{"id":"https://openalex.org/W2982255917","doi":"https://doi.org/10.1145/3343031.3351037","title":"Critic-based Attention Network for Event-based Video Captioning","display_name":"Critic-based Attention Network for Event-based Video Captioning","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982255917","doi":"https://doi.org/10.1145/3343031.3351037","mag":"2982255917"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5109431406","display_name":"Elaheh Barati","orcid":null},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elaheh Barati","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100736156","display_name":"Xuewen Chen","orcid":"https://orcid.org/0000-0002-2794-3987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuewen Chen","raw_affiliation_strings":["AIWAYS AUTO, shanghai, China"],"affiliations":[{"raw_affiliation_string":"AIWAYS AUTO, shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109431406"],"corresponding_institution_ids":["https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":0.6073,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72853606,"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":"811","last_page":"817"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994000196456909,"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":0.9965999722480774,"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":0.9882304668426514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8552133440971375},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7525855302810669},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7076829075813293},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5134319067001343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49499672651290894},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4145379662513733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3846963346004486},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3842388391494751},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20447590947151184}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9882304668426514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552133440971375},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7525855302810669},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7076829075813293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5134319067001343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49499672651290894},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4145379662513733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3846963346004486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3842388391494751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20447590947151184},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2112429522","https://openalex.org/W2119717200","https://openalex.org/W2123301721","https://openalex.org/W2128554449","https://openalex.org/W2139501017","https://openalex.org/W2600463316","https://openalex.org/W2607151106","https://openalex.org/W2949376505","https://openalex.org/W2953213543","https://openalex.org/W2962937869","https://openalex.org/W2963014351","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963552819","https://openalex.org/W2963576560","https://openalex.org/W2963613897","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2964241990","https://openalex.org/W3103022576"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4385572368"],"abstract_inverted_index":{"In":[0,14],"this":[1,15],"paper,":[2],"we":[3],"investigate":[4],"utilizing":[5,132],"an":[6,10,44,105],"actor-critic":[7],"architecture":[8,38],"for":[9,99,110],"event-based":[11,139],"video":[12,19,56,140,156],"captioning.":[13],"captioning":[16,118,141,157],"task,":[17],"the":[18,27,30,49,63,66,75,80,88,111,123,136],"can":[20],"contain":[21],"multiple":[22],"overlapping":[23],"events.":[24],"We":[25,90,103,125],"consider":[26],"words":[28],"as":[29],"actions":[31],"that":[32,151],"our":[33,40,133,152],"model":[34,41],"takes":[35],"sequentially.":[36],"The":[37],"of":[39,43,65,113,129,138],"consists":[42],"actor":[45],"network":[46,60,94],"to":[47,61,95,108],"predict":[48],"captions":[50],"given":[51],"temporal":[52,85,101,120],"segments":[53,86],"in":[54,74,87,117,122,135],"a":[55,58,92,97,119,127],"and":[57,145],"critic":[59],"measure":[62],"quality":[64],"generated":[67],"captions.":[68],"Our":[69],"model,":[70],"first,":[71],"localizes":[72],"events":[73],"video,":[76],"then":[77],"by":[78],"using":[79],"localized":[81,115],"events,":[82],"it":[83],"locates":[84],"video.":[89,124],"adopt":[91],"global":[93],"generate":[96],"caption":[98],"each":[100,114],"segment.":[102],"propose":[104],"attention":[106],"mechanism":[107],"account":[109],"importance":[112],"event":[116],"segment":[121],"provide":[126],"set":[128],"experiments":[130],"on":[131,142],"method":[134,153],"task":[137],"ActivityNet":[143],"Captions":[144],"TACoS-MultiLevel":[146],"datasets.":[147],"Experimental":[148],"results":[149],"show":[150],"outperforms":[154],"state-of-the-art":[155],"methods.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}