PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
The DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.
Abstract
Scene text detection and recognition have been well explored in the past few years. Despite the progress, efficient and accurate end-to-end spotting of arbitrarily-shaped text remains challenging. In this work, we propose an end-to-end text spotting framework, termed PAN++, which can efficiently detect and recognize text of arbitrary shapes in natural scenes. PAN++ is based on the kernel representation that reformulates a text line as a text kernel (central region) surrounded by peripheral pixels. By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text. Moreover, as a pixel-based representation, the kernel representation can be predicted by a single fully convolutional network, which is very friendly to real-time applications. Taking the advantages of the kernel representation, we design a series of components as follows: 1) a computationally efficient feature enhancement network composed of stacked Feature Pyramid Enhancement Modules (FPEMs); 2) a lightweight detection head cooperating with Pixel Aggregation (PA); and 3) an efficient attention-based recognition head with Masked RoI. Benefiting from the kernel representation and the tailored components, our method achieves high inference speed while maintaining competitive accuracy. Extensive experiments show the superiority of our method. For example, the proposed PAN++ achieves an end-to-end text spotting F-measure of 64.9 at 29.2 FPS on the Total-Text dataset, which significantly outperforms the previous best method. Code will be available at: git.io/PAN.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 13×
“In 13 these experiments, we use ResNet18 as the default backbone network.”
MethodInfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“In virtue of the powerful representation of deep neural networks [1], [2], scene text detection and recognition has witnessed great progress in the past a few years [3], [4], [5], [6], [7], [8].”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 12×
“At time step 0 (initial time step), the decoder takes SOS’s feature vector fs and zero LSTM initial states as input.”
BackgroundInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“All models are optimized by using ADAM [66] optimizer with a batch size of 16 on 4 GPUs.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 4×
“3(f), where an attention-based text recognition head was added on Mask R-CNN to simultaneously detect and recognize irregular text lines.”
MethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“In these experiments, we use the ResNet [2] pre-trained on ImageNet [65] as the backbone network of our method.”
MethodGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
““Conv” and “BN” represent regular convolution [49] and Batch Normalization [50], respectively.”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 8×
“Second, we compare our feature enhancement network (2- stacked FPEMs) with other widely used methods, including FPN [51], PAFPN [74], and NAS-FPN [75].”
BackgroundMethodInfluential
Research works printed but not linked: 1
- [58] C. Yao, X. Bai, W. Liu, Y. Ma, and Z. Tu, 'Detecting texts of arbitrary orientations in natural images,' in Proc. IEEE Conf. Comp. Vis. Patt. Recogn. , 2012. - · DOI · Paper page
Cited by
Items 101–162 of 162
Zeng, C., & Song, C. (2022) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics55264.2022.9873542 · Cited by 2
“In order to improve the detection speed of PSENet, Pan++ [4] This work was partly supported by the National Natural Science Foundation of China (Grant No 61966006), the Guizhou Provincial Science and Technology Projects (Grant No [2020]1Y281), and the Science Research Foundation for High-level Talents of Guizhou Insti…”
BackgroundInfluentialCFS: Character Feature Summarization Model for Real-time End-to-end Text Spotting
Gong, C., Mei, H., Qiu, H., Hao, X., Jiao, J., Tang, S., & Li, H. (2023) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip59821.2023.10402719 · Cited by 1
“Most existing real-time methods [10], [12]–[14], [24] adopt a two-stage approach, where a detection head and a recognition head are separately used on a shared feature map to obtain the position and content of text instances.”
