.pth.tar
MODELDIR=$HOME/VisualSearch/checkpoints

# download trained checkpoints on Test1k-Yu
wegt -P $MODELDIR http://8.210.46.84:8787/checkpoints/msrvtt10kyu_model_best.pth.tar

# evaluate on Test1k-Yu of MSR-VTT
CUDA_VISIBLE_DEVICES=0 python tester.py --testCollection msrvtt10kyu --logger_name $MODELDIR  --checkpoint_name msrvtt10kyu_model_best.pth.tar

Expected Performance

The expected performance of Dual Encoding on MSR-VTT is as follows. Notice that due to random factors in SGD based training, the numbers differ slightly from those reported in the paper.

Split Text-to-Video Retrieval Video-to-Text Retrieval SumR
[email protected] [email protected] [email protected] MedR mAP [email protected] [email protected] [email protected] MedR mAP
Official 11.8 30.6 41.8 17 21.4 21.6 45.9 58.5 7 10.3 210.2
Test1k-Miech 22.7 50.2 63.1 5 35.6 24.7 52.3 64.2 5 37.2 277.2
Test1k-Yu 21.5 48.8 60.2 6 34.0 21.7 49.0 61.4 6 34.6 262.6

Dual Encoding on VATEX

Required Data

Download VATEX dataset (vatex-i3d.tar.gz(3.0G)) and a pre-trained word2vec (vec500flickr30m.tar.gz(3.0G)). The data can also be downloaded from Baidu pan (url, password:p3p0) or Google drive (url). For more information about the dataset, please refer to here. Please extract data into $HOME/VisualSearch/.

Model Training and Evaluation

Run the following script to train and evaluate Dual Encoding network with hybrid space on VATEX.

# download and extract dataset
wget http://8.210.46.84:8787/vatex-i3d.tar.gz
tar zxf vatex-i3d.tar.gz -C $ROOTPATH

./do_all.sh vatex hybrid i3d_kinetics $ROOTPATH

Expected Performance

Run the following script to download and evaluate our trained model (vatex_model_best.pth.tar(230M)) on VATEX.

MODELDIR=$HOME/VisualSearch/checkpoints

# download trained checkpoints
wegt -P $MODELDIR http://8.210.46.84:8787/checkpoints/vatex_model_best.pth.tar

CUDA_VISIBLE_DEVICES=0 python tester.py --testCollection vatex --logger_name $MODELDIR  --checkpoint_name vatex_model_best.pth.tar

The expected performance of Dual Encoding with hybrid space learning on MSR-VTT is as follows.

Split Text-to-Video Retrieval Video-to-Text Retrieval SumR
[email protected] [email protected] [email protected] MedR mAP [email protected] [email protected] [email protected] MedR mAP
VATEX 35.8 72.8 82.9 2 52.0 47.5 76.0 85.3 2 39.1 400.3

Dual Encoding on Ad-hoc Video Search (AVS)

Required Data

The following datasets are used for training, validation and testing: the joint collection of MSR-VTT and TGIF, tv2016train and IACC.3. For more information about these datasets, please refer to here.

Frame-level feature data

Please download the frame-level features from Baidu pan (url, password:qwlc). The filename of feature data are summarized as follows.

Datasets 2048-dim ResNeXt-101 2048-dim ResNet-152
MSR-VTT msrvtt10k_ResNext-101.tar.gz msrvtt10k_ResNet-152.tar.gz
TGIF tgif_ResNext-101.tar.gz tgif_ResNet-152.tar.gz
tv2016train tv2016train_ResNext-101.tar.gz tv2016train_ResNet-152.tar.gz
IACC.3 iacc.3_ResNext-101.tar.gz iacc.3_ResNet-152.tar.gz

Note if you have already download MSR-VTT data we provide above, you need not download msrvtt10k_ResNext-101.tar.gz and msrvtt10k_ResNet-152.tar.gz.

Sentence data

Please download the above data, and run the following scripts to extract them into $HOME/VisualSearch/.

