{"id":"https://openalex.org/W4367060669","doi":"https://doi.org/10.1145/3539618.3591712","title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","display_name":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4367060669","doi":"https://doi.org/10.1145/3539618.3591712"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.12570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010816782","display_name":"Leigang Qu","orcid":"https://orcid.org/0009-0004-6555-3834"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Leigang Qu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-6555-3834","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5764","affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5199-1428","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034162160","display_name":"Zhedong Zheng","orcid":"https://orcid.org/0000-0002-2434-9050"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhedong Zheng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2434-9050","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1252","last_page":"1261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.7721617221832275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5648205876350403},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5643988251686096},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5344820022583008},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4822419583797455},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4713396728038788},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4712315797805786},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43402013182640076},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4314419627189636},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43096524477005005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38715189695358276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37264567613601685},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33601248264312744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3315725326538086},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.258454293012619},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1324470043182373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721617221832275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648205876350403},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5643988251686096},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5344820022583008},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4822419583797455},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4713396728038788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4712315797805786},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43402013182640076},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4314419627189636},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43096524477005005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38715189695358276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37264567613601685},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33601248264312744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3315725326538086},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.258454293012619},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1324470043182373},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3539618.3591712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.12570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12570","pdf_url":"https://arxiv.org/pdf/2304.12570","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/245935","is_oa":false,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/245935","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Elements","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.12570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12570","pdf_url":"https://arxiv.org/pdf/2304.12570","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7696304900","display_name":null,"funder_award_id":"62006142","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"},{"id":"https://openalex.org/F4320324777","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37"},{"id":"https://openalex.org/F4320335334","display_name":"Defence Science and Technology Group","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367060669.pdf","grobid_xml":"https://content.openalex.org/works/W4367060669.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1979931042","https://openalex.org/W2076188996","https://openalex.org/W2100398441","https://openalex.org/W2118286847","https://openalex.org/W2123024445","https://openalex.org/W2138621090","https://openalex.org/W2148809531","https://openalex.org/W2185175083","https://openalex.org/W2242818826","https://openalex.org/W2544587078","https://openalex.org/W2559091987","https://openalex.org/W2584637367","https://openalex.org/W2745461083","https://openalex.org/W2774267535","https://openalex.org/W2798354744","https://openalex.org/W2798397499","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2897078023","https://openalex.org/W2954626788","https://openalex.org/W2955732934","https://openalex.org/W2962964995","https://openalex.org/W2963055199","https://openalex.org/W2963588253","https://openalex.org/W2970885858","https://openalex.org/W2981448908","https://openalex.org/W2988823324","https://openalex.org/W2990519439","https://openalex.org/W2996078716","https://openalex.org/W3029678209","https://openalex.org/W3035183674","https://openalex.org/W3035454331","https://openalex.org/W3035588244","https://openalex.org/W3035590471","https://openalex.org/W3035605030","https://openalex.org/W3042994108","https://openalex.org/W3092820619","https://openalex.org/W3099206234","https://openalex.org/W3105817677","https://openalex.org/W3106498098","https://openalex.org/W3111331302","https://openalex.org/W3118694826","https://openalex.org/W3154902219","https://openalex.org/W3155114168","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W3212922056","https://openalex.org/W4224903584","https://openalex.org/W4284672647","https://openalex.org/W4287394079","https://openalex.org/W4287720131","https://openalex.org/W4299131346","https://openalex.org/W4300466008","https://openalex.org/W4312099781","https://openalex.org/W4312926916"],"related_works":["https://openalex.org/W2011472225","https://openalex.org/W3000057026","https://openalex.org/W3048565508","https://openalex.org/W3163984363","https://openalex.org/W3127142483","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W4390446658","https://openalex.org/W4378713479"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,60],"aims":[2],"to":[3,66,72,151,172],"bridge":[4],"the":[5,21,33,52,80,116,122,154,158,178,201],"modality":[6],"gap":[7],"and":[8,89,91,105,110,121,156,176,198,205],"retrieve":[9],"cross-modal":[10],"content":[11],"based":[12],"on":[13,20,192],"semantic":[14],"similarities.":[15],"Prior":[16],"work":[17],"usually":[18],"focuses":[19],"pairwise":[22],"relations":[23,36,57,118,155],"(i.e.,":[24,37],"whether":[25],"a":[26,38,46,93,133,146,163,168],"data":[27,43,113],"sample":[28,128],"matches":[29],"another)":[30],"but":[31],"ignores":[32],"higher-order":[34],"neighbor":[35,56,117],"matching":[39],"structure":[40,169],"among":[41],"multiple":[42],"samples).":[44],"Re-ranking,":[45],"popular":[47],"post-processing":[48],"practice,":[49],"has":[50],"revealed":[51],"superiority":[53],"of":[54,183,207],"capturing":[55],"in":[58],"single-modality":[59],"tasks.":[61],"However,":[62],"it":[63],"is":[64],"ineffective":[65],"directly":[67],"extend":[68],"existing":[69],"re-ranking":[70,97,210],"algorithms":[71],"image-text":[73],"retrieval.":[74],"In":[75,124],"this":[76,125],"paper,":[77],"we":[78,100,144,187],"analyze":[79],"reason":[81],"from":[82],"four":[83],"perspectives,":[84],"i.e.,":[85,196],"generalization,":[86,204],"flexibility,":[87],"sparsity,":[88],"asymmetry,":[90],"propose":[92],"novel":[94],"learnable":[95],"pillar-based":[96],"paradigm.":[98,211],"Concretely,":[99],"first":[101],"select":[102],"top-ranked":[103],"intra-":[104],"intermodal":[106],"neighbors":[107],"as":[108],"pillars,":[109],"then":[111],"reconstruct":[112],"samples":[114],"with":[115],"between":[119],"them":[120],"pillars.":[123],"way,":[126],"each":[127],"can":[129],"be":[130],"mapped":[131],"into":[132],"multimodal":[134],"pillar":[135],"space":[136],"only":[137],"using":[138],"similarities,":[139],"ensuring":[140],"generalization.":[141],"After":[142],"that,":[143],"design":[145],"neighbor-aware":[147],"graph":[148],"reasoning":[149],"module":[150],"flexibly":[152],"exploit":[153],"excavate":[157],"sparse":[159],"positive":[160],"items":[161],"within":[162],"neighborhood.":[164],"We":[165],"also":[166],"present":[167],"alignment":[170],"constraint":[171],"promote":[173],"crossmodal":[174],"collaboration":[175],"align":[177],"asymmetric":[179],"modalities.":[180],"On":[181],"top":[182],"various":[184],"base":[185],"backbones,":[186],"carry":[188],"out":[189],"extensive":[190],"experiments":[191],"two":[193],"benchmark":[194],"datasets,":[195],"Flickr30K":[197],"MS-COCO,":[199],"demonstrating":[200],"effectiveness,":[202],"superiority,":[203],"transferability":[206],"our":[208],"proposed":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}