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

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Official implementation of ETH-XGaze dataset baseline

Deep Learning to Improve Breast Cancer Detection on Screening Mammography

Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis

Rethinking Nearest Neighbors for Visual Classification

Source code of D-HAN: Dynamic News Recommendation with Hierarchical Attention Network

Implementing DropPath/StochasticDepth in PyTorch

Implementation of our NeurIPS 2021 paper "A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs".

A Streamlit component to render ECharts.

Official Implementation (PyTorch) of "Point Cloud Augmentation with Weighted Local Transformations", ICCV 2021

GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification

Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

Efficient 3D Backbone Network for Temporal Modeling

Sample code and notebooks for Vertex AI, the end-to-end machine learning platform on Google Cloud

Pyramid Pooling Transformer for Scene Understanding

Boostcamp AI Tech 3rd / Basic Paper reading w.r.t Embedding

Code for the AI lab course 2021/2022 of the University of Verona

A tiny, friendly, strong baseline code for Person-reID (based on pytorch).

Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)

QuadTree Attention for Vision Transformers (ICLR2022)