One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer-Reference-Cited by-同舟云学术

One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer

Published:2023-10-26 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 31st ACM International Conference on Multimedia
language:
Short-container-title:

Author:

Guo Hang¹^ORCID,Dai Tao²^ORCID,Zhu Mingyan¹^ORCID,Meng Guanghao³^ORCID,Chen Bin⁴^ORCID,Wang Zhi¹^ORCID,Xia Shu-Tao⁵^ORCID

Affiliation:

1. Tsinghua University, Shenzhen, China

2. Shenzhen University, Shenzhen, China

3. Tsinghua University, Peng Cheng Laboratory, Shenzhen, China

4. Harbin Institute of Technology, Shenzhen, Shenzhen, China

5. Tsinghua University & Peng Cheng Laboratory, Shenzhen, China

Funder

Shenzhen Science and Technology Program

PCNL KEY project

National Key Research and Development Program of China

National Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3581783.3611777

Reference62 articles.

1. Sequence-to-Sequence Contrastive Learning for Text Recognition

2. Mohamad Alansari , Oussama Abdul Hay , Sajid Javed, Abdulhaid Shoufan, Yahya Zweiri, and Naoufel Werghi. 2023 . GhostFaceNets: Lightweight Face Recognition Model from Cheap Operations. IEEE Access ( 2023). Mohamad Alansari, Oussama Abdul Hay, Sajid Javed, Abdulhaid Shoufan, Yahya Zweiri, and Naoufel Werghi. 2023. GhostFaceNets: Lightweight Face Recognition Model from Cheap Operations. IEEE Access (2023).

3. Darwin Bautista and Rowel Atienza . 2022 . Scene text recognition with permuted autoregressive sequence models. In Computer Vision--ECCV 2022: 17th European Conference , Tel Aviv , Israel, October 23-27, 2022, Proceedings, Part XXVIII. Springer, 178--196. Darwin Bautista and Rowel Atienza. 2022. Scene text recognition with permuted autoregressive sequence models. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVIII. Springer, 178--196.

4. Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation

5. An approach to road scene text recognition with per-frame accumulation and dynamic stopping decision