Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

Chen, Ying; Liang, Qiao; Cheng, Zhanzhan; Pu, Shiliang; Niu, Yi; Li, Xi

doi:10.1007/978-3-031-19815-1_21

Cited by 2 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach significantly improved real-time performance without sacrificing accuracy. Chen et al [29] proposed a low-cost and efficient dynamic resolution distillation framework, offering varying resolutions for different input texts and images to strike a balance between recognition accuracy and computational efficiency. Additionally, they introduced sequence knowledge distillation to achieve superior recognition results, particularly for low-resolution images.…”

Section: End-to-end Text Recognitionmentioning

confidence: 99%

A person re‐identification method for sports event scenes incorporating textual information mining

Wang,

Zhu,

Wan

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Person re‐identification represents a pivotal sub‐problem in image retrieval, boasting broad application prospects in fields such as intelligent security and video surveillance. However, most existing person re‐identification methods predominantly focus solely on visual features pertaining to the person targets, thereby disregarding some supporting information closely related to the scene context. In the context of athlete re‐identification during sports event scenes, the athlete bib number is fully considered, an important clue that can provide different athletes' identities, and the traditional visual features of the person and high‐level semantic information of the bib number text are fused. A multi‐source information mutual gain mechanism is designed to improve the accuracy of the person re‐identification task. In the existing only publicly available marathon bib number dataset RBNR, the recognition accuracy of this method is significantly superior to that of the existing person re‐identification method. In addition, this paper constructs and publishes an athlete re‐identification dataset (HNNU‐ReID8000) for mainstream sports events, and the mean average precision (mAP) value of this method reaches 96.1% on this dataset, significantly ahead of existing state‐of‐the‐art person re‐identification methods. The code and the HNNU‐ReID8000 dataset will be released at https://github.com/yanbin‐zhu/zyb_person‐reid.

show abstract

Section: End-to-end Text Recognitionmentioning

confidence: 99%