{"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/towards-unified-scene-text-spotting-based-on","title":"Towards Unified Scene Text Spotting based on Sequence Generation","arxiv_id":"2304.03435","date":"2023-04-07","proceeding":"CVPR 2023 1","authors":["Taeho Kil","Seonghyeon Kim","Sukmin Seo","Yoonsik Kim","Daehee Kim"],"abstract":"Sequence generation models have recently made significant progress in unifying various vision tasks. Although some auto-regressive models have demonstrated promising results in end-to-end text spotting, they use specific detection formats while ignoring various text shapes and are limited in the maximum number of text instances that can be detected. To overcome these limitations, we propose a UNIfied scene Text Spotter, called UNITS. Our model unifies various detection formats, including quadrilaterals and polygons, allowing it to detect text in arbitrary shapes. Additionally, we apply starting-point prompting to enable the model to extract texts from an arbitrary starting point, thereby extracting more texts beyond the number of instances it was trained on. Experimental results demonstrate that our method achieves competitive performance compared to state-of-the-art methods. Further analysis shows that UNITS can extract a larger number of texts than it was trained on. We provide the code for our method at https://github.com/clovaai/units.","url_abs":"https://arxiv.org/abs/2304.03435v1","url_pdf":"https://arxiv.org/pdf/2304.03435v1.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":"towards-unified-scene-text-spotting-based-on","repo_url":"https://github.com/clovaai/units","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-spotting-on-icdar-2015","task":"Text Spotting","dataset":"ICDAR 2015","model":"UNITS","rank_in_archive_order":1,"of":18,"metrics":{"F-measure (%) - Generic Lexicon":"80.3","F-measure (%) - Strong Lexicon":"89.0","F-measure (%) - Weak Lexicon":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-total-text","task":"Text Spotting","dataset":"Total-Text","model":"UNITS","rank_in_archive_order":5,"of":12,"metrics":{"F-measure (%) - Full Lexicon":"86.0","F-measure (%) - No Lexicon":"78.7"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.03435","atlas_url":"https://app.syntology.ai/?focus=2304.03435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03435"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/clovaai/units","reach":null}],"summary":{"ran":5,"ran_violates":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2dfdf4c6074881e3","entry":"DropPath","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2dfdf4c6074881e3"}},{"code_sha256_prefix":"47317ba080310bb3","entry":"FeedForwardLayer","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47317ba080310bb3"}},{"code_sha256_prefix":"80bf32862e6262ab","entry":"MLP","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80bf32862e6262ab"}},{"code_sha256_prefix":"aadfde725d36fb50","entry":"PositionalEncoding","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aadfde725d36fb50"}},{"code_sha256_prefix":"cb3d66f0d29d9cf4","entry":"Units","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb3d66f0d29d9cf4"}},{"code_sha256_prefix":"3012a28a2f1411bd","entry":"_floor_div","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3012a28a2f1411bd"}},{"code_sha256_prefix":"f5ab76486eeab7b9","entry":"drop_path","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5ab76486eeab7b9"}},{"code_sha256_prefix":"b0aa6ea96897be51","entry":"init_weights","repo":"clovaai/units","repo_kind":"official","path":"units/models/model.py","file_url":"https://github.com/clovaai/units/blob/HEAD/units/models/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0aa6ea96897be51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}