{"id":"https://openalex.org/W2897043747","doi":"https://doi.org/10.1109/bigmm.2018.8499357","title":"Video Captioning with Semantic Guiding","display_name":"Video Captioning with Semantic Guiding","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2897043747","doi":"https://doi.org/10.1109/bigmm.2018.8499357","mag":"2897043747"},"language":"en","primary_location":{"id":"doi:10.1109/bigmm.2018.8499357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","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/A5100603557","display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9600-7789"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083602794","display_name":"Chunna Tian","orcid":"https://orcid.org/0000-0002-3217-0368"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunna Tian","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114672955","display_name":"Xiangnan Zhang","orcid":"https://orcid.org/0000-0003-4433-3686"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangnan Zhang","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067367860","display_name":"Yuxuan Ding","orcid":"https://orcid.org/0000-0003-0172-1857"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Ding","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323672","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0002-0655-056X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100603557"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.6267,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.74509625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":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":0.9976999759674072,"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":0.9954000115394592,"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":0.8796550035476685},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7758376002311707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6386765837669373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5935735702514648},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.5590286254882812},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.499286413192749},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.47166121006011963},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44890066981315613},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4305221438407898},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4207257926464081},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4064125716686249},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.28428351879119873},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20659157633781433},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07420185208320618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8796550035476685},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7758376002311707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6386765837669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5935735702514648},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.5590286254882812},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.499286413192749},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.47166121006011963},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44890066981315613},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4305221438407898},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4207257926464081},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4064125716686249},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.28428351879119873},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20659157633781433},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07420185208320618},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigmm.2018.8499357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1931639407","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2325920097","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2949365443","https://openalex.org/W2952238956","https://openalex.org/W2953022248","https://openalex.org/W2963149042","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6685670348","https://openalex.org/W6729190352"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W2376633828","https://openalex.org/W2380556669","https://openalex.org/W2031477912","https://openalex.org/W2389993829","https://openalex.org/W2349174110","https://openalex.org/W207304934","https://openalex.org/W2977842567","https://openalex.org/W1536405386","https://openalex.org/W2900598933"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2],"to":[3,89,93,99],"generate":[4,100],"descriptions":[5],"of":[6,20,72,77],"videos.":[7],"Most":[8],"existing":[9],"approaches":[10],"adopt":[11],"the":[12,33,38,95,107,120],"encoder-decoder":[13],"architecture,":[14],"which":[15],"usually":[16],"use":[17,74,94],"different":[18],"kinds":[19],"visual":[21,51],"features,":[22,29],"such":[23],"as":[24],"temporal":[25],"features":[26,52],"and":[27,53,84],"motion":[28],"but":[30],"they":[31],"neglect":[32],"abundant":[34],"semantic":[35,54,68,78,83,86],"information":[36],"in":[37],"video.":[39],"To":[40],"address":[41],"this":[42],"issue,":[43],"we":[44],"propose":[45],"a":[46],"framework":[47,118],"that":[48,116],"jointly":[49],"explores":[50],"attributions":[55],"named":[56],"Semantic":[57],"Guiding":[58],"Long":[59],"Short-Term":[60],"Memory":[61],"(SG-LSTM).":[62],"The":[63],"proposed":[64],"SG-LSTM":[65],"has":[66],"two":[67],"guiding":[69],"layers,":[70],"both":[71],"them":[73],"three":[75],"types":[76],"-":[79,87],"global":[80],"semantic,":[81],"object":[82],"verb":[85],"attributes":[88],"guide":[90],"language":[91],"model":[92],"most":[96],"relevant":[97],"representation":[98],"sentences.":[101],"We":[102],"evaluate":[103],"our":[104,117],"method":[105],"on":[106],"public":[108],"available":[109],"challenging":[110],"Youtube2Text":[111],"dataset.":[112],"Experimental":[113],"results":[114],"shown":[115],"outperforms":[119],"state-of-the-art":[121],"methods.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}