{"id":"https://openalex.org/W2896902935","doi":"https://doi.org/10.1145/3240508.3240513","title":"Object-Difference Attention: A Simple Relational Attention for Visual Question Answering","display_name":"Object-Difference Attention: A Simple Relational Attention for Visual Question Answering","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2896902935","doi":"https://doi.org/10.1145/3240508.3240513","mag":"2896902935"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240513","doi":"https://doi.org/10.1145/3240508.3240513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240513","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"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"},"parent_works":[],"lineage":["https://openalex.org/W2896902935"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5101571309","display_name":"Chenfei Wu","orcid":"https://orcid.org/0000-0002-5678-9691","observed_orcids":["https://orcid.org/0000-0002-5678-9691"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenfei Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748854","display_name":"Jinlai Liu","orcid":"https://orcid.org/0000-0001-5993-683X","observed_orcids":["https://orcid.org/0000-0001-5993-683X"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlai Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951","observed_orcids":["https://orcid.org/0000-0003-0314-8951"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xuan Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Dong","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.8311,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.92034077,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"519","last_page":"527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9932000041007996,"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":0.9932000041007996,"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":0.00559999980032444,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0003000000142492354,"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/visual-question-answering","display_name":"visual question answering","score":0.984000027179718},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.7160000205039978},{"id":"https://openalex.org/keywords/relational-attention","display_name":"relational attention","score":0.7670000195503235},{"id":"https://openalex.org/keywords/difference-operators","display_name":"difference operators","score":0.6600000262260437},{"id":"https://openalex.org/keywords/attention-allocation","display_name":"attention allocation","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536081671714783},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6885182857513428},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6594460606575012},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6546334028244019},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6336230039596558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362934470176697},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.5133036971092224},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4690307378768921},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.43191924691200256},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3749558627605438},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.20791617035865784},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06008034944534302},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240513","doi":"https://doi.org/10.1145/3240508.3240513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240513","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"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":[],"study_designs":[],"awards":[],"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":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2095705004","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2174492417","https://openalex.org/W2179022885","https://openalex.org/W2416885651","https://openalex.org/W2442626797","https://openalex.org/W2463565445","https://openalex.org/W2471768434","https://openalex.org/W2532034655","https://openalex.org/W2546696630","https://openalex.org/W2553418567","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2616125804","https://openalex.org/W2624614404","https://openalex.org/W2745132836","https://openalex.org/W2745461083","https://openalex.org/W2753474648","https://openalex.org/W2787119853","https://openalex.org/W2962933067","https://openalex.org/W2963082899","https://openalex.org/W2963143606","https://openalex.org/W2963150162","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963560969","https://openalex.org/W2963656855","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W2964199361"],"related_works":["https://openalex.org/W3011329351","https://openalex.org/W2966988657","https://openalex.org/W2941471352","https://openalex.org/W2997531716","https://openalex.org/W2807941860","https://openalex.org/W3095478416","https://openalex.org/W2795782778","https://openalex.org/W3004349648","https://openalex.org/W2949693283","https://openalex.org/W2799345082"],"abstract_inverted_index":{"Attention":[0,12],"mechanism":[1],"has":[2],"greatly":[3],"promoted":[4],"the":[5,46,59,100,116,136],"development":[6],"of":[7,45,72,102,118,143,167],"Visual":[8],"Question":[9],"Answering":[10],"(VQA).":[11],"distribution,":[13],"which":[14,98],"weights":[15],"differently":[16],"on":[17,50,76,124,164],"objects":[18,111],"(such":[19],"as":[20],"image":[21,28,52,66,110,114],"regions":[22],"or":[23],"bounding":[24],"boxes)":[25],"in":[26,41,112,120],"an":[27,94,113],"according":[29],"to":[30,57],"their":[31],"importance":[32],"for":[33,85],"answering":[34],"a":[35,38,69,140],"question,":[36],"plays":[37],"crucial":[39],"role":[40],"attention":[42,60,96,103,145],"mechanism.":[43],"Most":[44],"existing":[47],"work":[48],"focuses":[49],"fusing":[51],"features":[53,56],"and":[54],"text":[55],"calculate":[58],"distribution":[61],"without":[62],"comparisons":[63,77],"between":[64,78,108],"different":[65,79,109,165],"objects.":[67,80],"As":[68],"major":[70],"property":[71],"attention,":[73],"selectivity":[74],"depends":[75],"Comparisons":[81],"provide":[82],"more":[83],"information":[84],"assigning":[86],"attentions":[87,153,161],"better.":[88],"For":[89],"achieving":[90],"this,":[91],"we":[92],"propose":[93],"object-difference":[95],"(ODA)":[97],"calculates":[99],"probability":[101],"by":[104],"implementing":[105],"difference":[106],"operator":[107],"under":[115],"guidance":[117],"questions":[119],"hand.":[121],"Experimental":[122,156],"results":[123,157],"three":[125],"publicly":[126],"available":[127],"datasets":[128],"show":[129,158],"our":[130],"ODA":[131],"based":[132],"VQA":[133],"model":[134],"achieves":[135],"state-of-the-art":[137],"results.":[138],"Furthermore,":[139],"general":[141],"form":[142],"relational":[144,152,160],"is":[146],"proposed.":[147],"Besides":[148],"ODA,":[149],"several":[150],"other":[151],"are":[154],"given.":[155],"those":[159],"have":[162],"strengths":[163],"types":[166],"questions.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2018-10-26T00:00:00"}