{"id":"https://openalex.org/W3206433232","doi":"https://doi.org/10.1145/3474085.3479217","title":"Multi-Level Visual Representation with Semantic-Reinforced Learning for Video Captioning","display_name":"Multi-Level Visual Representation with Semantic-Reinforced Learning for Video Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206433232","doi":"https://doi.org/10.1145/3474085.3479217","mag":"3206433232"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3479217","doi":"https://doi.org/10.1145/3474085.3479217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479217","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"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/A5003552265","display_name":"Chengbo Dong","orcid":"https://orcid.org/0000-0001-8062-8209","observed_orcids":["https://orcid.org/0000-0001-8062-8209"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengbo Dong","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579735","display_name":"Xinru Chen","orcid":"https://orcid.org/0009-0004-6582-7559","observed_orcids":["https://orcid.org/0009-0004-6582-7559"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinru Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006279575","display_name":"Aozhu Chen","orcid":"https://orcid.org/0000-0002-7771-2300","observed_orcids":["https://orcid.org/0000-0002-7771-2300"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aozhu Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031338143","display_name":"Fan Hu","orcid":"https://orcid.org/0000-0002-5371-7780","observed_orcids":["https://orcid.org/0000-0002-5371-7780"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Hu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380111","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0003-4018-1603","observed_orcids":["https://orcid.org/0000-0003-4018-1603"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310","observed_orcids":["https://orcid.org/0000-0002-0220-8310"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.4906,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73359202,"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":"4750","last_page":"4754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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/video-captioning","display_name":"video captioning","score":1.0},{"id":"https://openalex.org/keywords/multi-head-self-attention","display_name":"multi-head self-attention","score":0.9269999861717224},{"id":"https://openalex.org/keywords/object-level-features","display_name":"object-level features","score":0.9620000123977661},{"id":"https://openalex.org/keywords/cross-modal-matching","display_name":"cross-modal matching","score":0.9900000095367432}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.965236485004425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585212230682373},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6006569266319275},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5537013411521912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510431528091431},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5254485011100769},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5124983787536621},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47297683358192444},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4607774615287781},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45647555589675903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4132902920246124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3639276623725891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3338448405265808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1384870409965515},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3479217","doi":"https://doi.org/10.1145/3474085.3479217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479217","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8289562263","display_name":null,"funder_award_id":"4202033","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W2101105183","https://openalex.org/W2470139095","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2560313346","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2799269579","https://openalex.org/W2942642798","https://openalex.org/W2963101956","https://openalex.org/W2963753226","https://openalex.org/W2970641574","https://openalex.org/W2987391422","https://openalex.org/W2989322838","https://openalex.org/W3015538334","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3107973541","https://openalex.org/W3126721948","https://openalex.org/W3175095612"],"related_works":["https://openalex.org/W4391647933","https://openalex.org/W4220848440","https://openalex.org/W2950579554","https://openalex.org/W2963552819","https://openalex.org/W4327950607","https://openalex.org/W2790776232","https://openalex.org/W4281251030","https://openalex.org/W2507365558","https://openalex.org/W2963177403","https://openalex.org/W4387934928"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,81],"bronze-medal":[4],"solution":[5],"for":[6,15],"the":[7,12,22,70,92,120,128,132,135],"video":[8,30,43,111],"captioning":[9],"task":[10],"of":[11,134],"ACMMM2021":[13],"Pre-Training":[14],"Video":[16],"Understanding":[17],"Challenge.":[18],"We":[19],"depart":[20],"from":[21,95],"Bottom-Up-Top-Down":[23],"model,":[24],"with":[25],"technical":[26],"improvements":[27],"on":[28,119],"both":[29],"content":[31],"encoding":[32],"and":[33,49,56,76,112,124],"caption":[34,94,103],"decoding.":[35],"For":[36],"encoding,":[37],"we":[38,79,101],"propose":[39],"to":[40,90],"extract":[41],"multi-level":[42],"features":[44,58],"that":[45],"describe":[46],"holistic":[47],"scenes":[48],"fine-grained":[50],"key":[51],"objects,":[52],"respectively.":[53],"The":[54],"scene-level":[55],"object-level":[57],"are":[59],"enhanced":[60],"separately":[61],"by":[62,84,98,105,127],"multi-head":[63],"self-attention":[64],"mechanisms":[65],"before":[66],"feeding":[67],"them":[68],"into":[69],"decoding":[71],"module.":[72],"Towards":[73],"generating":[74],"content-relevant":[75],"human-like":[77],"captions,":[78],"train":[80],"network":[82],"end-to-end":[83],"semantic-reinforced":[85],"learning.":[86],"Finally,":[87],"in":[88],"order":[89],"select":[91],"best":[93],"captions":[96],"produced":[97],"distinct":[99],"models,":[100],"perform":[102],"reranking":[104],"cross-modal":[106],"matching":[107],"between":[108],"a":[109],"given":[110],"each":[113],"candidate":[114],"caption.":[115],"Both":[116],"internal":[117],"experiments":[118],"MSR-VTT":[121],"test":[122],"set":[123],"external":[125],"evaluations":[126],"challenge":[129],"organizers":[130],"justify":[131],"viability":[133],"proposed":[136],"solution.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-25T00:00:00"}