ROOTPATH=$HOME/VisualSearch

# extract ResNext-101
tar zxf tgif_ResNext-101.tar.gz -C $ROOTPATH
tar zxf msrvtt10k_ResNext-101.tar.gz -C $ROOTPATH
tar zxf tv2016train_ResNext-101.tar.gz -C $ROOTPATH
tar zxf iacc.3_ResNext-101.tar.gz -C $ROOTPATH

# extract ResNet-152
tar zxf tgif_ResNet-152.tar.gz -C $ROOTPATH
tar zxf msrvtt10k_ResNet-152.tar -C $ROOTPATH
tar zxf tv2016train_ResNet-152.tar.gz -C $ROOTPATH
tar zxf iacc.3_ResNet-152.tar.gz -C $ROOTPATH

# combine feature of tgif and msrvtt10k
./do_combine_features.sh

Train Dual Encoding model from scratch

ROOTPATH=$HOME/VisualSearch
trainCollection=tgif-msrvtt10k
overwrite=0

# Generate a vocabulary on the training set
./util/do_get_vocab.sh $trainCollection $ROOTPATH $overwrite

# Generate concepts according to video captions
./util/do_get_tags.sh $trainCollection $ROOTPATH $overwrite

# Generate video frame info
visual_feature=resnext101-resnet152
./util/do_get_frameInfo.sh $trainCollection $visual_feature $ROOTPATH $overwrite

# training and testing
./do_all_avs.sh $ROOTPATH

How to run Dual Encoding on other datasets?

Our code supports dataset structure:

  • One-folder structure: train, validation and test subset are stored in a folder.
  • Multiple-folder structure: train, validation and test subset are stored in three folders respectively.

One-folder structure

Store the train, validation and test subset into a folder in the following structure.

${collection}
├── FeatureData
│   └── ${feature_name}
│       ├── feature.bin
│       ├── shape.txt
│       └── id.txt
└── TextData
    └── ${collection}train.caption.txt
    └── ${collection}val.caption.txt
    └── ${collection}test.caption.txt
  • FeatureData: video frame features. Using txt2bin.py to convert video frame feature in the required binary format.
  • ${collection}train.caption.txt: training caption data.
  • ${collection}val.caption.txt: validation caption data.
  • ${collection}test.caption.txt: test caption data. The file structure is as follows, in which the video and sent in the same line are relevant.
video_id_1#1 sentence_1
video_id_1#2 sentence_2
...
video_id_n#1 sentence_k
...

Please run the script to generate vocabulary and concepts:

./util/do_vocab_concept.sh $collection 0 $ROOTPATH

Run the following script to train and evaluate Dual Encoding on your own dataset:

./do_all.sh ${collection} hybrid ${feature_name} ${rootpath}

Multiple-folder structure

Store the training, validation and test subsets into three folders in the following structure respectively.

${subset_name}
├── FeatureData
│   └── ${feature_name}
│       ├── feature.bin
│       ├── shape.txt
│       └── id.txt
└── TextData
    └── ${subset_name}.caption.txt
  • FeatureData: video frame features.
  • ${dsubset_name}.caption.txt: caption data of corresponding subset.

You can run the following script to check whether the data is ready:

./do_format_check.sh ${train_set} ${val_set} ${test_set} ${rootpath} ${feature_name}

where train_set, val_set and test_set indicate the name of training, validation and test set, respectively, ${rootpath} denotes the path where datasets are saved and feature_name is the video frame feature name.

Please run the script to generate vocabulary and concepts:

./util/do_vocab_concept.sh ${train_set} 0 $ROOTPATH

If you pass the format check, use the following script to train and evaluate Dual Encoding on your own dataset:

./do_all_multifolder.sh ${train_set} ${val_set} ${test_set} hybrid ${feature_name} ${rootpath}

References

If you find the package useful, please consider citing our TPAMI'21 or CVPR'19 paper:

@article{dong2021dual,
  title={Dual Encoding for Video Retrieval by Text},
  author={Dong, Jianfeng and Li, Xirong and Xu, Chaoxi and Yang, Xun and Yang, Gang and Wang, Xun and Wang, Meng},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  doi = {10.1109/TPAMI.2021.3059295},
  year={2021}
}
@inproceedings{cvpr2019-dual-dong,
title = {Dual Encoding for Zero-Example Video Retrieval},
author = {Jianfeng Dong and Xirong Li and Chaoxi Xu and Shouling Ji and Yuan He and Gang Yang and Xun Wang},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019},
}
Scale-aware Automatic Augmentation for Object Detection (CVPR 2021)

SA-AutoAug Scale-aware Automatic Augmentation for Object Detection Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya Jia [Paper] [Bi

Jia Research Lab 182 Dec 29, 2022
[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

本文基于tensorflow、keras/pytorch实现对自然场景的文字检测及端到端的OCR中文文字识别 update20190706 为解决本项目中对数学公式预测的准确性,做了其他的改进和尝试,效果还不错,https://github.com/xiaofengShi/Image2Katex 希

xiaofeng 2.7k Dec 25, 2022
This repository summarized computer vision theories.