MethodInfluentialWu, J., Fang, Z., Lyu, P., Zhang, C., Chen, F., Lu, G., & Pei, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72751-1_17 · Cited by 5
Wang, L., Zhang, J., Wang, P., & Bai, Y. (2024) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.24231 · Cited by 1
Natural Scene Text Detection With Multiscale Feature Augmentation and Attention Mechanisms
Wang, G., Wang, R., Liang, M., Wei, S., Zhao, X., Yang, D., & Wang, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3502432 · Cited by 1
DLFANet: a Deep-Learned Fusion Attention Network for Robust Text Detection in Complex Scenes
Subbukalai, R., & vijayan, V. (2026) · Journal of Signal Processing Systems · doi:10.1007/s11265-025-01981-8 · Cited by 1
Scene Text Spotting With Decoupled Transformer
Su, Y., Chen, Z., Du, Y., Wu, Z., & Jiang, Y. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3673544 · Cited by 2
“MaskTextSpotter v3 [26] and PAN++ [27] adopt RoI-Mask to filter out noise by applying binary masks to features.”
Text Detection in Sign Images Using Maximally Stable External Regions and Stroke Width Transform
Fan, T., Sun, Q., Zhang, J., Tao, X., Xu, Y., & He, T. (2021) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei53629.2021.9624391 · Cited by 1
Scene Text Recognition: An Overview
Liang, S., Bi, N., & Tan, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-09037-0_27 · Cited by 1
Representative Batch Normalization for Scene Text Recognition
Sun, Y., Cao, X., & Sun, Y. (2022) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2022.07.015 · Cited by 1
Rwin-FPN++: Rwin Transformer with Feature Pyramid Network for Dense Scene Text Spotting
Zeng, C., Liu, Y. F., & Song, C. (2022) · Applied Sciences · doi:10.3390/app12178488 · Cited by 1
A Survey of Text Detection Algorithms in Images Based on Deep Learning
Li, L., Hu, C., & Liu, Y. (2022) · 2022 4th International Conference on Natural Language Processing (ICNLP) · doi:10.1109/icnlp55136.2022.00016 · Cited by 2
Robust Scene Text Detection Under Occlusion via Multi-scale Adaptive Deep Network
Dinh, M.-T., Tran, M.-T., Dang, Q.-V., & Lee, G.-S. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-4914-4_10 · Cited by 1
“With the development of deep learning, scene text detection [1, 3], scene text segmentation [27, 29, 32], scene text recognition [31], and text spotting [30] have many achievements in scene text reading.”
BackgroundDeformation Robust Text Spotting with Geometric Prior
Hao, X., Zhang, A., Meng, X., & Fu, B. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10223185 · Cited by 1
Refinement Correction Network for Scene Text Detection
Lian, Z., Yin, Y., Hu, W. D., Xu, Q., Zhi, M., Lu, J., & Qi, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5603-2_8 · Cited by 1
A Text Detector Based on the Specific Text Prompt
Lin, X., Gong, C., Wang, L., Qiu, H., Tong, S., & Li, H. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647439 · Cited by 1
Chinese Traffic Guide Panel Text Detection Based on Pixel Aggregation
Li, X., Han, T., Fan, X., & Zhao, W. (2024) · International Conference on Algorithm, Image Processing and Machine Vision (AIPMV) · doi:10.1109/aipmv62663.2024.10692256 · Cited by 1
“To overcome the problem of complex post-processing, PAN++ [3] adopts a series of light-weight modules, integrates the instance vector in the detection head and uses pixel aggregation (PA) to realize real-time end-to-end text detection and recognition.”
