{"id":"https://openalex.org/W3049493117","doi":"https://doi.org/10.1145/3394171.3413880","title":"Poet: Product-oriented Video Captioner for E-commerce","display_name":"Poet: Product-oriented Video Captioner for E-commerce","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3049493117","doi":"https://doi.org/10.1145/3394171.3413880","mag":"3049493117"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413880","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.06880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shengyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqi Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Tan","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yu","raw_affiliation_strings":["Alibaba Group, Bei Jing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Bei Jing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Kuang","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingren Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongxia Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia Yang","raw_affiliation_strings":["Alibaba Group, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5376,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88682559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1292","last_page":"1301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9799000024795532,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9648000001907349,"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":0.9563000202178955},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6516000032424927},{"id":"https://openalex.org/keywords/video-production","display_name":"Video production","score":0.5005999803543091},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4876999855041504},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.43209999799728394},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4203999936580658},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9563000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065000176429749},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4876999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4507000148296356},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.40369999408721924},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2612999975681305},{"id":"https://openalex.org/C3018537244","wikidata":"https://www.wikidata.org/wiki/Q242256","display_name":"Video monitoring","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413880","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413880","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"},{"id":"pmh:oai:arXiv.org:2008.06880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06880","pdf_url":"https://arxiv.org/pdf/2008.06880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.06880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.06880","pdf_url":"https://arxiv.org/pdf/2008.06880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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/G4865411318","display_name":null,"funder_award_id":"61625107, 61751209, 61836002","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G6473908178","display_name":null,"funder_award_id":"2020QNA5024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8365256475","display_name":null,"funder_award_id":"LR19F020006","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1596841185","https://openalex.org/W1956340063","https://openalex.org/W2078238240","https://openalex.org/W2139501017","https://openalex.org/W2581637843","https://openalex.org/W2751304263","https://openalex.org/W2765621372","https://openalex.org/W2766159440","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2806331055","https://openalex.org/W2895845501","https://openalex.org/W2896878184","https://openalex.org/W2897464551","https://openalex.org/W2897550429","https://openalex.org/W2904378456","https://openalex.org/W2928773704","https://openalex.org/W2962944176","https://openalex.org/W2963410018","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W2981385984","https://openalex.org/W2981411942","https://openalex.org/W2981575209","https://openalex.org/W2981750519","https://openalex.org/W2982255917","https://openalex.org/W2986407524"],"related_works":[],"abstract_inverted_index":{"In":[0],"e-commerce,":[1],"a":[2,47,62],"growing":[3],"number":[4],"of":[5,84,101],"user-generated":[6],"videos":[7,74],"are":[8,49,145],"used":[9],"for":[10,30,52,96],"product":[11,22,138],"promotion.":[12],"How":[13],"to":[14,174],"generate":[15],"video":[16,27,34,54,64,150,155,161,180,184],"descriptions":[17],"that":[18,126],"narrate":[19],"the":[20,26,73,82,85,98,113,171],"user-preferred":[21],"characteristics":[23],"depicted":[24],"in":[25,46,109],"is":[28],"vital":[29],"successful":[31],"promoting.":[32],"Traditional":[33],"captioning":[35,151,181],"methods,":[36],"which":[37],"focus":[38],"on":[39,81,93,147,178],"routinely":[40],"describing":[41],"what":[42],"exists":[43],"and":[44,120,141,158,182],"happens":[45],"video,":[48],"not":[50],"amenable":[51],"product-oriented":[53,63,76,149],"captioning.":[55],"To":[56],"address":[57],"this":[58],"problem,":[59],"we":[60,88],"propose":[61],"captioner":[65],"framework,":[66],"abbreviated":[67],"as":[68,75],"Poet.":[69],"Poet":[70,110,127],"firstly":[71],"represents":[72],"spatial-temporal":[77,91],"graphs.":[78],"Then,":[79],"based":[80],"aspects":[83,139],"video-associated":[86],"product,":[87],"perform":[89],"knowledge-enhanced":[90],"inference":[92],"those":[94],"graphs":[95],"capturing":[97],"dynamic":[99,121],"change":[100],"fine-grained":[102],"product-part":[103],"characteristics.":[104],"The":[105],"knowledge":[106,118],"leveraging":[107],"module":[108],"differs":[111],"from":[112,165],"traditional":[114],"design":[115],"by":[116],"performing":[117],"filtering":[119],"memory":[122],"modeling.":[123],"We":[124,168],"show":[125],"achieves":[128],"consistent":[129],"performance":[130],"improvement":[131],"over":[132],"previous":[133],"methods":[134],"concerning":[135],"generation":[136],"quality,":[137],"capturing,":[140],"lexical":[142],"diversity.":[143],"Experiments":[144],"performed":[146],"two":[148],"datasets,":[152],"buyer-generated":[153],"fashion":[154,160],"dataset":[156,162],"(BFVD)":[157],"fan-generated":[159],"(FFVD),":[163],"collected":[164],"Mobile":[166],"Taobao.":[167],"will":[169],"release":[170],"desensitized":[172],"datasets":[173],"promote":[175],"further":[176],"investigations":[177],"both":[179],"general":[183],"analysis":[185],"problems.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-08-21T00:00:00"}