This repository summarized computer vision theories.

3 Feb 04, 2022
How to detect objects in real time by using Jupyter Notebook and Neural Networks , by using Yolo3

Real Time Object Recognition From your Screen Desktop . In this post, I will explain how to build a simply program to detect objects from you desktop

Ruslan Magana Vsevolodovna 2 Sep 28, 2022
PyQT5 app that colorize black & white pictures using CNN(use pre-trained model which was made with OpenCV)

About PyQT5 app that colorize black & white pictures using CNN(use pre-trained model which was made with OpenCV) Colorizor Приложение для проекта Yand

1 Apr 04, 2022
Pixel art search engine for opengameart

Pixel Art Reverse Image Search for OpenGameArt What does the final search look like? The final search with an example can be found here. It looks like

Eivind Magnus Hvidevold 92 Nov 06, 2022
Convert PDF/Image to TXT using EasyOcr - the best OCR engine available!

PDFImage2TXT - DOWNLOAD INSTALLER HERE What can you do with it? Convert scanned PDFs to TXT. Convert scanned Documents to TXT. No coding required!! In

Hans Alemão 2 Feb 22, 2022
TextBoxes re-implement using tensorflow

TextBoxes-TensorFlow TextBoxes re-implementation using tensorflow. This project is greatly inspired by slim project And many functions are modified ba

Gu Xiaodong 44 Dec 29, 2022
Pixie - A full-featured 2D graphics library for Python

Pixie - A full-featured 2D graphics library for Python Pixie is a 2D graphics library similar to Cairo and Skia. pip install pixie-python Features: Ty

treeform 65 Dec 30, 2022
Generates a message from the infamous Jerma Impostor image

Generate your very own jerma sus imposter message. Modes: Default Mode: Only supports the characters " ", !, a, b, c, d, e, h, i, m, n, o, p, q, r, s,

Giorno420 1 Oct 27, 2022
Drowsiness Detection and Alert System

A countless number of people drive on the highway day and night. Taxi drivers, bus drivers, truck drivers, and people traveling long-distance suffer from lack of sleep.

Astitva Veer Garg 4 Aug 01, 2022
~1000 book pages + OpenCV + python = page regions identified as paragraphs, lines, images, captions, etc.

cosc428-structor I had an open-ended Computer Vision assignment to complete, and an out-of-copyright book that I wanted to turn into an ebook. Convent

Chad Oliver 45 Dec 06, 2022
Validate and transform various OCR file formats (hOCR, ALTO, PAGE, FineReader)

ocr-fileformat Validate and transform between OCR file formats (hOCR, ALTO, PAGE, FineReader) Installation Docker System-wide Usage CLI GUI API Transf

Universitätsbibliothek Mannheim 152 Dec 20, 2022
Character Segmentation using TensorFlow

Character Segmentation Segment characters and spaces in one text line,from this paper Chinese English mixed Character Segmentation as Semantic Segment

26 Aug 25, 2022
Color Picker and Color Detection tool for METR4202

METR4202 Color Detection Help This is sample code that can be used for the METR4202 project demo. There are two files provided, both running on Python

Miguel Valencia 1 Oct 23, 2021
Demo processor to illustrate OCR-D Python API

ocrd_vandalize/ Demo processor to illustrate the OCR-D/core Python API Description :TODO: write docs :) Installation From PyPI pip3 install ocrd_vanda

Konstantin Baierer 5 May 05, 2022
A python screen recorder for low-end computers, provides high quality video output.

RecorderX - v1.0 A screen recorder made in Python with the help of OpenCv, it has ability to record your screen in high quality. No matter what your P

Priyanshu Jindal 4 Nov 10, 2021
code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

DeepCAD This repository provides source code for our paper: DeepCAD: A Deep Generative Network for Computer-Aided Design Models Rundi Wu, Chang Xiao,

Rundi Wu 85 Dec 31, 2022
make a better chinese character recognition OCR than tesseract

deep ocr See README_en.md for English installation documentation. 只在ubuntu下面测试通过,需要virtualenv安装,安装路径可自行调整: git clone https://github.com/JinpengLI/deep

Jinpeng 1.5k Dec 28, 2022