{"id":"https://openalex.org/W3155230099","doi":"https://doi.org/10.1145/3404835.3462829","title":"Dynamic Modality Interaction Modeling for Image-Text Retrieval","display_name":"Dynamic Modality Interaction Modeling for Image-Text Retrieval","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155230099","doi":"https://doi.org/10.1145/3404835.3462829","mag":"3155230099"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010816782","display_name":"Leigang Qu","orcid":"https://orcid.org/0009-0004-6555-3834"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leigang Qu","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"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":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654190","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048947531","display_name":"Zan Gao","orcid":"https://orcid.org/0000-0003-2182-5741"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zan Gao","raw_affiliation_strings":["Shandong Artificial Intelligence Institute, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Artificial Intelligence Institute, Jinan, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":179,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1104","last_page":"1113"},"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":0.9991000294685364,"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":0.862730860710144},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.692222535610199},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5403573513031006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5250625014305115},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4511338174343109},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.449384868144989},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.4461477994918823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38349226117134094},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3438805341720581}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.862730860710144},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.692222535610199},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5403573513031006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250625014305115},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4511338174343109},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.449384868144989},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.4461477994918823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38349226117134094},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3438805341720581},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3462829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2745461083","https://openalex.org/W2798354744","https://openalex.org/W2883311563","https://openalex.org/W2884751099","https://openalex.org/W2944668088","https://openalex.org/W2948958195","https://openalex.org/W2954672622","https://openalex.org/W2962944050","https://openalex.org/W2962964995","https://openalex.org/W2963055199","https://openalex.org/W2963136578","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2982108874","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W3010277541","https://openalex.org/W3029678209","https://openalex.org/W3035071066","https://openalex.org/W3035454331","https://openalex.org/W3035485997","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3101429639","https://openalex.org/W3157181916"],"related_works":["https://openalex.org/W2127180614","https://openalex.org/W4235531327","https://openalex.org/W2139908560","https://openalex.org/W2177095534","https://openalex.org/W1964344619","https://openalex.org/W1603115038","https://openalex.org/W2163233359","https://openalex.org/W4251026061","https://openalex.org/W4249446840","https://openalex.org/W4238466892"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1],"is":[2,82],"a":[3,70,118,123,138],"fundamental":[4],"and":[5,20,31,52,86,113,173],"crucial":[6],"branch":[7],"in":[8,17,117,141],"information":[9],"retrieval.":[10,93],"Although":[11],"much":[12],"progress":[13],"has":[14],"been":[15],"made":[16],"bridging":[18],"vision":[19],"language,":[21],"it":[22],"remains":[23],"challenging":[24],"because":[25],"of":[26,58,101,110,133,178],"the":[27,56,78,83,128,131,148,176],"difficult":[28],"intra-modal":[29],"reasoning":[30],"cross-modal":[32],"alignment.":[33],"Existing":[34],"modality":[35,72,111],"interaction":[36,59,73,89],"methods":[37],"have":[38],"achieved":[39],"impressive":[40],"results":[41],"on":[42,49,152,167],"public":[43],"datasets.":[44],"However,":[45],"they":[46],"heavily":[47],"rely":[48],"expert":[50],"experience":[51],"empirical":[53],"feedback":[54],"towards":[55,91],"design":[57,98],"patterns,":[60],"therefore,":[61],"lacking":[62],"flexibility.":[63],"To":[64,126],"address":[65],"these":[66],"issues,":[67],"we":[68,96,136],"develop":[69],"novel":[71],"modeling":[74],"network":[75],"based":[76],"upon":[77],"routing":[79,124],"mechanism,":[80],"which":[81],"first":[84,97],"unified":[85],"dynamic":[87,139],"multimodal":[88],"framework":[90],"image-text":[92],"In":[94],"particular,":[95],"four":[99],"types":[100],"cells":[102],"as":[103],"basic":[104],"units":[105],"to":[106,121],"explore":[107],"different":[108,159,163],"levels":[109],"interactions,":[112],"then":[114],"connect":[115],"them":[116],"dense":[119],"strategy":[120],"construct":[122],"space.":[125],"endow":[127],"model":[129,155,180],"with":[130,182],"capability":[132],"path":[134],"decision,":[135],"integrate":[137],"router":[140],"each":[142],"cell":[143],"for":[144,162],"pattern":[145],"exploration.":[146],"As":[147],"routers":[149],"are":[150],"conditioned":[151],"inputs,":[153],"our":[154,179],"can":[156],"dynamically":[157],"learn":[158],"activated":[160],"paths":[161],"data.":[164],"Extensive":[165],"experiments":[166],"two":[168],"benchmark":[169],"datasets,":[170],"i.e.,":[171],"Flickr30K":[172],"MS-COCO,":[174],"verify":[175],"superiority":[177],"compared":[181],"several":[183],"state-of-the-art":[184],"baselines.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":24}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}