MethodSelf-citationArbitrary-Shape Text Spotting Based on Global, Pixel and Sequence Semantics
Chun-hu, Z., Ibrayim, M., Hamdulla, A., & Deng, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8702-9_34 · Cited by 1
NetOps-VL: Leveraging Multimodal LLM for Enhanced Network Operations
Lu, S., Shen, J., Guan, X., Yao, J.-L., Si, Y., Zhao, L., & Qian, B. (2024) · IEEE International Conference on Electronics and Communication Engineering (ICECE) · doi:10.1109/icece63871.2024.10976943 · Cited by 1
Deformable Kernel Expansion Model for Efficient Arbitrary-Shaped Scene Text DetectionPreprint
He, T., Huang, S., Tang, W., & Лю, Б. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4676354 · Cited by 1
Scene Text Detection based on Dual-branch Multi-resolution Feature-aware Enhancement Network
Wang, R., Li, Q., Huang, H., & Li, Q. (2022) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic54216.2022.9836553
RWYI: Reading What You Are Interested in with a Learning-Based Text Interactive System
Yu, Z., Wang, H., Yang, H., & Zhou, H. (2022) · Mobile Information Systems · doi:10.1155/2022/6378011
HTD: A Fast Human-centered Text-locating Method for Auxiliary Reading
Yu, Z., Wang, H., Yang, H., & Zhou, H. (2022) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv55858.2022.9953262
“At the same time, text recognition methods [14, 27, 28, 29, 30, 31] and text reading competitions [32] were also developing, which enabled the steady progress of auxiliary text reading tasks.”
BackgroundText Detection and Recognition in Natural Scene with Key-Points Detection and Multi-Hot Structure
Han, X., Qiu, W., Hou, J., & Zhou, Z. (2022) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait56212.2022.10138003
“PAN++ [24] use clustering methods to obtain text regions and use LSTM for recognition.”
MethodExploring Anchor-Free Approach for Reading Chinese Characters
Wang, Z., Wang, Y., Zhou, Z., Yuan, H., & Jin, C. (2023) · International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE) · doi:10.1145/3607541.3616813
Scene Text Detection with Box Supervision and Level Set Evolution
Zhao, M., Yin, F., & Liu, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47634-1_14
CVTD: A Robust Car-Mounted Video Text Detector
Zhou, D., Zhang, J., Li, C., Guo, Y., & Li, B. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.047236
Liu, Y., Zhou, G., Yang, Y., Ma, J., Tian, J., & Yang, J. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10451540
“We used PAN++ [12] as the base model and obtained a pre-trained model by following the pre-training procedure outlined in their original paper.”
MethodDATS: Driver assistance text spotter
Dave, D., Gandhi, J., Patel, P. B., & Bagi, R. (2024) · AIP conference proceedings · doi:10.1063/5.0209773
A Review on the Application of Segmentation-Based Text Detection Techniques for Natural Scenes
陈, 伟. (2024) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2024.132041
TWIST: Text-only Weakly Supervised Scene Text Spotting Using Pseudo Labels
Wen, L., Tang, X., & Zhang, D. (2024) · International Conference on Multimedia Retrieval · doi:10.1145/3652583.3658075
LATextSpotter: Empowering Transformer Decoder with Length Perception Ability
Li, Z., Qu, Y., Xie, H., & Zhang, Y. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558151
“Many other similar works [23] [24] [25] are striving to discover more robust connectors or more powerful proposal generation networks, achieving remarkable results.”
BackgroundMejoras en extracción de URLs en smishing mediante text spotting
Medina, P. B., Biswas, R., Castro, V. G., Aláiz-Rodríguez, R., Fidalgo, E., & Alegre, E. (2024) · Jornadas de Automática · doi:10.17979/ja-cea.2024.45.10954
A Real-Time Scene Uyghur Text Detection Network Based on Feature Complementation
Ibrayim, M., Chen, M., Hamdulla, A., Kang, J., & Chun-hu, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70549-6_4
Text Spotting with a Unified Transformer Decoder
Zheng, G., Qiu, M., & Gao, X. H. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650315
“…✓ 88.9 85.0 87.0 65.0 Unconstrained [37] ResNet-50 + MSF ✓ 83.3 83.4 83.3 67.8 Text Perceptron [8] ResNet-50 + FPN ✓ 88.8 81.8 85.2 69.7 PAN++ [38] ResNet18 + FPEMs ✓ – – – 68.6 ABCNet [29] ResNet-50 + FPN ✓ – – – 69.5 ABCNet v2 [30] ResNet-50 + FPN ✓ 90.2 84.1 87.0 70.4 SwinTextspotter [11]…”
InfluentialReal-Time Text Detection with Multi-level Feature Fusion and Pixel Clustering
Xu, L., Jiang, Z., Han, X., Wang, H., & Fan, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8511-7_2
Accurate extraction of handwritten text line in complex document images
Wu, R., Zeng, H., Xie, J., Hao, H., Gu, Q., & Chen, W. (2024) · IEEE International Conference on Computer Vision and Machine Intelligence (CVMI) · doi:10.1109/cvmi61877.2024.10781918
“Subsequently, Wang et al. [23] improved the PAN network to make inference faster and detection results more accurate.”
