{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/primitive-representation-learning-for-scene","title":"Primitive Representation Learning for Scene Text Recognition","arxiv_id":"2105.04286","date":"2021-05-10","proceeding":"CVPR 2021 1","authors":["Ruijie Yan","Liangrui Peng","Shanyu Xiao","Gang Yao"],"abstract":"Scene text recognition is a challenging task due to diverse variations of text instances in natural scene images. Conventional methods based on CNN-RNN-CTC or encoder-decoder with attention mechanism may not fully investigate stable and efficient feature representations for multi-oriented scene texts. In this paper, we propose a primitive representation learning method that aims to exploit intrinsic representations of scene text images. We model elements in feature maps as the nodes of an undirected graph. A pooling aggregator and a weighted aggregator are proposed to learn primitive representations, which are transformed into high-level visual text representations by graph convolutional networks. A Primitive REpresentation learning Network (PREN) is constructed to use the visual text representations for parallel decoding. Furthermore, by integrating visual text representations into an encoder-decoder model with the 2D attention mechanism, we propose a framework called PREN2D to alleviate the misalignment problem in attention-based methods. Experimental results on both English and Chinese scene text recognition tasks demonstrate that PREN keeps a balance between accuracy and efficiency, while PREN2D achieves state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2105.04286v1","url_pdf":"https://arxiv.org/pdf/2105.04286v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"primitive-representation-learning-for-scene","repo_url":"https://github.com/RuijieJ/pren","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"primitive-representation-learning-for-scene","repo_url":"https://github.com/jaguar-paw33/PREN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"primitive-representation-learning-for-scene","repo_url":"https://github.com/OneYearIsEnough/PaddleOCR-Recog-LmdbDataset-Conversion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"primitive-representation-learning-for-scene","repo_url":"https://github.com/developWmark/paddle_PROCR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.04286","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}