{"id":"https://openalex.org/W4404520683","doi":"https://doi.org/10.1109/tpami.2024.3496576","title":"Partial Scene Text Retrieval","display_name":"Partial Scene Text Retrieval","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404520683","doi":"https://doi.org/10.1109/tpami.2024.3496576","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030386"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3496576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3496576","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-2227-075X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2227-075X","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030174783","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0002-2583-4314"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Liao","raw_affiliation_strings":["Huawei, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2583-4314","affiliations":[{"raw_affiliation_string":"Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011170398","display_name":"Zhouyi Xie","orcid":"https://orcid.org/0009-0006-3030-340X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouyi Xie","raw_affiliation_strings":["Huawei, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-3030-340X","affiliations":[{"raw_affiliation_string":"Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665053","display_name":"Wenyu Liu","orcid":"https://orcid.org/0000-0002-4582-7488"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Liu","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4582-7488","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3449-5940","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1412159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"47","issue":"3","first_page":"1548","last_page":"1563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7037326097488403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6166930794715881},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5347674489021301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40266117453575134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38416188955307007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037326097488403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6166930794715881},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5347674489021301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40266117453575134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38416188955307007}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3496576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3496576","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030386","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030386","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2195389174","display_name":null,"funder_award_id":"2023YFF0905400","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1922126009","https://openalex.org/W1994488211","https://openalex.org/W2010576059","https://openalex.org/W2012689760","https://openalex.org/W2053317383","https://openalex.org/W2064675550","https://openalex.org/W2107698128","https://openalex.org/W2110119381","https://openalex.org/W2123410090","https://openalex.org/W2160741934","https://openalex.org/W2166010828","https://openalex.org/W2250539671","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2563764042","https://openalex.org/W2565639579","https://openalex.org/W2605982830","https://openalex.org/W2727586675","https://openalex.org/W2784050770","https://openalex.org/W2786459439","https://openalex.org/W2888894220","https://openalex.org/W2914492226","https://openalex.org/W2962986948","https://openalex.org/W2963299604","https://openalex.org/W2963516811","https://openalex.org/W2963647456","https://openalex.org/W2963908984","https://openalex.org/W2964294787","https://openalex.org/W2970910956","https://openalex.org/W2981969038","https://openalex.org/W2982770724","https://openalex.org/W2996956254","https://openalex.org/W2997371611","https://openalex.org/W2998621280","https://openalex.org/W3003218881","https://openalex.org/W3003711889","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3004206460","https://openalex.org/W3034792612","https://openalex.org/W3086275027","https://openalex.org/W3097932944","https://openalex.org/W3102695566","https://openalex.org/W3110398855","https://openalex.org/W3138516171","https://openalex.org/W3177167102","https://openalex.org/W3186906052","https://openalex.org/W3196976036","https://openalex.org/W4214922754","https://openalex.org/W4225683503","https://openalex.org/W4241698512","https://openalex.org/W4253518031","https://openalex.org/W4295246343","https://openalex.org/W4296473552","https://openalex.org/W4312658754","https://openalex.org/W4321485374","https://openalex.org/W6636510571","https://openalex.org/W6636915900","https://openalex.org/W6640383297","https://openalex.org/W6691603626"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0,281],"task":[1],"of":[2,40,54,86,137,207],"partial":[3,43,78,106,185,209,229],"scene":[4,91],"text":[5,12,24,89,92,233,258],"retrieval":[6],"involves":[7],"localizing":[8],"and":[9,76,90,99,148,204,219,228,243,268,284],"searching":[10,41],"for":[11,42,146,182,252,277],"instances":[13,48,75,227],"that":[14,69,178],"are":[15,286],"the":[16,38,58,83,183,192,201,205,213,253,278],"same":[17],"or":[18],"similar":[19],"to":[20,51,118,163],"a":[21,52,67,95,112,134,158,172,188],"given":[22],"query":[23,123],"from":[25,187],"an":[26],"image":[27],"gallery.":[28],"However,":[29,129],"existing":[30],"methods":[31],"can":[32,70,141,179],"only":[33],"handle":[34,105],"text-line":[35,47,74,189,226],"instances,":[36],"leaving":[37],"problem":[39],"patches":[44],"within":[45],"these":[46],"unsolved":[49],"due":[50],"lack":[53],"patch":[55,186],"annotations":[56],"in":[57,222],"training":[59],"data.":[60],"To":[61,104,152],"address":[62,153],"this":[63,154],"issue,":[64,155],"we":[65,156,170],"propose":[66,157],"network":[68],"simultaneously":[71],"retrieve":[72],"both":[73,217],"their":[77,101,120],"patches.":[79,210,230],"Our":[80],"method":[81,215,236],"embeds":[82],"two":[84,223,254,279],"types":[85],"data":[87],"(query":[88],"instances)":[93],"into":[94],"shared":[96],"feature":[97],"space":[98],"measures":[100],"cross-modal":[102],"similarities.":[103],"patches,":[107],"our":[108,235,260],"proposed":[109,214],"approach":[110,117,162,261],"adopts":[111],"Multiple":[113],"Instance":[114],"Learning":[115],"(MIL)":[116],"learn":[119],"similarities":[121],"with":[122],"text,":[124],"without":[125,195],"requiring":[126,196],"extra":[127],"annotations.":[128],"constructing":[130],"bags,":[131],"which":[132],"is":[133],"standard":[135],"step":[136],"conventional":[138],"MIL":[139,160],"approaches,":[140],"introduce":[142],"numerous":[143],"noisy":[144,167],"samples":[145],"training,":[147],"lower":[149],"inference":[150,193],"speed.":[151],"Ranking":[159],"(RankMIL)":[161],"adaptively":[164],"filter":[165],"those":[166],"samples.":[168],"Additionally,":[169],"present":[171],"Dynamic":[173],"Partial":[174],"Match":[175],"Algorithm":[176],"(DPMA)":[177],"directly":[180],"search":[181,202],"target":[184],"instance":[190],"during":[191],"stage,":[194],"bags.":[197],"This":[198],"greatly":[199],"improves":[200],"efficiency":[203],"performance":[206],"retrieving":[208,225],"We":[211],"evaluate":[212],"on":[216,246,271],"English":[218,232],"Chinese":[220,257],"datasets":[221,251,276],"tasks:":[224],"For":[231,256],"retrieval,":[234,259],"outperforms":[237],"state-of-the-art":[238,263],"approaches":[239,264],"by":[240,265],"8.04%":[241],"mAP":[242,245,267,270],"12.71%":[244],"average,":[247,272],"respectively,":[248,273],"among":[249,274],"three":[250,275],"tasks.":[255,280],"surpasses":[262],"24.45%":[266],"38.06%":[269],"source":[282],"code":[283],"dataset":[285],"available":[287],"at":[288],"https://github.com/lanfeng4659/PSTR.":[289]},"counts_by_year":[],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}