Hear the Scene: Audio-Enhanced Text SpottingPreprint
Li, J., & Wang, B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.19504
“Total-Text End-to-End None Full Fully-Supervised methods CharNet Xing et al. [2019] 66.2 - ABCNet Liu et al. [2020a] 64.2 75.7 PGNet Wang et al. [2021a] 63.1 - Mask TextSpotter Lyu et al. [2018] 65.3 77.4 Qin et al Qin et al. [2019] 67.8 - Mask TextSpotter v3 Liao et al. [2020] 71.2 78.4 MANGO Qiao et al. [2021] 72.9…”
InfluentialLi, J., & Zhou, H. (2025) · International Conference on Signal Processing and Computer Science (SPCS) · doi:10.1117/12.3053112
“We compared our algorithm with the following state-of-the-art methods: PAN++ [5], ABCNetV2 [6], SwinTextSpotter [7], TESTR [8], and DeepSolo [9].”
Li, Y., Shu, Y., Li, B., & Xu, R. (2025) · Electronics · doi:10.3390/electronics14050851 · Cited by 1
DoubleYolo: Efficient Scene Text Detection Using Double Edge Method and YOLOv8n
Mahesha, M., Aradhya, V. N. M., Basavaraju, H. T., & Siddesha, S. (2025) · Mathematical Modelling and Engineering Problems · doi:10.18280/mmep.120430
“The pixel wise representational traits shared by kernel version and fully convolutional neural network that efficiently represent text cases, efficiently and accurately [16].”
Wan, Y., Wu, Y., Hu, X., & Yao, L. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033246
Scene Text Detection Method with Improved Feature Pyramid and Feature Enhancement
Xia, Z., Wang, S., Yang, T., & Zhang, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9952-0_13
Compensating for the Incomplete With the Complete: An Efficient Scene Text Detector
Han, X., & Wang, Q. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3588711
“This result is still superior to some existing SOTA methods, which are trained directly on the MSRA-TD500, such as DBNet [7], PAN [35], and PAN ++ [54].”
Character feature Alignment-based scene text spotter
Han, G., Huang, H., Wang, Z., Sun, J., & Ye, J. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104533
Chinese Text Detection in Natural Scenes Based on Feature Pyramid with Attention Mechanism
Fu, Y., Lv, L., Liu, J., Wu, B., & Deng, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9869-1_34
A text-only weakly supervised learning framework for text spotting via text-to-polygon generator
Zhang, G., Gan, Z., Deng, L., Niu, S., Peng, Z., Dai, G., Huang, S., & Xu, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112408
Preventing Fake GPS Signal Assaults on Unmanned Vehicles through Contextual Learning - A Blueprint
Troja, E., DeBello, J. E., & Truong, L. M. (2025) · International Conference on Data Science and Its Applications (ICoDSA) · doi:10.1109/icodsa67155.2025.11157336
Balancing Optimization Strategies and Practical Goals: An Efficient Scene Text Detector
Han, X., Yang, C., Gao, J., & Wang, Q. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3623548
Advances in Text Detection and Recognition in Multi View Image Scenes
Sachith, B. K., & Umesh, D. (2025) · International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) · doi:10.1109/iacis65746.2025.11211428
Bao, Z., & Ibrayim, M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229105
EdgeSpotter: Multi-Scale Dense Text Spotting for Industrial Panel Monitoring
Fu, C., Lin, H., Zuo, H., Yao, L., & Zhang, L. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247478
“Furthermore, the practical effectiveness of these methods has not been thoroughly validated in real-world industrial settings, and their high computational demands present challenges for edge deployment.”
