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}
}
87 Jan 03, 2023
27 Dec 10, 2022
2 Dec 30, 2021
7 Dec 27, 2022
12.2k Jan 03, 2023
2 Jan 05, 2023
43 Nov 17, 2022
208 Dec 23, 2022
3 Nov 16, 2022
25 Jul 19, 2022
76 Dec 12, 2022
47 Dec 20, 2022
3 Dec 26, 2022
58 Dec 21, 2022
1.8k Jan 01, 2023
268 Jan 09, 2023
7 Jul 12, 2022
13 Jul 25, 2022
4.9k Dec 29, 2022
18 Dec 09, 2022