{"id":"https://openalex.org/W1596746947","doi":"https://doi.org/10.1109/icme.2015.7177427","title":"Predicting image caption by a unified hierarchical model","display_name":"Predicting image caption by a unified hierarchical model","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1596746947","doi":"https://doi.org/10.1109/icme.2015.7177427","mag":"1596746947"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2015.7177427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101797092","display_name":"Lin Bai","orcid":"https://orcid.org/0000-0002-2324-9779"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Bai","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107837627","display_name":"Kan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kan Li","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China","Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Haidian District, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101797092"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.5523,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73292352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9854999780654907,"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":0.8040186166763306},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7097342014312744},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6527789831161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6296149492263794},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6185367703437805},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.547508955001831},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5429993867874146},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4816204905509949},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4589501619338989},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4477246403694153},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.41559380292892456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3772323429584503},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2130853235721588},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07201692461967468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040186166763306},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7097342014312744},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6527789831161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6296149492263794},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6185367703437805},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.547508955001831},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5429993867874146},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4816204905509949},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4589501619338989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4477246403694153},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.41559380292892456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3772323429584503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2130853235721588},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07201692461967468},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2015.7177427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","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":21,"referenced_works":["https://openalex.org/W62621907","https://openalex.org/W203345490","https://openalex.org/W1517303303","https://openalex.org/W1895577753","https://openalex.org/W1972283961","https://openalex.org/W1976546217","https://openalex.org/W2049705550","https://openalex.org/W2050964073","https://openalex.org/W2080920426","https://openalex.org/W2097117768","https://openalex.org/W2100495367","https://openalex.org/W2112912048","https://openalex.org/W2132172482","https://openalex.org/W2143449221","https://openalex.org/W2159991108","https://openalex.org/W2169393274","https://openalex.org/W2296385829","https://openalex.org/W6639657675","https://openalex.org/W6674914833","https://openalex.org/W6676647902","https://openalex.org/W6681184217"],"related_works":["https://openalex.org/W1991139010","https://openalex.org/W2140435402","https://openalex.org/W4285276086","https://openalex.org/W2388546068","https://openalex.org/W2161633202","https://openalex.org/W2039787362","https://openalex.org/W2901621883","https://openalex.org/W1750537857","https://openalex.org/W2163490908","https://openalex.org/W3022564861"],"abstract_inverted_index":{"Automatically":[0],"describing":[1,145],"the":[2,23,28,32,36,47,58,63,67,73,80,87,93,100,106,114,118,125,146],"content":[3,60,116],"of":[4,31,95,120],"an":[5],"image":[6,24,59,115,147],"is":[7,16],"a":[8,41],"challenging":[9],"task":[10],"in":[11,19,35,139],"artificial":[12],"intelligence.":[13],"The":[14],"difficulty":[15],"particularly":[17],"pronounced":[18],"activity":[20,49],"recognition":[21],"and":[22,52,55,86,144],"caption":[25],"revealed":[26],"by":[27,61],"relationship":[29,65],"analysis":[30],"activities":[33,101,143],"involved":[34],"image.":[37],"This":[38],"paper":[39],"presents":[40],"unified":[42,134],"hierarchical":[43,135],"model":[44,46,136],"to":[45,90,112],"interaction":[48,68,77,97,110,142],"between":[50,84],"human":[51,85],"nearby":[53],"object,":[54],"then":[56],"speculates":[57],"analyzing":[62],"logical":[64],"among":[66,124],"activities.":[69,98,126],"In":[70],"our":[71,133],"model,":[72],"first-layer":[74],"factored":[75,108],"three-way":[76,109],"machine":[78,111],"models":[79],"3D":[81,121],"spatial":[82,122],"context":[83,123],"relevant":[88],"object":[89],"straightly":[91],"aid":[92],"prediction":[94],"human-object":[96,141],"Then,":[99],"are":[102],"further":[103],"processed":[104],"through":[105],"top-layer":[107],"learn":[113],"with":[117],"help":[119],"Experiments":[127],"on":[128],"joint":[129],"dataset":[130],"show":[131],"that":[132],"outperforms":[137],"state-of-the-arts":[138],"predicting":[140],"caption.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}