{"id":"https://openalex.org/W2897964062","doi":"https://doi.org/10.1145/3240508.3240583","title":"Look Deeper See Richer","display_name":"Look Deeper See Richer","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2897964062","doi":"https://doi.org/10.1145/3240508.3240583","mag":"2897964062"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","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/A5100389369","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0002-0107-7347"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063603492","display_name":"Yadan Luo","orcid":"https://orcid.org/0000-0001-6272-2971"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yadan Luo","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733463","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-5484-0895"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088492734","display_name":"Hongzhi Yin","orcid":"https://orcid.org/0000-0003-1395-261X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongzhi Yin","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100389369"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":2.2328,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91452137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"672","last_page":"680"},"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":0.9940999746322632,"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":0.9843000173568726,"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":0.9654958248138428},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.8920128345489502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998137474060059},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.798757791519165},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7852365374565125},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6479269862174988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6176514029502869},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.584865927696228},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5529718399047852},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5107643604278564},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5050464272499084}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9654958248138428},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.8920128345489502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998137474060059},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.798757791519165},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7852365374565125},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6479269862174988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176514029502869},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.584865927696228},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5529718399047852},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5107643604278564},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5050464272499084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W49643808","https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1803059841","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2176263492","https://openalex.org/W2481240925","https://openalex.org/W2508429489","https://openalex.org/W2527145521","https://openalex.org/W2527938858","https://openalex.org/W2549599535","https://openalex.org/W2575842049","https://openalex.org/W2607662938","https://openalex.org/W2739107216","https://openalex.org/W2766237723","https://openalex.org/W2766375149","https://openalex.org/W2803620531","https://openalex.org/W2809645418","https://openalex.org/W2887712318","https://openalex.org/W2949376505","https://openalex.org/W2963649796","https://openalex.org/W3103022576","https://openalex.org/W3104557502","https://openalex.org/W4249502209"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W2391800119","https://openalex.org/W2052919063","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280"],"abstract_inverted_index":{"With":[0],"the":[1,56,63,70,89,93,139,151,161,164,169,187,194,200,203,206],"widespread":[2],"availability":[3],"of":[4,52,60,118,132,205],"image":[5,15,23,45,71,79,119],"captioning":[6,47,81],"at":[7],"a":[8,25,41,50,104,130,154,180],"sentence":[9,170],"level,":[10],"how":[11],"to":[12,54,87,110,126,142],"automatically":[13],"generate":[14,88,111],"paragraphs":[16],"is":[17,85],"yet":[18],"well":[19],"explored.":[20],"Describing":[21],"an":[22],"by":[24,40,68],"full":[26],"paragraph":[27,46,112,152,173],"involves":[28],"organising":[29],"sentences":[30,53],"orderly,":[31],"coherently":[32],"and":[33,58,75,96,156,186,202],"diversely,":[34],"inevitably":[35],"leading":[36],"higher":[37],"complexity":[38],"than":[39],"single":[42],"sentence.":[43],"Existing":[44],"methods":[48],"give":[49],"series":[51],"represent":[55],"objects":[57,74,128],"regions":[59,76],"interests,":[61],"where":[62],"descriptions":[64,90,178],"are":[65,121],"essentially":[66],"generated":[67],"feeding":[69],"fragments":[72],"containing":[73],"into":[77],"conventional":[78],"single-sentence":[80],"models.":[82],"This":[83,148],"strategy":[84],"difficult":[86],"that":[91],"guarantee":[92],"stereoscopic":[94],"hierarchy":[95],"non-overlapping":[97],"objects.":[98,147],"In":[99],"this":[100],"paper,":[101],"we":[102],"propose":[103],"Depth-aware":[105],"Attention":[106],"Model":[107],"(\\textitDAM":[108],")":[109],"captions":[113],"for":[114],"images.":[115],"The":[116],"depths":[117],"areas":[120],"firstly":[122],"estimated":[123],"in":[124,129,153],"order":[125],"discriminate":[127],"range":[131],"spatial":[133,144],"locations,":[134],"which":[135,198],"can":[136],"further":[137],"guide":[138],"linguistic":[140],"decoder":[141],"reveal":[143],"relationships":[145],"among":[146],"model":[149,166],"completes":[150],"logical":[155],"coherent":[157],"manner.":[158],"By":[159],"incorporating":[160],"attention":[162],"mechanism,":[163],"learned":[165],"swiftly":[167],"shifts":[168],"focus":[171],"during":[172],"generation,":[174],"whilst":[175],"avoiding":[176],"verbose":[177],"on":[179,193],"same":[181],"object.":[182],"Extensive":[183],"quantitative":[184],"experiments":[185],"user":[188],"study":[189],"have":[190],"been":[191],"conducted":[192],"Visual":[195],"Genome":[196],"dataset,":[197],"demonstrate":[199],"effectiveness":[201],"interpretability":[204],"proposed":[207],"model.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}