{"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/see-towards-semi-supervised-end-to-end-scene","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","arxiv_id":"1712.05404","date":"2017-12-14","proceeding":null,"authors":["Christian Bartz","Haojin Yang","Christoph Meinel"],"abstract":"Detecting and recognizing text in natural scene images is a challenging, yet\nnot completely solved task. In recent years several new systems that try to\nsolve at least one of the two sub-tasks (text detection and text recognition)\nhave been proposed. In this paper we present SEE, a step towards\nsemi-supervised neural networks for scene text detection and recognition, that\ncan be optimized end-to-end. Most existing works consist of multiple deep\nneural networks and several pre-processing steps. In contrast to this, we\npropose to use a single deep neural network, that learns to detect and\nrecognize text from natural images, in a semi-supervised way. SEE is a network\nthat integrates and jointly learns a spatial transformer network, which can\nlearn to detect text regions in an image, and a text recognition network that\ntakes the identified text regions and recognizes their textual content. We\nintroduce the idea behind our novel approach and show its feasibility, by\nperforming a range of experiments on standard benchmark datasets, where we\nachieve competitive results.","url_abs":"http://arxiv.org/abs/1712.05404v1","url_pdf":"http://arxiv.org/pdf/1712.05404v1.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":"see-towards-semi-supervised-end-to-end-scene","repo_url":"https://github.com/Bartzi/see","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"see-towards-semi-supervised-end-to-end-scene","repo_url":"https://github.com/jeasung-pf/see","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"text-detection","task_name":"Text Detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.05404","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}