{"id":"https://openalex.org/W2256357568","doi":null,"title":"Deep Compositional Question Answering with Neural Module Networks","display_name":"Deep Compositional Question Answering with Neural Module Networks","publication_year":2015,"publication_date":"2015-11-09","ids":{"openalex":"https://openalex.org/W2256357568","mag":"2256357568"},"language":"en","primary_location":{"id":"mag:2256357568","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1511.02799v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1511.02799v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070829652","display_name":"Jacob Andreas","orcid":"https://orcid.org/0000-0002-3141-5845","observed_orcids":["https://orcid.org/0000-0002-3141-5845"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacob Andreas","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3141-5845","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024481540","display_name":"Marcus Rohrbach","orcid":"https://orcid.org/0000-0001-5908-7751","observed_orcids":["https://orcid.org/0000-0001-5908-7751"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Rohrbach","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5908-7751","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5453-8533","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902","observed_orcids":["https://orcid.org/0000-0002-8881-1902","https://orcid.org/0009-0002-5983-2904"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Klein","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8881-1902","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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":0.9961000084877014,"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":0.0007999999797903001,"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":0.00039999998989515007,"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":0.9490000009536743},{"id":"https://openalex.org/keywords/question-decomposition","display_name":"question decomposition","score":0.5929999947547913},{"id":"https://openalex.org/keywords/modular-networks","display_name":"modular networks","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8983737230300903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780084609985352},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.735055685043335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7168378829956055},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6362926363945007},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6042922139167786},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5731446743011475},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5676147937774658},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48437365889549255},{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.42281368374824524},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.4112702012062073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10695025324821472},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2256357568","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1511.02799v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:2256357568","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1511.02799v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1514535095","https://openalex.org/W1525961042","https://openalex.org/W1575833922","https://openalex.org/W1632114991","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1902568950","https://openalex.org/W1905882502","https://openalex.org/W1923162067","https://openalex.org/W1983927101","https://openalex.org/W2048343491","https://openalex.org/W2064675550","https://openalex.org/W2094061585","https://openalex.org/W2097606805","https://openalex.org/W2102605133","https://openalex.org/W2110485445","https://openalex.org/W2112796928","https://openalex.org/W2112912048","https://openalex.org/W2133280805","https://openalex.org/W2142192571","https://openalex.org/W2159149613","https://openalex.org/W2173051530","https://openalex.org/W2186283982","https://openalex.org/W2189070436","https://openalex.org/W2202226326","https://openalex.org/W2214429195","https://openalex.org/W2247513039","https://openalex.org/W2250318122","https://openalex.org/W2272482229","https://openalex.org/W2396147015","https://openalex.org/W2504108613","https://openalex.org/W2563399268","https://openalex.org/W2951183276","https://openalex.org/W2951619830","https://openalex.org/W2963143606","https://openalex.org/W2963672682","https://openalex.org/W2963735856","https://openalex.org/W2964199361","https://openalex.org/W3037881859"],"related_works":["https://openalex.org/W2416885651","https://openalex.org/W2963224792","https://openalex.org/W4226199031","https://openalex.org/W2892051617","https://openalex.org/W2230472587","https://openalex.org/W2963722138","https://openalex.org/W3105009590","https://openalex.org/W2391839782","https://openalex.org/W7151771960","https://openalex.org/W2904311512"],"abstract_inverted_index":{"Visual":[0],"question":[1,8,70,115],"answering":[2],"is":[3,11,21,26],"fundamentally":[4],"compositional":[5,43],"in":[6],"nature---a":[7],"like":[9,18],"where":[10,25],"the":[12,22,27,35,42,122],"dog?":[13,23],"shares":[14],"substructure":[15],"with":[16],"questions":[17,75,133],"what":[19],"color":[20],"and":[24,41,54,80,127],"cat?":[28],"This":[29],"paper":[30],"seeks":[31],"to":[32,84],"simultaneously":[33],"exploit":[34],"representational":[36],"capacity":[37],"of":[38,46,62,131],"deep":[39,67],"networks":[40,68,88,101],"linguistic":[44,78],"structure":[45],"questions.":[47],"We":[48,105],"describe":[49],"a":[50,128],"procedure":[51],"for":[52,69,92,113],"constructing":[53],"learning":[55],"*neural":[56],"module":[57],"networks*,":[58],"which":[59],"compose":[60],"collections":[61],"jointly-trained":[63],"neural":[64],"modules":[65],"into":[66,76],"answering.":[71],"Our":[72],"approach":[73,108],"decomposes":[74],"their":[77],"substructures,":[79],"uses":[81],"these":[82],"structures":[83],"dynamically":[85],"instantiate":[86],"modular":[87],"(with":[89],"reusable":[90],"components":[91],"recognizing":[93],"dogs,":[94],"classifying":[95],"colors,":[96],"etc.).":[97],"The":[98],"resulting":[99],"compound":[100],"are":[102],"jointly":[103],"trained.":[104],"evaluate":[106],"our":[107],"on":[109,120],"two":[110],"challenging":[111],"datasets":[112],"visual":[114],"answering,":[116],"achieving":[117],"state-of-the-art":[118],"results":[119],"both":[121],"VQA":[123],"natural":[124],"image":[125],"dataset":[126,130],"new":[129],"complex":[132],"about":[134],"abstract":[135],"shapes.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}