{"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/pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","arxiv_id":"1801.01315","date":"2018-01-04","proceeding":null,"authors":["Dan Deng","Haifeng Liu","Xuelong. Li","Deng Cai"],"abstract":"Most state-of-the-art scene text detection algorithms are deep learning based\nmethods that depend on bounding box regression and perform at least two kinds\nof predictions: text/non-text classification and location regression.\nRegression plays a key role in the acquisition of bounding boxes in these\nmethods, but it is not indispensable because text/non-text prediction can also\nbe considered as a kind of semantic segmentation that contains full location\ninformation in itself. However, text instances in scene images often lie very\nclose to each other, making them very difficult to separate via semantic\nsegmentation. Therefore, instance segmentation is needed to address this\nproblem. In this paper, PixelLink, a novel scene text detection algorithm based\non instance segmentation, is proposed. Text instances are first segmented out\nby linking pixels within the same instance together. Text bounding boxes are\nthen extracted directly from the segmentation result without location\nregression. Experiments show that, compared with regression-based methods,\nPixelLink can achieve better or comparable performance on several benchmarks,\nwhile requiring many fewer training iterations and less training data.","url_abs":"http://arxiv.org/abs/1801.01315v1","url_pdf":"http://arxiv.org/pdf/1801.01315v1.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":"pixellink-detecting-scene-text-via-instance","repo_url":"https://github.com/Autonise-AI/Text-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pixellink-detecting-scene-text-via-instance","repo_url":"https://github.com/ZJULearning/pixel_link","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pixellink-detecting-scene-text-via-instance","repo_url":"https://github.com/dengdan/seglink","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pixellink-detecting-scene-text-via-instance","repo_url":"https://github.com/mayank-git-hub/Text-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pixellink-detecting-scene-text-via-instance","repo_url":"https://github.com/opconty/pixellink_keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"PixelLink+VGG16 2s MS","rank_in_archive_order":6,"of":16,"metrics":{"F-Measure":"88.1%","Precision":"88.6","Recall":"87.5"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"SLPR","rank_in_archive_order":26,"of":43,"metrics":{"F-Measure":"84.5","Precision":"85.5","Recall":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","task":"Scene Text Detection","dataset":"MSRA-TD500","model":"PixelLink + VGG16 2s","rank_in_archive_order":16,"of":18,"metrics":{"F-Measure":"77.8","Precision":"83","Recall":"73.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.01315","atlas_url":"https://app.syntology.ai/?focus=1801.01315","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":"1801.01315"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.01315\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.01315"},"call":"get_concepts_for_paper(arxiv_id=\"1801.01315\")"}],"by_repo":[{"repo":"Autonise-AI/Text-Recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ZJULearning/pixel_link","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dengdan/seglink","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mayank-git-hub/Text-Recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"opconty/pixellink_keras","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":"ad7938218d79c3378110118ce78178893761e4c6a0a4a86d965337b3b0145e3d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}