{"id":"https://openalex.org/W2740757571","doi":"https://doi.org/10.24963/ijcai.2017/558","title":"An Attention-based Regression Model for Grounding Textual Phrases in Images","display_name":"An Attention-based Regression Model for Grounding Textual Phrases in Images","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740757571","doi":"https://doi.org/10.24963/ijcai.2017/558","mag":"2740757571"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/558","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/558","pdf_url":"https://www.ijcai.org/proceedings/2017/0558.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0558.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003118111","display_name":"Endo Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ko Endo","raw_affiliation_strings":["Toyohashi University of Technology"],"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022595726","display_name":"Masaki Aono","orcid":"https://orcid.org/0000-0003-1383-1076"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Aono","raw_affiliation_strings":["Toyohashi University of Technology"],"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056903330","display_name":"Eric Nichols","orcid":"https://orcid.org/0000-0003-0734-6621"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eric Nichols","raw_affiliation_strings":["Honda Research Institute Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Honda Research Institute Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003118111"],"corresponding_institution_ids":["https://openalex.org/I136259955"],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.76081566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3995","last_page":"4001"},"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":0.9952999949455261,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/phrase","display_name":"Phrase","score":0.8749215602874756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7600716352462769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6971290707588196},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6705349683761597},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6386033296585083},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4984893798828125},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4753279983997345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46454334259033203},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4389336407184601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4360581636428833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10654151439666748}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8749215602874756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600716352462769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6971290707588196},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6705349683761597},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6386033296585083},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4984893798828125},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4753279983997345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46454334259033203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4389336407184601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4360581636428833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10654151439666748},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/558","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/558","pdf_url":"https://www.ijcai.org/proceedings/2017/0558.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/558","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/558","pdf_url":"https://www.ijcai.org/proceedings/2017/0558.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7599130655","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740757571.pdf","grobid_xml":"https://content.openalex.org/works/W2740757571.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W114341944","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1525954826","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1922126009","https://openalex.org/W1933349210","https://openalex.org/W2006147162","https://openalex.org/W2037227137","https://openalex.org/W2131494463","https://openalex.org/W2133564696","https://openalex.org/W2167090521","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2463565445","https://openalex.org/W2583360688","https://openalex.org/W2963383024","https://openalex.org/W2963735856","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3098232790","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2916983164","https://openalex.org/W2356613672"],"abstract_inverted_index":{"Grounding,":[0],"or":[1],"localizing,":[2],"a":[3,10,56,61,71,134],"textual":[4,72,110],"phrase":[5],"in":[6,108,124,137],"an":[7,162],"image":[8,90,104,156,163],"is":[9,14],"challenging":[11,114],"problem":[12,58],"that":[13,37,154],"integral":[15],"to":[16,22,63,69,88,169],"visual":[17],"language":[18],"understanding.":[19],"Previous":[20],"approaches":[21],"this":[23,50,117],"task":[24,118],"typically":[25],"make":[26],"use":[27],"of":[28,38,116,121,139],"candidate":[29,79],"region":[30,40,67,80,98],"proposals,":[31],"where":[32],"end":[33],"performance":[34,138],"depends":[35],"on":[36,126],"the":[39,66,75,96,109,113,127,143],"proposal":[41],"method":[42,62,132],"and":[43,59,91,94,106,119,157,161],"additional":[44],"computational":[45],"costs":[46],"are":[47],"incurred.":[48],"In":[49],"paper,":[51],"we":[52],"treat":[53],"grounding":[54],"as":[55],"regression":[57],"propose":[60],"directly":[64],"identify":[65],"referred":[68],"by":[70,147],"phrase,":[73],"eliminating":[74],"need":[76],"for":[77],"external":[78],"prediction.":[81],"Our":[82],"approach":[83],"uses":[84],"deep":[85],"neural":[86],"networks":[87],"combine":[89],"text":[92,158],"representations":[93],"refines":[95],"target":[97],"with":[99],"attention":[100,159,164],"models":[101,160],"over":[102,148],"both":[103],"subregions":[105],"words":[107],"phrase.":[111],"Despite":[112],"nature":[115],"sparsity":[120],"available":[122],"data,":[123],"evaluation":[125],"ReferIt":[128],"dataset,":[129],"our":[130],"proposed":[131],"achieves":[133],"new":[135],"state-of-the-art":[136],"37.26%":[140],"accuracy,":[141],"surpassing":[142],"previously":[144],"reported":[145],"best":[146],"5":[149],"percentage":[150],"points.":[151],"We":[152],"find":[153],"combining":[155],"area-sensitive":[165],"loss":[166],"function":[167],"contribute":[168],"substantial":[170],"improvements.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}