End-to-End Shipping Container Code Spotting Based on Visual Sensors for Intelligent Inspection
Chen, H., Piao, X., You, S., Jiang, M., Chen, C., & Chen, P. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3641379
“But, both CTC-based and attention-based methods are highly susceptible to the impact of detection network performance due to error accumulation [18], [19], [20].”
InfluentialPrompt-Based Dynamic Text Detector for Real-Time Industrial Panel Monitoring
Zheng, H., Hua, L., Zuo, H., & Fu, C. (2025) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm65671.2025.11293714
LICS: Locating Inter-Character Spaces for Multilingual Scene Text Detection
Su, P.-C., Lee, M.-C., Tung, Y.-T., Chen, L., Han, C.-H., & Kuo, T.-Y. (2025) · Sensors · doi:10.3390/s26010197
Li, W., Lyu, C., Ji, W. D., Zhou, L., Gurrin, C. G., & Guo, Y. F. (2025) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp64401.2025.11324237
“Our study utilizes PAN++ [14], a model adept at text detection and recognition, especially for text of arbitrary shapes.”
AI-Driven Document Intelligence: A Survey on Preprocessing, Detection and Recognition
Cheng, T., Feng, S., Yu, Z., Liu, F., Zhang, P., & Song, P. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11387963
“Wang, Qian et al. [38] made in-depth improvements to PAN.”
A Novel Framework for Robust Scene Text Localization: The OmniTextNet Paradigm
Li, S., Liu, Y., Chai, L., & Liu, Y. (2025) · International Conference on Computer, Vision and Intelligent Technology (ICCVIT) · doi:10.1109/iccvit67848.2025.11391334
FastGOT: Task-Driven Visual Tokens Pruning
Long, T., & Guan, L. (2025) · International Conference on Data Science and Intelligent Systems (DSIS) · doi:10.1109/dsis67228.2025.11390106
“Some methods [28]– [31] have attempted to simplify pipelines by integrating text detection and recognition into an end-to-end model, sharing a common backbone network to improve accuracy and efficiency.”
Universal Adversarial Watermarking for Text Image Protection via Template-Based Underpainting
Yan, F., Huang, Y., Dong, L., Deng, J., Jiang, Q., Wang, Z., & Liao, X. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3695161
“Pixel-level classification methods employ pixel-level classification followed by post-processing to generate detection boxes, making them well-suited for irregular or curved text, such as PSENet [19] and PAN++ [20].”
Multi-query text spotter transformer for arbitrary shape scene text detection and recognition
Xu, C., Chen, Y., Li, J., & Shi, C. (2026) · Physica Scripta · doi:10.1088/1402-4896/ae94bb
Sparse-TextSpotter: Efficient Text Spotting with Encoder Token Sparsification
Sultan, T., Eli, E., Tursun, I., Abudugeni, M., & Ubul, K. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729542
Metadata
- Authors
- Wang, W., Xie, E., Li, X., Liu, X., Liang, D., Zhibo, Y., Lu, T., & Shen, C.
- Affiliations
- Nanjing University (CN)
- University of Hong Kong (HK)
- Nanjing University of Science and Technology (CN)
- Sensetime (China) (CN)
- Monash University (AU)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021
- Volume
- 44
- Issue
- 9
- Pages
- 1-1
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3159307593
- Semantic Scholar
- 70aa3857040d2934ab7544988468ede697cb90c9
- Cited by
- 140
- References
- 73
- Citations by year
- 2026: 6 · 2025: 31 · 2024: 47 · 2023: 27 · 2022: 26 · 2021: 3
- FWCI
- 9.26
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Vehicle License Plate Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- scene text detection, scene text recognition, lightweight detection head, pixel aggregation, real-time inference
- MeSH terms
- Algorithms
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.