TransVTSpotter: End-to-end Video Text Spotter with Transformer

Last update: Dec 26, 2022

Related tags

Deep Learning TransVTSpotter

Overview

TransVTSpotter: End-to-end Video Text Spotter with Transformer

Introduction

A Multilingual, Open World Video Text Dataset and End-to-end Video Text Spotter with Transformer

Link to our MOVText: A Large-Scale, Multilingual Open World Dataset for Video Text Spotting

Updates

(08/04/2021) Refactoring the code.
(10/20/2021) The complete code has been released .

ICDAR2015(video) Tracking challenge

Methods	MOTA	MOTP	IDF1	Mostly Matched	Partially Matched	Mostly Lost
TransVTSpotter	45.75	73.58	57.56	658	611	647

Notes

The training time is on 8 NVIDIA V100 GPUs with batchsize 16.
We use the models pre-trained on COCOTextV2.
We do not release the recognition code due to the company's regulations.

Demo

Installation

The codebases are built on top of Deformable DETR and TransTrack.

Requirements

Linux, CUDA>=9.2, GCC>=5.4
Python>=3.7
PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this
OpenCV is optional and needed by demo and visualization

Steps

Install and build libs

git clone [email protected]:weijiawu/TransVTSpotter.git
cd TransVTSpotter
cd models/ops
python setup.py build install
cd ../..
pip install -r requirements.txt

Prepare datasets and annotations

# pretrain COCOTextV2
python3 track_tools/convert_COCOText_to_coco.py

# ICDAR15
python3 track_tools/convert_ICDAR15video_to_coco.py

COCOTextV2 dataset is available in COCOTextV2.

python3 track_tools/convert_crowdhuman_to_coco.py

ICDAR2015 dataset is available in icdar2015.

python3 track_tools/convert_mot_to_coco.py

Pre-train on COCOTextV2

python3 -m torch.distributed.launch --nproc_per_node=8 --use_env main_track.py  --output_dir ./output/Pretrain_COCOTextV2 --dataset_file pretrain --coco_path ./Data/COCOTextV2 --batch_size 2  --with_box_refine --num_queries 500 --epochs 300 --lr_drop 100 --resume ./output/Pretrain_COCOTextV2/checkpoint.pth

python3 track_tools/Pretrain_model_to_mot.py

The pre-trained model is available Baidu Netdisk， password:59w8. Google Netdisk

And the MOTA 44% can be found here password:xnlw. Google Netdisk

Train TransVTSpotter

python3 -m torch.distributed.launch --nproc_per_node=8 --use_env main_track.py  --output_dir ./output/ICDAR15 --dataset_file text --coco_path ./Data/ICDAR2015_video --batch_size 2  --with_box_refine  --num_queries 300 --epochs 80 --lr_drop 40 --resume ./output/Pretrain_COCOTextV2/pretrain_coco.pth

Visualize TransVTSpotter

python3 track_tools/Evaluation_ICDAR15_video/vis_tracking.py

License

TransVTSpotter is released under MIT License.

Citing

If you use TranVTSpotter in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@article{wu2021opentext,
  title={A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer},
  author={Weijia Wu, Debing Zhang, Yuanqiang Cai, Sibo Wang, Jiahong Li, Zhuang Li, Yejun Tang, Hong Zhou},
  journal={35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks},
  year={2021}
}

TransVTSpotter: End-to-end Video Text Spotter with Transformer

Related tags

Overview

TransVTSpotter: End-to-end Video Text Spotter with Transformer

Introduction

Updates

ICDAR2015(video) Tracking challenge

Notes

Demo

Installation

Requirements

Steps

License

Citing

Owner

weijiawu

Predict the latency time of the deep learning models

A Pytorch reproduction of Range Loss, which is proposed in paper 《Range Loss for Deep Face Recognition with Long-Tailed Training Data》

Learning Off-Policy with Online Planning, CoRL 2021

Code for Ditto: Building Digital Twins of Articulated Objects from Interaction

A Self-Supervised Contrastive Learning Framework for Aspect Detection

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)

Official PyTorch Implementation of Unsupervised Learning of Scene Flow Estimation Fusing with Local Rigidity

This is project is the implementation of the DeepShift: Towards Multiplication-Less Neural Networks paper

Benchmark library for high-dimensional HPO of black-box models based on Weighted Lasso regression

DAT4 - General Assembly's Data Science course in Washington, DC

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

This is a Keras implementation of a CNN for estimating age, gender and mask from a camera.

Liecasadi - liecasadi implements Lie groups operation written in CasADi

AAI supports interdisciplinary research to help better understand human, animal, and artificial cognition.

This repository is the code of the paper Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

This is the code of NeurIPS'21 paper "Towards Enabling Meta-Learning from Target Models".

Uni-Fold: Training your own deep protein-folding models

Learning Chinese Character style with conditional GAN

Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV

Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)