{"id":"https://openalex.org/W4283390709","doi":"https://doi.org/10.1145/3512527.3531374","title":"Cross-Modal Retrieval between Event-Dense Text and Image","display_name":"Cross-Modal Retrieval between Event-Dense Text and Image","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283390709","doi":"https://doi.org/10.1145/3512527.3531374"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5102947045","display_name":"Zhongwei Xie","orcid":"https://orcid.org/0000-0001-6346-0707"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongwei Xie","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037897744","display_name":"Luo Zhong","orcid":"https://orcid.org/0000-0002-2346-9659"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Zhong","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079797505","display_name":"Jianquan Liu","orcid":"https://orcid.org/0000-0003-4303-9020"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianquan Liu","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343991","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0002-4138-3082"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102947045"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.604,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6638029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9970999956130981,"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/embedding","display_name":"Embedding","score":0.7569063305854797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300059199333191},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6874525547027588},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6123071908950806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5951279401779175},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5430769920349121},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5407047867774963},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4315921664237976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4255630373954773},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4008982181549072},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3979952931404114},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35571786761283875}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7569063305854797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300059199333191},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6874525547027588},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6123071908950806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5951279401779175},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5430769920349121},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5407047867774963},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4315921664237976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4255630373954773},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4008982181549072},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3979952931404114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35571786761283875},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1773149199","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2049705550","https://openalex.org/W2092361219","https://openalex.org/W2106277773","https://openalex.org/W2137918516","https://openalex.org/W2194775991","https://openalex.org/W2264685884","https://openalex.org/W2549139847","https://openalex.org/W2565041183","https://openalex.org/W2737041163","https://openalex.org/W2747329762","https://openalex.org/W2765440071","https://openalex.org/W2892164947","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2963055199","https://openalex.org/W2963997278","https://openalex.org/W2987222078","https://openalex.org/W3033103428","https://openalex.org/W3034303366","https://openalex.org/W3035032757","https://openalex.org/W3043990051","https://openalex.org/W3164325351","https://openalex.org/W3190517769","https://openalex.org/W3197950609","https://openalex.org/W3206660842","https://openalex.org/W3207562294","https://openalex.org/W3208696560","https://openalex.org/W4239167255"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,207],"novel":[4],"approach":[5,65,200,205],"to":[6,38,51,70,81,107],"the":[7,17,20,39,46,53,57,61,67,72,77,82,91,102,109,113,120,125,130,136,141,145,151,156,160,173,178,184,203],"problem":[8],"of":[9,22,41,56,93,112,144,154],"event-dense":[10,58,78],"text":[11,18,59,115,137,167],"and":[12,75,98,138,158,169],"image":[13,126,139,147,170],"cross-modal":[14,73,162,189],"retrieval":[15,34,80,215],"where":[16],"contains":[19],"descriptions":[21],"numerous":[23],"events.":[24,121],"It":[25],"is":[26,31,49],"known":[27],"that":[28,117,194],"modality":[29,198],"alignment":[30,55,199],"crucial":[32],"for":[33,85,188,213],"performance.":[35],"However,":[36],"due":[37],"lack":[40],"event":[42,95,105,131,179],"sequence":[43],"information":[44],"in":[45],"image,":[47],"it":[48,100],"challenging":[50],"perform":[52],"fine-grain":[54],"with":[60,101,140,172,177,206],"image.":[62],"Our":[63],"proposed":[64,196],"incorporates":[66],"event-oriented":[68,197],"features":[69],"enhance":[71,108],"alignment,":[74],"applies":[76],"text-image":[79],"food":[83],"domain":[84],"empirical":[86],"validation.":[87],"Specifically,":[88],"we":[89,123,165],"capture":[90],"significance":[92],"each":[94],"by":[96,128,135,181],"Transformer,":[97],"combine":[99],"identified":[103],"key":[104],"elements,":[106],"discriminative":[110],"ability":[111],"learned":[114],"embedding":[116,127,143,168,171,186],"summarizes":[118],"all":[119,155],"Next,":[122],"produce":[124],"combining":[129],"tag":[132,180],"jointly":[133],"shared":[134],"visual":[142],"event-related":[146],"regions,":[148],"which":[149],"describes":[150],"eventual":[152],"consequence":[153],"events":[157],"facilitates":[159],"event-based":[161],"alignment.":[163],"Finally,":[164],"integrate":[166],"loss":[174],"optimization":[175],"empowered":[176],"iteratively":[182],"regulating":[183],"joint":[185],"learning":[187],"retrieval.":[190],"Extensive":[191],"experiments":[192],"demonstrate":[193],"our":[195],"significantly":[201],"outperforms":[202],"state-of-the-art":[204],"23.3%":[208],"improvement":[209],"on":[210,216],"top-1":[211],"Recall":[212],"image-to-recipe":[214],"Recipe1M":[217],"10k":[218],"test":[219],"set.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}