{"id":"https://openalex.org/W3180392817","doi":"https://doi.org/10.1007/978-3-030-88361-4_7","title":"Graphhopper: Multi-hop Scene Graph Reasoning for Visual Question Answering","display_name":"Graphhopper: Multi-hop Scene Graph Reasoning for Visual Question Answering","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3180392817","doi":"https://doi.org/10.1007/978-3-030-88361-4_7","mag":"3180392817"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-88361-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047843370","display_name":"Rajat Koner","orcid":"https://orcid.org/0000-0003-3441-8192"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Rajat Koner","raw_affiliation_strings":["Ludwig Maximilian University of Munich, Munich, Germany","Ludwig Maximilian University of Munich, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455129","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-1230-4007"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]},{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Ludwig Maximilian University of Munich, Munich, Germany","Siemens AG, Munich, Germany","Ludwig Maximilian University of Munich, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006443017","display_name":"Marcel Hildebrandt","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]},{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcel Hildebrandt","raw_affiliation_strings":["Ludwig Maximilian University of Munich, Munich, Germany","Siemens AG, Munich, Germany","Ludwig Maximilian University of Munich, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089494843","display_name":"Deepan Das","orcid":"https://orcid.org/0000-0001-8910-5973"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Deepan Das","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074808403","display_name":"Volker Tresp","orcid":"https://orcid.org/0000-0001-9428-3686"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]},{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Tresp","raw_affiliation_strings":["Ludwig Maximilian University of Munich, Munich, Germany","Siemens AG, Munich, Germany","Ludwig Maximilian University of Munich, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Siemens AG, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Ludwig Maximilian University of Munich, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074504351","display_name":"Stephan G\u00fcnnemann","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stephan G\u00fcnnemann","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047843370"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.7019,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68925023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"127"},"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":0.9973999857902527,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8182700872421265},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7839303016662598},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6394801735877991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239796280860901},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48258769512176514},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4630472958087921},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4510176181793213},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33081334829330444},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1914381980895996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182700872421265},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7839303016662598},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6394801735877991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239796280860901},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48258769512176514},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4630472958087921},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4510176181793213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33081334829330444},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1914381980895996},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-88361-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2107.06325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.06325","pdf_url":"https://arxiv.org/pdf/2107.06325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3180392817","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2107.06325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.06325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.06325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-88361-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-88361-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-88361-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3180392817.pdf","grobid_xml":"https://content.openalex.org/works/W3180392817.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1529533208","https://openalex.org/W1533861849","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2077069816","https://openalex.org/W2095705004","https://openalex.org/W2119717200","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2519887557","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2766453196","https://openalex.org/W2769099080","https://openalex.org/W2786209943","https://openalex.org/W2899771611","https://openalex.org/W2916723116","https://openalex.org/W2950104027","https://openalex.org/W2953388933","https://openalex.org/W2962779575","https://openalex.org/W2962886429","https://openalex.org/W2962933067","https://openalex.org/W2963150162","https://openalex.org/W2963224792","https://openalex.org/W2963403868","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964172232","https://openalex.org/W2969679616","https://openalex.org/W2979729166","https://openalex.org/W2987123286","https://openalex.org/W2990397898","https://openalex.org/W2997463623","https://openalex.org/W2998269860","https://openalex.org/W3016897814","https://openalex.org/W3033912416","https://openalex.org/W3035017890","https://openalex.org/W3035145964","https://openalex.org/W3035688398","https://openalex.org/W3175630421","https://openalex.org/W6600075759","https://openalex.org/W6605520847","https://openalex.org/W6739901393","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W3203581965","https://openalex.org/W3119150707","https://openalex.org/W3109250529","https://openalex.org/W3046003264","https://openalex.org/W3034943799","https://openalex.org/W2963532541","https://openalex.org/W3031771644","https://openalex.org/W3205821239","https://openalex.org/W3160140554","https://openalex.org/W3154933149","https://openalex.org/W3004349648","https://openalex.org/W3043670582","https://openalex.org/W2997344006","https://openalex.org/W3131567567","https://openalex.org/W3205857725","https://openalex.org/W3205632231","https://openalex.org/W2947385066","https://openalex.org/W3035497100","https://openalex.org/W2996984511","https://openalex.org/W2965433310"],"abstract_inverted_index":{"Abstract":[0],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"is":[5,42,83,131],"concerned":[6],"with":[7,32,183],"answering":[8],"free-form":[9],"questions":[10],"about":[11],"an":[12,43,158],"image.":[13],"Since":[14],"it":[15,31,41],"requires":[16,47],"a":[17,61,102,107,127,137,213],"deep":[18],"semantic":[19,97],"and":[20,26,46,54,75,95,98,122,171,207],"linguistic":[21],"understanding":[22],"of":[23],"the":[24,27,39,66,92,112,115,141,151,162],"question":[25],"ability":[28],"to":[29,133,145],"associate":[30],"various":[33],"objects":[34,113],"that":[35,64,110,179,194],"are":[36,150],"present":[37],"in":[38,114,136],"image,":[40,116],"ambitious":[44],"task":[45,67],"multi-modal":[48],"reasoning":[49,89,147,201],"from":[50],"both":[51,168,204],"computer":[52,73],"vision":[53],"natural":[55,76],"language":[56,77],"processing.":[57],"We":[58,156],"propose":[59],"Graphhopper,":[60],"novel":[62],"method":[63,82],"approaches":[65],"by":[68,212],"integrating":[69],"knowledge":[70],"graph":[71,109,144,200],"reasoning,":[72],"vision,":[74],"processing":[78],"techniques.":[79],"Concretely,":[80],"our":[81],"based":[84,90,166],"on":[85,91,161,167,186,203],"performing":[86],"context-driven,":[87],"sequential":[88],"scene":[93,108,143,174,189,199,210],"entities":[94],"their":[96,120,123],"spatial":[99],"relationships.":[100,125],"As":[101],"first":[103],"step,":[104],"we":[105,180,192],"derive":[106],"describes":[111],"as":[117,119],"well":[118],"attributes":[121],"mutual":[124],"Subsequently,":[126],"reinforcement":[128],"learning":[129],"agent":[130],"trained":[132],"autonomously":[134],"navigate":[135],"multi-hop":[138],"manner":[139],"over":[140],"extracted":[142],"generate":[146],"paths,":[148],"which":[149],"basis":[152],"for":[153],"deriving":[154],"answers.":[155],"conduct":[157],"experimental":[159],"study":[160],"challenging":[163],"dataset":[164],"GQA,":[165],"manually":[169,187,205],"curated":[170,188,206],"automatically":[172,208],"generated":[173,209],"graphs.":[175,190],"Our":[176],"results":[177],"show":[178],"keep":[181],"up":[182],"human":[184],"performance":[185],"Moreover,":[191],"find":[193],"Graphhopper":[195],"outperforms":[196],"another":[197],"state-of-the-art":[198],"model":[202],"graphs":[211],"significant":[214],"margin.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}