{"id":"https://openalex.org/W3190457301","doi":"https://doi.org/10.24963/ijcai.2021/160","title":"Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching","display_name":"Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3190457301","doi":"https://doi.org/10.24963/ijcai.2021/160","mag":"3190457301"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/160","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/160","pdf_url":"https://www.ijcai.org/proceedings/2021/0160.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0160.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047021636","display_name":"Bofeng Wu","orcid":"https://orcid.org/0000-0002-4539-4854"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bofeng Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China","School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009352936","display_name":"Guocheng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocheng Niu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112673776","display_name":"Xinyan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Xiao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042342029","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-6478-9192"},"institutions":[{"id":"https://openalex.org/I105126617","display_name":"Zhejiang International Studies University","ror":"https://ror.org/01vwvvq12","country_code":"CN","type":"education","lineage":["https://openalex.org/I105126617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Zhejiang International Studies University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang International Studies University, Hangzhou, China","institution_ids":["https://openalex.org/I105126617"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047021636"],"corresponding_institution_ids":["https://openalex.org/I50760025","https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":0.2914,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5573503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1157","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10812","display_name":"Human Pose and Action Recognition","score":0.994700014591217,"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":0.9775999784469604,"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":0.8492743372917175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332510590553284},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6733825206756592},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.663325309753418},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.649877667427063},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6463375091552734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922954082489014},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5733534693717957},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5434655547142029},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4823957681655884},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4745272696018219},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.46109285950660706},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45915356278419495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3440014719963074},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3284684419631958},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21600523591041565}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8492743372917175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332510590553284},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6733825206756592},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.663325309753418},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.649877667427063},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6463375091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922954082489014},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5733534693717957},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5434655547142029},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4823957681655884},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4745272696018219},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.46109285950660706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45915356278419495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3440014719963074},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3284684419631958},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21600523591041565},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/160","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/160","pdf_url":"https://www.ijcai.org/proceedings/2021/0160.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/160","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/160","pdf_url":"https://www.ijcai.org/proceedings/2021/0160.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G7528510259","display_name":null,"funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3190457301.pdf","grobid_xml":"https://content.openalex.org/works/W3190457301.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W2519328139","https://openalex.org/W2550143307","https://openalex.org/W2607119937","https://openalex.org/W2745461083","https://openalex.org/W2755876276","https://openalex.org/W2883910824","https://openalex.org/W2896457183","https://openalex.org/W2945634346","https://openalex.org/W2949789546","https://openalex.org/W2963351113","https://openalex.org/W2963916161","https://openalex.org/W2964216549","https://openalex.org/W2968104955","https://openalex.org/W2983918066","https://openalex.org/W3027790991","https://openalex.org/W3043840704","https://openalex.org/W3094751268"],"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":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"approach":[4],"to":[5,26,41,45,58,79,102,113],"Dense":[6],"Video":[7],"Captioning":[8],"(DVC)":[9],"without":[10],"pairwise":[11],"event-sentence":[12],"annotation.":[13],"First,":[14],"we":[15,32],"adopt":[16],"the":[17,50,60,66,81,90,108],"knowledge":[18],"distilled":[19],"from":[20],"relevant":[21],"and":[22,36,52,97,106],"well":[23],"solved":[24],"tasks":[25,44],"generate":[27],"high-quality":[28],"event":[29,94],"proposals.":[30],"Then":[31],"incorporate":[33],"contrastive":[34],"loss":[35,38],"cycle-consistency":[37],"typically":[39],"applied":[40],"cross-modal":[42,98],"retrieval":[43],"build":[46],"semantic":[47,100],"matching":[48,69,82,101],"between":[49],"proposals":[51],"sentences,":[53],"which":[54],"are":[55,71],"eventually":[56],"used":[57],"train":[59],"caption":[61],"generation":[62,96],"module.":[63],"In":[64],"addition,":[65],"parameters":[67],"of":[68,92,110],"module":[70],"initialized":[72],"via":[73],"pre-training":[74],"based":[75],"on":[76,86],"annotated":[77],"images":[78],"improve":[80],"performance.":[83],"Extensive":[84],"experiments":[85],"ActivityNet-Caption":[87],"dataset":[88],"reveal":[89],"significance":[91],"distillation-based":[93],"proposal":[95],"retrieval-based":[99],"weakly":[103],"supervised":[104],"DVC,":[105],"demonstrate":[107],"superiority":[109],"our":[111],"method":[112],"existing":[114],"state-of-the-art":[115],"methods.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}