{"id":"https://openalex.org/W3173961205","doi":"https://doi.org/10.1109/tmm.2021.3093725","title":"Exploring Pairwise Relationships Adaptively From Linguistic Context in Image Captioning","display_name":"Exploring Pairwise Relationships Adaptively From Linguistic Context in Image Captioning","publication_year":2021,"publication_date":"2021-06-30","ids":{"openalex":"https://openalex.org/W3173961205","doi":"https://doi.org/10.1109/tmm.2021.3093725","mag":"3173961205"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3093725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3093725","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5060113731","display_name":"Zongjian Zhang","orcid":"https://orcid.org/0000-0001-9309-1826"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zongjian Zhang","raw_affiliation_strings":["School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9309-1826","affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063629854","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0001-5641-2483"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5641-2483","affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714578","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-6815-0879"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fang Chen","raw_affiliation_strings":["School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4971-8729","affiliations":[{"raw_affiliation_string":"School of Electrical and Data Engineering - FEIT, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":2.5439,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91273307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"3101","last_page":"3113"},"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":0.9962999820709229,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9814000129699707,"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":0.9128760099411011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337584733963013},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6267887353897095},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6077756881713867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5911017060279846},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5709470510482788},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5333960056304932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4832054376602173},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.42527350783348083},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42225661873817444},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37834739685058594},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15177485346794128}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9128760099411011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337584733963013},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6267887353897095},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6077756881713867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5911017060279846},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5709470510482788},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5333960056304932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4832054376602173},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.42527350783348083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42225661873817444},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37834739685058594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15177485346794128},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3093725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3093725","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123442489","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2560645892","https://openalex.org/W2560920409","https://openalex.org/W2735553491","https://openalex.org/W2745461083","https://openalex.org/W2753232960","https://openalex.org/W2754927243","https://openalex.org/W2802194751","https://openalex.org/W2885013662","https://openalex.org/W2887272576","https://openalex.org/W2887712318","https://openalex.org/W2890531016","https://openalex.org/W2901988662","https://openalex.org/W2906314281","https://openalex.org/W2909827971","https://openalex.org/W2913618459","https://openalex.org/W2945223572","https://openalex.org/W2962938439","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963630207","https://openalex.org/W2964018924","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6726873649","https://openalex.org/W6728881024","https://openalex.org/W6731370813","https://openalex.org/W6751795543"],"related_works":["https://openalex.org/W3045147787","https://openalex.org/W4320016117","https://openalex.org/W2970216048","https://openalex.org/W3113933322","https://openalex.org/W2574790321","https://openalex.org/W2168273525","https://openalex.org/W4376109757","https://openalex.org/W2052907849","https://openalex.org/W2019533095","https://openalex.org/W2125481629"],"abstract_inverted_index":{"For":[0],"image":[1],"captioning,":[2],"recent":[3],"works":[4,24],"start":[5],"to":[6,104,125,174,195,221],"focus":[7,26],"on":[8,27,64,83,169,232],"exploring":[9],"visual":[10,39,65,128,163,177,197,205,247],"relationships":[11,74,129,178,198],"for":[12,199,207],"generating":[13,200],"high-quality":[14],"interactive":[15,70,201],"words":[16,59,71,77,109,202],"(i.e.":[17],"verbs":[18],"and":[19,179],"prepositions).":[20],"However,":[21],"many":[22],"existing":[23],"only":[25,79],"semantic":[28],"level":[29],"by":[30,148],"analysing":[31],"the":[32,38,43,48,57,73,89,105,113,149,153,185,190,222,227],"feature":[33],"similarity":[34],"between":[35,75,108,130],"objects":[36,132,206],"in":[37,47,88,112],"domain":[40],"but":[41],"ignore":[42],"linguistic":[44,100,117,150,186,224],"context":[45,107,118,151,225],"included":[46],"caption":[49,114,154,228],"decoder.":[50,155],"When":[51],"captioning":[52,92],"is":[53,98,145,166,213],"being":[54],"carried":[55],"out,":[56],"entity":[58,76,208],"can":[60,78,119],"be":[61,80,120],"inferred":[62,81],"based":[63,82,168],"information":[66],"of":[67,91,162,193,226],"objects.":[68],"The":[69,116],"representing":[72],"high-level":[84,95],"language":[85,96],"meaning":[86,97],"generated":[87],"process":[90,192],"decoding.":[93],"Such":[94],"called":[99],"context,":[101],"which":[102],"refers":[103],"relational":[106],"or":[110,203],"phrases":[111],"sentences.":[115],"used":[121],"as":[122,215],"strong":[123],"guidance":[124],"explore":[126,175,246],"related":[127,176,196,204],"different":[131],"effectively.":[133],"To":[134,188],"achieve":[135,189],"this,":[136],"we":[137],"propose":[138],"a":[139,159,170],"novel":[140,160],"context-adaptive":[141],"attention":[142,165,211,217],"module":[143],"that":[144,245],"strongly":[146],"driven":[147],"from":[152],"In":[156],"this":[157],"module,":[158],"design":[161],"relationship":[164],"proposed":[167],"bilinear":[171],"self-attention":[172],"model":[173,236],"encode":[180],"more":[181],"discriminative":[182],"features":[183],"under":[184],"context.":[187],"adaptive":[191],"attending":[194],"words,":[209],"an":[210,216],"modulator":[212],"integrated":[214],"channel":[218],"controller":[219],"responding":[220],"changing":[223],"decoder":[229],"dynamically.":[230],"Experimented":[231],"MSCOCO":[233],"dataset,":[234],"our":[235],"achieves":[237],"promising":[238],"performances":[239],"compared":[240],"with":[241],"all":[242],"counterpart":[243],"models":[244],"relationships.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}