{"task":"Text Spotting","dataset":"Total-Text","metric_names":["F-measure (%) - No Lexicon","F-measure (%) - Full Lexicon"],"rows":[{"id":10348,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"DeepSolo (ViTAEv2-S, TextOCR)","metrics":{"F-measure (%) - Full Lexicon":"89.6","F-measure (%) - No Lexicon":"83.6"},"paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","paper_date":"2022-11-19","code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":10349,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"DeepSolo (ResNet-50, TextOCR)","metrics":{"F-measure (%) - Full Lexicon":"88.7","F-measure (%) - No Lexicon":"82.5"},"paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","paper_date":"2022-11-19","code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":10350,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"DeepSolo (ResNet-50)","metrics":{"F-measure (%) - Full Lexicon":"87.0","F-measure (%) - No Lexicon":"79.7"},"paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","paper_date":"2022-11-19","code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10351,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"A3S","metrics":{"F-measure (%) - Full Lexicon":"85.1","F-measure (%) - No Lexicon":"79.4"},"paper_url":"https://arxiv.org/abs/2302.10641v1","paper_title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","paper_date":"2023-02-21","code_links":[],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10352,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"UNITS","metrics":{"F-measure (%) - Full Lexicon":"86.0","F-measure (%) - No Lexicon":"78.7"},"paper_url":"https://arxiv.org/abs/2304.03435v1","paper_title":"Towards Unified Scene Text Spotting based on Sequence Generation","paper_date":"2023-04-07","code_links":[{"title":"clovaai/units","url":"https://github.com/clovaai/units"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":10353,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"GLASS","metrics":{"F-measure (%) - Full Lexicon":"83.0","F-measure (%) - No Lexicon":"76.6"},"paper_url":"https://arxiv.org/abs/2208.03364v1","paper_title":"GLASS: Global to Local Attention for Scene-Text Spotting","paper_date":"2022-08-05","code_links":[{"title":"amazon-science/glass-text-spotting","url":"https://github.com/amazon-science/glass-text-spotting"},{"title":"amazon-research/glass-text-spotting","url":"https://github.com/amazon-research/glass-text-spotting"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10354,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"DEER","metrics":{"F-measure (%) - Full Lexicon":"83.3","F-measure (%) - No Lexicon":"74.8"},"paper_url":"https://arxiv.org/abs/2203.05122v1","paper_title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","paper_date":"2022-03-10","code_links":[],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10355,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"SwinTextSpotter","metrics":{"F-measure (%) - Full Lexicon":"84.1","F-measure (%) - No Lexicon":"74.3"},"paper_url":"https://arxiv.org/abs/2203.10209v1","paper_title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","paper_date":"2022-03-19","code_links":[{"title":"mxin262/swintextspotter","url":"https://github.com/mxin262/swintextspotter"},{"title":"jacobtyo/swintextspotter","url":"https://github.com/jacobtyo/swintextspotter"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10356,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"TESTR","metrics":{"F-measure (%) - Full Lexicon":"83.9","F-measure (%) - No Lexicon":"73.3"},"paper_url":"https://arxiv.org/abs/2204.01918v1","paper_title":"Text Spotting Transformers","paper_date":"2022-04-05","code_links":[{"title":"mlpc-ucsd/testr","url":"https://github.com/mlpc-ucsd/testr"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10357,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"MANGO","metrics":{"F-measure (%) - Full Lexicon":"83.6","F-measure (%) - No Lexicon":"72.9"},"paper_url":"https://arxiv.org/abs/2012.04350v2","paper_title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","paper_date":"2020-12-08","code_links":[{"title":"hikopensource/davar-lab-ocr","url":"https://github.com/hikopensource/davar-lab-ocr"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10358,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"MaskTextSpotter v3","metrics":{"F-measure (%) - Full Lexicon":"78.4","F-measure (%) - No Lexicon":"71.2"},"paper_url":"https://arxiv.org/abs/2007.09482v1","paper_title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","paper_date":"2020-07-18","code_links":[{"title":"MhLiao/MaskTextSpotterV3","url":"https://github.com/MhLiao/MaskTextSpotterV3"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":10359,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"ABCNet v2","metrics":{"F-measure (%) - Full Lexicon":"78.1","F-measure (%) - No Lexicon":"70.4"},"paper_url":"https://arxiv.org/abs/2105.03620v3","paper_title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","paper_date":"2021-05-08","code_links":[{"title":"Yuliang-Liu/ABCNet_Chinese","url":"https://github.com/Yuliang-Liu/ABCNet_Chinese"}],"metrics_order":"[\"F-measure (%) - No Lexicon\", \"F-measure (%) - Full Lexicon\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":590157,"task":"Text Spotting","parent_task":null,"dataset":"Total-Text","model_name":"Soft","metrics":{"F-measure (%) - Full Lexicon":"83.4"},"paper_url":"https://paperswithcode.com/paper/do-you-need-text-rectification-soft-attention-mask-embedding-for-rectification-free-scene-text-spotting","paper_title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","paper_date":"2026-05-18","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}