{"id":"https://openalex.org/W2963498278","doi":"https://doi.org/10.1109/icip.2016.7532983","title":"Beyond caption to narrative: Video captioning with multiple sentences","display_name":"Beyond caption to narrative: Video captioning with multiple sentences","publication_year":2016,"publication_date":"2016-08-17","ids":{"openalex":"https://openalex.org/W2963498278","doi":"https://doi.org/10.1109/icip.2016.7532983","mag":"2963498278"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2016.7532983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Image Processing (ICIP)","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/A5057366552","display_name":"Andrew Shin","orcid":"https://orcid.org/0000-0002-0969-9925"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Shin","raw_affiliation_strings":["Grad. School of Information Science and Technology, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grad. School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112092551","display_name":"Katsunori Ohnishi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsunori Ohnishi","raw_affiliation_strings":["Grad. School of Information Science and Technology, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grad. School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042711470","display_name":"Tatsuya Harada","orcid":"https://orcid.org/0000-0002-3712-3691"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Harada","raw_affiliation_strings":["Grad. School of Information Science and Technology, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grad. School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0282,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91577804,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3364","last_page":"3368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9972000122070312,"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":0.9962728023529053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8577913641929626},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6747687458992004},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5597281455993652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.554724395275116},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5113050937652588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4220014214515686},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4158865809440613},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3779919147491455},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33146435022354126}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9962728023529053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577913641929626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6747687458992004},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5597281455993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554724395275116},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5113050937652588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4220014214515686},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4158865809440613},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3779919147491455},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33146435022354126},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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/icip.2016.7532983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1566289585","https://openalex.org/W1572567476","https://openalex.org/W1573040851","https://openalex.org/W1595717062","https://openalex.org/W1632114991","https://openalex.org/W1686810756","https://openalex.org/W1797109199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1944615693","https://openalex.org/W1950136256","https://openalex.org/W1956340063","https://openalex.org/W2010267071","https://openalex.org/W2022582203","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2081580037","https://openalex.org/W2095242101","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2105101328","https://openalex.org/W2108598243","https://openalex.org/W2118877769","https://openalex.org/W2123442489","https://openalex.org/W2126574503","https://openalex.org/W2131042978","https://openalex.org/W2131744502","https://openalex.org/W2133459682","https://openalex.org/W2147238549","https://openalex.org/W2155893237","https://openalex.org/W2161969291","https://openalex.org/W2164290393","https://openalex.org/W2179034043","https://openalex.org/W2187772033","https://openalex.org/W2190406907","https://openalex.org/W2425121537","https://openalex.org/W2481240925","https://openalex.org/W2545708073","https://openalex.org/W2962835968","https://openalex.org/W4239072543","https://openalex.org/W4294650876","https://openalex.org/W4323697410","https://openalex.org/W6600983433","https://openalex.org/W6634126550","https://openalex.org/W6634426396","https://openalex.org/W6635755983","https://openalex.org/W6636649193","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6639425484","https://openalex.org/W6639657675","https://openalex.org/W6639809013","https://openalex.org/W6640169532","https://openalex.org/W6640559356","https://openalex.org/W6640767456","https://openalex.org/W6674914833","https://openalex.org/W6676297131","https://openalex.org/W6677548441","https://openalex.org/W6679775712","https://openalex.org/W6684090549","https://openalex.org/W6686679147","https://openalex.org/W6687037952","https://openalex.org/W6717767745","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Recent":[0],"advances":[1,109],"in":[2,11,47,81,100,110,119,155,189,208],"image":[3,34,111,142],"captioning":[4,13,20,35,112,121,128,143],"task":[5,113],"have":[6,114],"led":[7,115],"to":[8,51,83,116,159,191],"increasing":[9,117],"interests":[10,118],"video":[12,19,53,63,120,127,161,171],"task.":[14,122],"However,":[15,123],"most":[16,124],"works":[17,125],"on":[18,23,126,131],"are":[21,98,129,206],"focused":[22,130],"generating":[24,67,132,175],"single":[25,133],"input":[26,134],"of":[27,43,135,151],"aggregated":[28,136],"features,":[29,137],"which":[30,138],"hardly":[31,139],"deviates":[32,140],"from":[33,70,141,178],"process":[36,144],"and":[37,73,102,145,181,210],"does":[38,146],"not":[39,147],"fully":[40,148],"take":[41,149],"advantage":[42,150],"dynamic":[44,152],"contents":[45,58,101,153,166,209],"present":[46,154],"videos.":[48,156],"We":[49,88,157,196],"attempt":[50,158],"generate":[52,84,95,160,192,203],"captions":[54,69,96,162,177,204],"that":[55,90,97,163,198,205],"convey":[56,164],"richer":[57,99,165,207],"by":[59,167],"temporally":[60,168],"segmenting":[61,169],"the":[62,170],"with":[64,76,105,172,184,213],"action":[65,173],"localization,":[66,174],"multiple":[68,71,176,179],"frames,":[72,180],"connecting":[74,182],"them":[75,183],"natural":[77,185],"language":[78,186],"processing":[79,187],"techniques,":[80,188],"order":[82,190],"a":[85,193],"story-like":[86,194],"caption.":[87,195],"show":[89,197],"our":[91,199],"proposed":[92,200],"method":[93,107,201,215],"can":[94,103,202,211],"compete":[104,212],"state-of-the-art":[106,214],"wRecent":[108],"without":[216],"explicitly":[217],"using":[218],"video-level":[219],"features":[220],"as":[221],"input.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}