{"id":"https://openalex.org/W2766711654","doi":"https://doi.org/10.1145/3126686.3126715","title":"Learning Deep Contextual Attention Network for Narrative Photo Stream Captioning","display_name":"Learning Deep Contextual Attention Network for Narrative Photo Stream Captioning","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2766711654","doi":"https://doi.org/10.1145/3126686.3126715","mag":"2766711654"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","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/A5029797380","display_name":"Hanqi Wang","orcid":"https://orcid.org/0000-0003-3549-3901"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanqi Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343725","display_name":"Yin Zhang","orcid":"https://orcid.org/0000-0002-6761-2269"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039792198","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0001-5498-4947"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029797380"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.4551,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7332856,"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":"271","last_page":"279"},"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":0.9973000288009644,"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":0.9937999844551086,"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":0.929463803768158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.859825611114502},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6764544248580933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.582335889339447},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5725829601287842},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.560965359210968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.560380220413208},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5267093777656555},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.43584126234054565},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.424133837223053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33862242102622986},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24196556210517883},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22731620073318481},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15762081742286682}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.929463803768158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859825611114502},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6764544248580933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582335889339447},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5725829601287842},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.560965359210968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.560380220413208},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5267093777656555},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.43584126234054565},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.424133837223053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33862242102622986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24196556210517883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22731620073318481},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15762081742286682},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126686.3126715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4395682344","display_name":null,"funder_award_id":"U1611461, U1509206, 61625107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W92662927","https://openalex.org/W1514535095","https://openalex.org/W1586939924","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1931639407","https://openalex.org/W1969616664","https://openalex.org/W2105103432","https://openalex.org/W2109586012","https://openalex.org/W2131179926","https://openalex.org/W2139501017","https://openalex.org/W2143449221","https://openalex.org/W2157331557","https://openalex.org/W2183386595","https://openalex.org/W2197223256","https://openalex.org/W2302086703","https://openalex.org/W2399607792","https://openalex.org/W2544271936","https://openalex.org/W2559780844","https://openalex.org/W2951008357","https://openalex.org/W2953106684","https://openalex.org/W2963576560","https://openalex.org/W2963758027","https://openalex.org/W2964241990","https://openalex.org/W3087871082","https://openalex.org/W3105311191","https://openalex.org/W4234552385"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"While":[0],"image":[1,154],"captioning":[2,22],"has":[3],"been":[4],"extensively":[5],"studied,":[6],"the":[7,28,39,66,73,86,99,115,120,124,138,141,151,160,168],"problem":[8],"of":[9,42,178],"generating":[10],"narrative":[11],"descriptions":[12],"for":[13],"photo":[14,61,139],"streams":[15,62],"still":[16],"remains":[17],"under":[18],"explored.":[19],"Photo":[20],"stream":[21],"is":[23,80,129,144],"more":[24,145],"challenging":[25],"due":[26],"to":[27,58,117,131],"large":[29],"visual":[30,89,133],"variance,":[31],"complicated":[32],"object":[33],"context,":[34],"and":[35,72,95,135,163,174,181],"sentence-to-sentence":[36],"coherence":[37,74,122],"in":[38,75,82,137,176],"ordered":[40],"collection":[41],"photos.":[43],"To":[44],"deal":[45],"with":[46,102],"these":[47],"challenges,":[48],"we":[49],"propose":[50],"a":[51,106],"novel":[52,107],"deep":[53],"contextual":[54],"attention":[55,100,134],"network":[56],"(CAN)":[57],"narratively":[59],"describe":[60],"by":[63,171],"jointly":[64],"exploring":[65],"rich":[67],"context":[68,136],"among":[69,123],"attended":[70],"regions":[71],"sentences.":[76,126],"The":[77],"proposed":[78],"CAN":[79,128,166],"designed":[81],"an":[83],"encoder-decoder":[84],"framework:":[85],"encoder":[87],"models":[88],"contexts":[90],"via":[91],"region-level":[92],"bilinear":[93],"similarity":[94],"selectively":[96],"focuses":[97],"on":[98,159],"areas":[101],"salient":[103],"context;":[104],"while":[105],"hierarchical":[108],"gated":[109],"recurrent":[110],"unit":[111],"(h-GRU)":[112],"acts":[113],"as":[114],"decoder":[116],"effectively":[118],"preserve":[119],"semantic":[121],"generated":[125,142],"As":[127],"capable":[130],"exploit":[132],"stream,":[140],"story":[143],"semantically":[146],"coherent":[147],"than":[148],"merely":[149],"concatenating":[150],"isolated":[152],"individual":[153],"captions.":[155],"We":[156],"conduct":[157],"experiments":[158],"SIND":[161],"dataset":[162],"show":[164],"that":[165],"outperforms":[167],"state-of-the-art":[169],"methods":[170],"3.1%,":[172],"8.9%,":[173],"9.1%":[175],"terms":[177],"BLEU,":[179],"METEOR":[180],"CIDEr,":[182],"respectively.":[183]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}