{"id":"https://openalex.org/W4304092645","doi":"https://doi.org/10.1145/3503161.3548180","title":"Search-oriented Micro-video Captioning","display_name":"Search-oriented Micro-video Captioning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092645","doi":"https://doi.org/10.1145/3503161.3548180"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548180","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":"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/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":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","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":null,"display_name":"Dai Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai Meng","raw_affiliation_strings":["Kuaishou, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","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 &amp; AI, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud &amp; AI, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081506611","display_name":"Alberto Del Bimbo","orcid":"https://orcid.org/0000-0002-1052-8322"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Del Bimbo","raw_affiliation_strings":["University of Florence, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3234","last_page":"3243"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9980999827384949,"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":0.9968000054359436,"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/closed-captioning","display_name":"Closed captioning","score":0.972170352935791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8550981283187866},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6049677133560181},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5409106016159058},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5182092785835266},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4861259460449219},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44597697257995605},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4181438982486725},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.41678690910339355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41357243061065674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35190463066101074},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2327823042869568}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.972170352935791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550981283187866},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6049677133560181},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5409106016159058},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5182092785835266},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4861259460449219},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44597697257995605},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4181438982486725},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.41678690910339355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41357243061065674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35190463066101074},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2327823042869568},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548180","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1861492603","https://openalex.org/W2049892260","https://openalex.org/W2110933980","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2527457059","https://openalex.org/W2604178507","https://openalex.org/W2788277448","https://openalex.org/W2897628926","https://openalex.org/W2962717182","https://openalex.org/W2962968835","https://openalex.org/W2963351113","https://openalex.org/W2964241990","https://openalex.org/W2981851019","https://openalex.org/W2982553922","https://openalex.org/W2988793532","https://openalex.org/W3034999214","https://openalex.org/W3035237998","https://openalex.org/W3035265375","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3039060838","https://openalex.org/W3105232955"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Pioneer":[0],"efforts":[1],"have":[2],"been":[3],"dedicated":[4],"to":[5,14,76,98],"the":[6,16,24,33,38,46,78,119,122],"content-oriented":[7],"video":[8,22,40,80],"captioning":[9,96],"that":[10,36],"generates":[11],"relevant":[12],"sentences":[13,44],"describe":[15],"visual":[17],"contents":[18],"of":[19],"a":[20,67,93,111,115],"given":[21,39],"from":[23,45,59,102],"producer":[25],"perspective.":[26],"By":[27],"contrast,":[28],"this":[29,63],"work":[30],"targets":[31],"at":[32],"search-oriented":[34],"one":[35],"summarizes":[37],"via":[41,110],"generating":[42],"query-like":[43],"consumer":[47],"angle.":[48],"Beyond":[49],"relevance,":[50],"diversity":[51],"is":[52,83,108],"vital":[53],"in":[54],"characterizing":[55],"consumers'":[56,103],"seeking":[57],"intention":[58],"different":[60,100],"aspects.":[61],"Towards":[62],"end,":[64],"we":[65,91],"devise":[66],"large-scale":[68],"multimodal":[69],"pre-training":[70],"network":[71],"regularized":[72],"by":[73],"five":[74],"tasks":[75],"strengthen":[77],"downstream":[79],"representation,":[81],"which":[82],"well-trained":[84],"over":[85,128],"our":[86,126,129],"collected":[87],"11M":[88],"micro-videos.":[89],"Thereafter,":[90],"present":[92],"flow-based":[94],"diverse":[95],"model":[97,107,127],"generate":[99],"captions":[101],"search":[104],"demand.":[105],"This":[106],"optimized":[109],"reconstruction":[112],"loss":[113],"and":[114,121,138],"KL":[116],"divergence":[117],"between":[118],"prior":[120],"posterior.":[123],"We":[124],"justify":[125],"constructed":[130],"golden":[131],"dataset":[132],"comprising":[133],"690k":[134],"<query,":[135],"micro-video>":[136],"pairs":[137],"experimental":[139],"results":[140],"demonstrate":[141],"its":[142],"superiority.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":19}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}