{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/glass-global-to-local-attention-for-scene","title":"GLASS: Global to Local Attention for Scene-Text Spotting","arxiv_id":"2208.03364","date":"2022-08-05","proceeding":null,"authors":["Roi Ronen","Shahar Tsiper","Oron Anschel","Inbal Lavi","Amir Markovitz","R. Manmatha"],"abstract":"In recent years, the dominant paradigm for text spotting is to combine the tasks of text detection and recognition into a single end-to-end framework. Under this paradigm, both tasks are accomplished by operating over a shared global feature map extracted from the input image. Among the main challenges that end-to-end approaches face is the performance degradation when recognizing text across scale variations (smaller or larger text), and arbitrary word rotation angles. In this work, we address these challenges by proposing a novel global-to-local attention mechanism for text spotting, termed GLASS, that fuses together global and local features. The global features are extracted from the shared backbone, preserving contextual information from the entire image, while the local features are computed individually on resized, high-resolution rotated word crops. The information extracted from the local crops alleviates much of the inherent difficulties with scale and word rotation. We show a performance analysis across scales and angles, highlighting improvement over scale and angle extremities. In addition, we introduce an orientation-aware loss term supervising the detection task, and show its contribution to both detection and recognition performance across all angles. Finally, we show that GLASS is general by incorporating it into other leading text spotting architectures, improving their text spotting performance. Our method achieves state-of-the-art results on multiple benchmarks, including the newly released TextOCR.","url_abs":"https://arxiv.org/abs/2208.03364v1","url_pdf":"https://arxiv.org/pdf/2208.03364v1.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":"glass-global-to-local-attention-for-scene","repo_url":"https://github.com/amazon-research/glass-text-spotting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"glass-global-to-local-attention-for-scene","repo_url":"https://github.com/amazon-science/glass-text-spotting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"text-detection","task_name":"Text Detection"},{"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":"GLASS","rank_in_archive_order":8,"of":18,"metrics":{"F-measure (%) - Generic Lexicon":"76.3","F-measure (%) - Strong Lexicon":"84.7","F-measure (%) - Weak Lexicon":"80.1"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-total-text","task":"Text Spotting","dataset":"Total-Text","model":"GLASS","rank_in_archive_order":6,"of":12,"metrics":{"F-measure (%) - Full Lexicon":"83.0","F-measure (%) - No Lexicon":"76.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.03364","atlas_url":"https://app.syntology.ai/?focus=2208.03364","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2208.03364"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2208.03364\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2208.03364"},"call":"get_concepts_for_paper(arxiv_id=\"2208.03364\")"}],"by_repo":[{"repo":"amazon-research/glass-text-spotting","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"amazon-science/glass-text-spotting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51e1868f416ba7d554838f877deccf97ee81acad583d8bbed0e023c3d56e4af2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}