{"id":"https://openalex.org/W3092820619","doi":"https://doi.org/10.1145/3394171.3413961","title":"Context-Aware Multi-View Summarization Network for Image-Text Matching","display_name":"Context-Aware Multi-View Summarization Network for Image-Text Matching","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092820619","doi":"https://doi.org/10.1145/3394171.3413961","mag":"3092820619"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5078164599","display_name":"Da Cao","orcid":"https://orcid.org/0000-0002-2611-2559"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Cao","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"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/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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-5165-4325"},"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":"Qi Tian","raw_affiliation_strings":["Huawei Cloud & AI, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud & AI, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":157,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1047","last_page":"1055"},"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":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8723284006118774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8710020184516907},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5449508428573608},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5186423659324646},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.487444669008255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48657453060150146},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4567505121231079},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45527997612953186},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4126068949699402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3647846281528473}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8723284006118774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710020184516907},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5449508428573608},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5186423659324646},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.487444669008255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48657453060150146},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4567505121231079},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45527997612953186},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4126068949699402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3647846281528473},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2077069816","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2346425926","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2602856279","https://openalex.org/W2745461083","https://openalex.org/W2765440071","https://openalex.org/W2894786240","https://openalex.org/W2897628926","https://openalex.org/W2956959730","https://openalex.org/W2962964995","https://openalex.org/W2962965405","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963748441","https://openalex.org/W2963882743","https://openalex.org/W2964067226","https://openalex.org/W2964727037","https://openalex.org/W2965848243","https://openalex.org/W2981586349","https://openalex.org/W2981951787","https://openalex.org/W2982078236","https://openalex.org/W2982108874","https://openalex.org/W2983141445","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2091301346","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4323520239"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,141],"is":[2,42],"a":[3,46,68,119,123,139],"vital":[4],"yet":[5],"challenging":[6],"task":[7],"in":[8],"the":[9,15,25,29,35,104,171],"field":[10],"of":[11,97,173],"multimedia":[12],"analysis.":[13],"Over":[14],"past":[16],"decades,":[17],"great":[18],"efforts":[19],"have":[20,157],"been":[21],"made":[22],"to":[23,52,56,74,94,111,126,143,178],"bridge":[24],"semantic":[26,61],"gap":[27],"between":[28],"visual":[30,77,98],"and":[31,37,100,167],"textual":[32,58],"modalities.":[33],"Despite":[34],"significance":[36],"value,":[38],"most":[39],"prior":[40],"work":[41],"still":[43],"confronted":[44],"with":[45,60,122,148],"multi-view":[47,71,140,145],"description":[48],"challenge,":[49],"i.e.,":[50,165],"how":[51],"align":[53],"an":[54,89],"image":[55,146],"multiple":[57,81],"descriptions":[59],"diversity.":[62],"Toward":[63],"this":[64],"end,":[65],"we":[66,87,108,117,137,156],"present":[67],"novel":[69],"context-aware":[70],"summarization":[72,120],"network":[73],"summarize":[75],"context-enhanced":[76],"region":[78],"information":[79,106],"from":[80,133],"views.":[82],"To":[83,152],"be":[84],"more":[85],"specific,":[86],"design":[88],"adaptive":[90],"gating":[91],"self-attention":[92],"module":[93,121],"extract":[95],"representations":[96],"regions":[99],"words.":[101],"By":[102],"controlling":[103],"internal":[105],"flow,":[107],"are":[109],"able":[110],"adaptively":[112],"capture":[113],"context":[114],"information.":[115],"Afterwards,":[116],"introduce":[118],"diversity":[124],"regularization":[125],"aggregate":[127],"region-level":[128],"features":[129,147],"into":[130],"image-level":[131],"ones":[132],"different":[134],"perspectives.":[135],"Ultimately,":[136],"devise":[138],"scheme":[142],"match":[144],"corresponding":[149],"text":[150],"ones.":[151],"justify":[153],"our":[154,174],"work,":[155],"conducted":[158],"extensive":[159],"experiments":[160],"on":[161],"two":[162],"benchmark":[163],"datasets,":[164],"Flickr30K":[166],"MS-COCO,":[168],"which":[169],"demonstrates":[170],"superiority":[172],"model":[175],"as":[176],"compared":[177],"several":[179],"state-of-the-art":[180],"baselines.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":14}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}