{"url":"/dataset/total-text","name":"Total-Text","full_name":null,"description_markdown":"**Total-Text** is a text detection dataset that consists of 1,555 images with a variety of text types including horizontal, multi-oriented, and curved text instances. The training split and testing split have 1,255 images and 300 images, respectively.\r\n\r\nSource: [Convolutional Character Networks](https://arxiv.org/abs/1910.07954)\r\nImage Source: [https://github.com/cs-chan/Total-Text-Dataset](https://github.com/cs-chan/Total-Text-Dataset)","description_withheld":null,"homepage":"https://github.com/cs-chan/Total-Text-Dataset","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/total-text-a-comprehensive-dataset-for-scene","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","first_author":"Chee Kheng Chng","url":null},"license":{"name":"BSD-3","url":"https://github.com/cs-chan/Total-Text-Dataset/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"},{"name":"Text Spotting","url":"/task/text-spotting","datasets_with_task":"/datasets/task/text-spotting"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Total-Text"],"data_loaders":[{"repo":"https://github.com/Kaggle/kaggle-api","url":"https://www.kaggle.com/datasets/konradb/text-recognition-total-text-dataset","frameworks":[]},{"repo":"https://github.com/cs-chan/Total-Text-Dataset","url":"https://github.com/cs-chan/Total-Text-Dataset","frameworks":[]}],"num_papers_in_archive":156,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-detection-on-total-text","task":"Scene Text Detection","dataset_variant":"Total-Text","rows":27,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper":"/paper/mixnet-toward-accurate-detection-of","metrics":{"F-Measure":"90.5%","FPS":"15.2","Precision":"93.0","Recall":"88.1"},"code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-spotting-on-total-text","task":"Text Spotting","dataset_variant":"Total-Text","rows":12,"metrics":["F-measure (%) - No Lexicon","F-measure (%) - Full Lexicon"],"first_row_in_archive_order":{"model":"DeepSolo (ViTAEv2-S, TextOCR)","paper":"/paper/deepsolo-let-transformer-decoder-with","metrics":{"F-measure (%) - Full Lexicon":"89.6","F-measure (%) - No Lexicon":"83.6"},"code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/srformer-empowering-regression-based-text","title":"SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression","date":"2023-08-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/towards-unified-scene-text-spotting-based-on","title":"Towards Unified Scene Text Spotting based on Sequence Generation","date":"2023-04-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a3s-adversarial-learning-of-semantic","title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","date":"2023-02-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deepsolo-let-transformer-decoder-with","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","date":"2022-11-19","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/glass-global-to-local-attention-for-scene","title":"GLASS: Global to Local Attention for Scene-Text Spotting","date":"2022-08-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dptext-detr-towards-better-scene-text","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","date":"2022-07-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/text-spotting-transformers","title":"Text Spotting Transformers","date":"2022-04-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":7,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/swintextspotter-scene-text-spotting-via","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","date":"2022-03-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deer-detection-agnostic-end-to-end-recognizer","title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","date":"2022-03-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with-1","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","date":"2022-02-21","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","date":"2021-11-03","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/i3cl-intra-and-inter-instance-collaborative","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","date":"2021-08-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/abcnet-v2-adaptive-bezier-curve-network-for","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","date":"2021-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mango-a-mask-attention-guided-one-stage-scene","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","date":"2020-12-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mask-textspotter-v3-segmentation-proposal","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","date":"2020-07-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textfusenet-scene-text-detection-with-richer","title":"TextFuseNet: Scene Text Detection with Richer Fused Features","date":"2020-05-17","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":3,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sa-text-simple-but-accurate-detector-for-text","title":"A method for detecting text of arbitrary shapes in natural scenes that improves text spotting","date":"2019-11-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/convolutional-character-networks","title":"Convolutional Character Networks","date":"2019-10-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/efficient-and-accurate-arbitrary-shaped-text","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","date":"2019-08-16","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":4,"samples_unverified":24,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190412640","title":"TextCohesion: Detecting Text for Arbitrary Shapes","date":"2019-04-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":40,"samples_ran":6,"samples_unverified":34,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/shape-robust-text-detection-with-progressive-1","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2019-03-28","rows_on_this_dataset":1,"code_links":19,"syntology":null},{"paper":"/paper/textfield-learning-a-deep-direction-field-for","title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","date":"2018-12-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scene-text-detection-with-supervised-pyramid","title":"Scene Text Detection with Supervised Pyramid Context Network","date":"2018-11-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mask-textspotter-an-end-to-end-trainable","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","date":"2018-07-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textsnake-a-flexible-representation-for","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","date":"2018-07-04","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/total-text-a-comprehensive-dataset-for-scene","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","date":"2017-10-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fused-text-segmentation-networks-for-multi","title":"Fused Text Segmentation Networks for Multi-oriented Scene Text Detection","date":"2017-09-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/east-an-efficient-and-accurate-scene-text","title":"EAST: An Efficient and Accurate Scene Text Detector","date":"2017-04-11","rows_on_this_dataset":1,"code_links":31,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":130,"samples_ran":37,"samples_unverified":93,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}