{"id":"https://openalex.org/W4285169708","doi":"https://doi.org/10.1109/tmm.2022.3177308","title":"Bidirectional Maximum Entropy Training With Word Co-Occurrence for Video Captioning","display_name":"Bidirectional Maximum Entropy Training With Word Co-Occurrence for Video Captioning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285169708","doi":"https://doi.org/10.1109/tmm.2022.3177308"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3177308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3177308","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5100319993","display_name":"Sheng Liu","orcid":"https://orcid.org/0000-0001-9608-0524"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9608-0524","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012121355","display_name":"Annan Li","orcid":"https://orcid.org/0000-0003-3497-5052"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Annan Li","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiahao Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8001-2703","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398976","display_name":"Yunhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6657-6403","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100319993"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.9184,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75011875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"25","issue":null,"first_page":"4494","last_page":"4507"},"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":0.9973999857902527,"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":0.9965999722480774,"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/closed-captioning","display_name":"Closed captioning","score":0.9769247770309448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8879961967468262},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6283988952636719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5582395195960999},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5398281216621399},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5388460159301758},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5347973704338074},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5279613733291626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49622780084609985},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45843371748924255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35581403970718384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19116130471229553}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9769247770309448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8879961967468262},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6283988952636719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5582395195960999},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5398281216621399},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5388460159301758},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5347973704338074},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5279613733291626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49622780084609985},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45843371748924255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35581403970718384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19116130471229553},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3177308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3177308","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":106,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W798224317","https://openalex.org/W1889081078","https://openalex.org/W1923211482","https://openalex.org/W1956340063","https://openalex.org/W1965555277","https://openalex.org/W2016589492","https://openalex.org/W2018490621","https://openalex.org/W2022523273","https://openalex.org/W2047666344","https://openalex.org/W2064675550","https://openalex.org/W2096175520","https://openalex.org/W2101105183","https://openalex.org/W2105482032","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2158548602","https://openalex.org/W2164290393","https://openalex.org/W2164948578","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2554906389","https://openalex.org/W2557264465","https://openalex.org/W2621571501","https://openalex.org/W2739107216","https://openalex.org/W2740388348","https://openalex.org/W2781726626","https://openalex.org/W2788527657","https://openalex.org/W2896457183","https://openalex.org/W2904246096","https://openalex.org/W2905145027","https://openalex.org/W2906314281","https://openalex.org/W2913822893","https://openalex.org/W2948358897","https://openalex.org/W2949376505","https://openalex.org/W2953461088","https://openalex.org/W2962681491","https://openalex.org/W2962918138","https://openalex.org/W2962934715","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963206148","https://openalex.org/W2963552819","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2982151481","https://openalex.org/W3006871679","https://openalex.org/W3009192917","https://openalex.org/W3009270862","https://openalex.org/W3009960797","https://openalex.org/W3014367186","https://openalex.org/W3018388102","https://openalex.org/W3019301826","https://openalex.org/W3034339250","https://openalex.org/W3034464851","https://openalex.org/W3035284526","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3036900224","https://openalex.org/W3039060838","https://openalex.org/W3045147787","https://openalex.org/W3049493117","https://openalex.org/W3092992946","https://openalex.org/W3098682680","https://openalex.org/W3099884890","https://openalex.org/W3100054454","https://openalex.org/W3103022576","https://openalex.org/W3109813419","https://openalex.org/W3111278072","https://openalex.org/W3134875898","https://openalex.org/W3135254306","https://openalex.org/W3136792391","https://openalex.org/W3166366124","https://openalex.org/W3170494780","https://openalex.org/W3174441232","https://openalex.org/W3176425931","https://openalex.org/W3176689360","https://openalex.org/W3177244742","https://openalex.org/W3211316995","https://openalex.org/W3214007456","https://openalex.org/W3217599442","https://openalex.org/W4289703391","https://openalex.org/W4304892053","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6639432524","https://openalex.org/W6674650171","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6683443546","https://openalex.org/W6684090549","https://openalex.org/W6685322675","https://openalex.org/W6739901393","https://openalex.org/W6747473740","https://openalex.org/W6757592117","https://openalex.org/W6776172991","https://openalex.org/W6804511247","https://openalex.org/W6921652704"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2803345361","https://openalex.org/W3009270862","https://openalex.org/W2047632477","https://openalex.org/W2158873310","https://openalex.org/W3041490575","https://openalex.org/W2049117375","https://openalex.org/W2970690932","https://openalex.org/W4321135767"],"abstract_inverted_index":{"Video":[0],"captioning":[1,21,79,153],"aims":[2],"to":[3,82,113,172],"generate":[4,83],"natural":[5],"language":[6,45],"descriptions":[7],"for":[8,115],"a":[9,14,25,50,84,107,156],"given":[10],"video,":[11],"which":[12,97],"is":[13,33],"more":[15,26,85,116],"challenging":[16],"task":[17],"than":[18],"static":[19],"image":[20],"since":[22],"it":[23,32],"requires":[24],"diverse":[27,86],"and":[28,174,183],"exhaustive":[29],"result.":[30],"Meanwhile,":[31],"also":[34],"important":[35],"that":[36,167],"the":[37,44,74,91,100,120,129,143,178],"generated":[38],"captions":[39,118],"should":[40],"be":[41,149],"consistent":[42],"with":[43,62,139],"habits":[46],"of":[47,77,103],"people":[48],"at":[49],"fine":[51],"granularity.":[52],"In":[53],"this":[54],"work,":[55],"unlike":[56],"most":[57],"recent":[58],"works":[59],"enhancing":[60],"performance":[61],"additional":[63],"data":[64],"modalities":[65],"or":[66],"complex":[67],"model":[68],"designs,":[69],"we":[70,89,127],"focus":[71],"on":[72,151,181],"optimizing":[73],"training":[75,144],"process":[76],"video":[78,87],"models.":[80],"Firstly,":[81],"caption,":[88],"propose":[90],"bidirectional":[92],"maximum":[93],"entropy":[94],"(BME)":[95],"training,":[96],"directly":[98],"optimizes":[99],"probability":[101],"distribution":[102],"neighboring":[104],"words":[105],"under":[106],"reinforcement":[108],"learning":[109],"(RL)":[110],"framework.":[111],"Secondly,":[112],"search":[114,122],"human-like":[117],"in":[119,142,155],"larger":[121],"space":[123],"created":[124],"by":[125],"BME,":[126],"introduce":[128],"word":[130],"co-occurrence":[131,140],"(WCO)":[132],"weighting.":[133],"It":[134],"adaptively":[135],"guides":[136],"RL":[137],"algorithms":[138],"statistics":[141],"corpus.":[145],"Our":[146],"method":[147,169],"can":[148],"deployed":[150],"existing":[152],"models":[154],"plug-and-play":[157],"manner":[158],"without":[159],"introducing":[160],"any":[161],"extra":[162],"parameters.":[163],"Experimental":[164],"results":[165],"show":[166],"our":[168],"yields":[170],"up":[171],"5.8%":[173],"7.0%":[175],"improvements":[176],"considering":[177],"CIDEr":[179],"score":[180],"MSVD":[182],"MSR-VTT,":[184],"respectively.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}