{"id":"https://openalex.org/W4304091789","doi":"https://doi.org/10.1145/3503161.3548237","title":"Point to Rectangle Matching for Image Text Retrieval","display_name":"Point to Rectangle Matching for Image Text Retrieval","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091789","doi":"https://doi.org/10.1145/3503161.3548237"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548237","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401164","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-3846-9157"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046424663","display_name":"Zhenwei Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenwei Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063603492","display_name":"Yadan Luo","orcid":"https://orcid.org/0000-0001-6272-2971"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yadan Luo","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100401164"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.4978,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.8828247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4977","last_page":"4986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rectangle","display_name":"Rectangle","score":0.6470933556556702},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6093441247940063},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5903258323669434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5783079266548157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4741729497909546},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.444012850522995},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4266052544116974},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42542409896850586},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42033398151397705},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.416192889213562},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41030487418174744},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3562648892402649},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33274349570274353}],"concepts":[{"id":"https://openalex.org/C2781302577","wikidata":"https://www.wikidata.org/wiki/Q209","display_name":"Rectangle","level":2,"score":0.6470933556556702},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6093441247940063},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5903258323669434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5783079266548157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4741729497909546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.444012850522995},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4266052544116974},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42542409896850586},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42033398151397705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.416192889213562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41030487418174744},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3562648892402649},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33274349570274353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548237","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G7385537255","display_name":null,"funder_award_id":"U20B2063 and 61976049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2117539524","https://openalex.org/W2250539671","https://openalex.org/W2560835477","https://openalex.org/W2596142952","https://openalex.org/W2606473278","https://openalex.org/W2744926832","https://openalex.org/W2883311563","https://openalex.org/W2962964995","https://openalex.org/W2963223306","https://openalex.org/W2963869273","https://openalex.org/W2982078236","https://openalex.org/W3037773948","https://openalex.org/W3108373531","https://openalex.org/W3109684201","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3155230099","https://openalex.org/W3169472988","https://openalex.org/W3201877472","https://openalex.org/W3205084812","https://openalex.org/W3205408642","https://openalex.org/W3206597437","https://openalex.org/W4207052765","https://openalex.org/W4245551996","https://openalex.org/W4288083516","https://openalex.org/W6600103761"],"related_works":["https://openalex.org/W2242098268","https://openalex.org/W4244945894","https://openalex.org/W4224881918","https://openalex.org/W2003462717","https://openalex.org/W2802042052","https://openalex.org/W174828583","https://openalex.org/W1987609185","https://openalex.org/W2321986606","https://openalex.org/W2059098648","https://openalex.org/W1976660375"],"abstract_inverted_index":{"The":[0],"difficulty":[1],"of":[2,11,18,48,73,119,130,167,199],"image-text":[3,109,200],"retrieval":[4,74],"is":[5,65,102,115],"further":[6],"exacerbated":[7],"by":[8,25],"the":[9,19,30,34,40,46,117,152,165,174,197],"phenomenon":[10],"one-to-many":[12,77,153],"correspondence,":[13,78],"where":[14],"multiple":[15,178],"semantic":[16,160],"manifestations":[17],"other":[20],"modality":[21],"could":[22,122,137,149],"be":[23,123,138],"obtained":[24],"a":[26,61,70,84,91,103,128,134,158],"given":[27],"query.":[28],"However,":[29],"prevailing":[31],"methods":[32],"adopt":[33],"deterministic":[35,62],"embedding":[36,136],"strategy":[37],"to":[38,68,86,93,125,141],"retrieve":[39],"most":[41],"similar":[42],"candidate,":[43],"which":[44,100],"encodes":[45],"representations":[47,118],"different":[49,120],"modalities":[50,121],"as":[51,97],"single":[52],"points":[53,131],"in":[54,195],"vector":[55],"space.":[56],"We":[57],"argue":[58],"that":[59,116],"such":[60,133],"point":[63],"mapping":[64],"obviously":[66],"insufficient":[67],"represent":[69],"potential":[71],"set":[72,129],"results":[75],"for":[76,108,169,177],"despite":[79],"its":[80],"noticeable":[81],"progress.":[82],"As":[83],"remedy":[85],"this":[87],"issue,":[88],"we":[89,156],"propose":[90],"Point":[92],"Rectangle":[94],"Matching":[95],"(abbreviated":[96],"P2RM)":[98],"mechanism,":[99],"actually":[101],"geometric":[104],"representation":[105],"learning":[106],"method":[107,148,163],"retrieval.":[110,201],"Specifically,":[111],"our":[112,146,170,191],"intuitive":[113],"insight":[114],"extended":[124],"rectangles,":[126],"then":[127],"inside":[132],"rectangle":[135,171],"semantically":[139],"related":[140],"many":[142],"candidate":[143],"correspondences.":[144],"Thus":[145],"P2RM":[147],"essentially":[150],"address":[151],"correspondence.":[154],"Besides,":[155],"design":[157],"novel":[159],"similarity":[161],"measurement":[162],"from":[164],"perspective":[166],"distance":[168],"embedding.":[172],"Under":[173],"evaluation":[175],"metric":[176],"matches,":[179],"extensive":[180],"experiments":[181],"and":[182,193],"ablation":[183],"studies":[184],"on":[185],"two":[186],"commonly":[187],"used":[188],"benchmarks":[189],"demonstrate":[190],"effectiveness":[192],"superiority":[194],"tackling":[196],"multiplicity":[198]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}