{"id":"https://openalex.org/W2972589507","doi":"https://doi.org/10.1109/icarm.2019.8834066","title":"Attention-based Visual-Audio Fusion for Video Caption Generation","display_name":"Attention-based Visual-Audio Fusion for Video Caption Generation","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2972589507","doi":"https://doi.org/10.1109/icarm.2019.8834066","mag":"2972589507"},"language":"en","primary_location":{"id":"doi:10.1109/icarm.2019.8834066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm.2019.8834066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"},"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/A5076870101","display_name":"Ningning Guo","orcid":"https://orcid.org/0009-0007-1970-5819"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningning Guo","raw_affiliation_strings":["Department of Computer Technology, University of Shanghai for Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Technology, University of Shanghai for Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102002511","display_name":"Linhua Jiang","orcid":"https://orcid.org/0000-0002-7990-0444"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhua Jiang","raw_affiliation_strings":["Department of Computer Technology, University of Shanghai for Science and Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Technology, University of Shanghai for Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I148128674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7188490629196167},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5849962830543518},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5074254870414734},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49510541558265686},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.45202940702438354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41898036003112793},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35308220982551575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188490629196167},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5849962830543518},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5074254870414734},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49510541558265686},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.45202940702438354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41898036003112793},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35308220982551575},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm.2019.8834066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm.2019.8834066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 4th International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1492731187","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1689977300","https://openalex.org/W1895577753","https://openalex.org/W1969616664","https://openalex.org/W1972040795","https://openalex.org/W1983364832","https://openalex.org/W2062118960","https://openalex.org/W2070150502","https://openalex.org/W2140428678","https://openalex.org/W2157331557","https://openalex.org/W2176091656","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2527349934","https://openalex.org/W2584992898","https://openalex.org/W2745461083","https://openalex.org/W2795275057","https://openalex.org/W2802773536","https://openalex.org/W2888836575","https://openalex.org/W2963504927","https://openalex.org/W2964241990","https://openalex.org/W4300081896"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W2801048620"],"abstract_inverted_index":{"Recently,":[0],"most":[1],"of":[2,5,59,66,115,130,147,170],"the":[3,21,41,47,53,57,112,125,144,152,163,176,183],"work":[4,67],"generating":[6],"a":[7,11,107,121,168],"text":[8],"description":[9,169],"from":[10,33],"video":[12,72,88],"is":[13,70,86,98,179],"based":[14],"on":[15,182],"an":[16],"Encoder-Decoder":[17],"framework.":[18],"Firstly,":[19],"in":[20,162],"encoder":[22,126],"stage,":[23,49,127],"different":[24,79],"convolutional":[25],"neural":[26],"networks":[27],"are":[28,44,63,83,138,160],"using":[29],"to":[30,55,119,150,166,188],"extract":[31],"features":[32,43],"audio":[34],"and":[35,39,135],"visual":[36],"modalities":[37,129],"respectively,":[38,140],"then":[40],"extracted":[42],"input":[45],"into":[46],"decoder":[48,164],"which":[50,110,141],"will":[51,74,90],"use":[52],"LSTM":[54,156],"generate":[56,167],"caption":[58,73,89],"video.":[60,171],"Currently,":[61],"there":[62],"two":[64,113,128,145,177],"types":[65,114],"concerns.":[68],"One":[69],"whether":[71,87],"be":[75,91],"generated":[76,92,151],"accurately":[77,94],"if":[78,95],"multimodal":[80,131],"fusion":[81,108,173],"strategies":[82],"adopted.":[84],"Another":[85],"more":[93],"attention":[96,158],"mechanism":[97,159],"added.":[99],"In":[100,124],"this":[101],"paper,":[102],"we":[103],"come":[104],"up":[105],"with":[106,157],"framework":[109],"combines":[111],"methods":[116,178],"concerned":[117],"above":[118],"produce":[120],"new":[122],"model.":[123],"fusion,":[132],"sharing":[133,136],"weights":[134],"memory":[137],"utilized":[139],"can":[142],"make":[143],"kinds":[146],"characteristics":[148],"resonated":[149],"final":[153],"feature":[154],"outputs.":[155],"used":[161],"state":[165],"Our":[172],"model":[174],"combining":[175],"well":[180],"validated":[181],"dataset":[184],"Microsoft":[185],"Research":[186],"Video":[187],"Text":[189],"(MSR-VTT).":[190]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}