{"id":"https://openalex.org/W2740437876","doi":"https://doi.org/10.18653/v1/p17-3008","title":"Segmentation Guided Attention Networks for Visual Question Answering","display_name":"Segmentation Guided Attention Networks for Visual Question Answering","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740437876","doi":"https://doi.org/10.18653/v1/p17-3008","mag":"2740437876"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-3008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-3008","pdf_url":"https://www.aclweb.org/anthology/P17-3008.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Student Research Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-3008.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102320649","display_name":"Vasu Sharma","orcid":"https://orcid.org/0009-0005-4733-3229"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vasu Sharma","raw_affiliation_strings":["Indian Institute of Technology, Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051937475","display_name":"Ankita Bishnu","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankita Bishnu","raw_affiliation_strings":["Indian Institute of Technology, Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010651961","display_name":"Labhesh Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Labhesh Patel","raw_affiliation_strings":["Indian Institute of Technology, Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102320649"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.6372,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78243706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":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":0.9987999796867371,"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":0.9973999857902527,"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/question-answering","display_name":"Question answering","score":0.8232537508010864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7021684050559998},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5861222147941589},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.48598775267601013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4145798683166504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3337985873222351},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32238659262657166},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14581120014190674},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07368865609169006},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07016986608505249}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8232537508010864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021684050559998},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5861222147941589},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.48598775267601013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4145798683166504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3337985873222351},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32238659262657166},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14581120014190674},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07368865609169006},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07016986608505249}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-3008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-3008","pdf_url":"https://www.aclweb.org/anthology/P17-3008.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Student Research Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-3008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-3008","pdf_url":"https://www.aclweb.org/anthology/P17-3008.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL 2017, Student Research Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740437876.pdf","grobid_xml":"https://content.openalex.org/works/W2740437876.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1488163396","https://openalex.org/W1575833922","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1894439495","https://openalex.org/W1903029394","https://openalex.org/W1933349210","https://openalex.org/W2125215748","https://openalex.org/W2131494463","https://openalex.org/W2136462581","https://openalex.org/W2142192571","https://openalex.org/W2189070436","https://openalex.org/W2194775991","https://openalex.org/W2250225488","https://openalex.org/W2340874616","https://openalex.org/W2463565445","https://openalex.org/W2949218037","https://openalex.org/W2949650786","https://openalex.org/W2962749469","https://openalex.org/W2963082528","https://openalex.org/W2963191264","https://openalex.org/W2963954913","https://openalex.org/W2964091467","https://openalex.org/W4308909683"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"In":[0],"this":[1,110,118],"paper":[2],"we":[3,23],"propose":[4],"to":[5,39,50,62,76,78,131],"solve":[6],"the":[7,52,56,60,73,80,88,98,106,114,125,139,154,159],"problem":[8],"of":[9,59,97,105,138],"Visual":[10],"Question":[11],"Answering":[12],"by":[13,32,72,120,158],"using":[14],"a":[15,33,64,93,121],"novel":[16],"segmentation":[17,29],"guided":[18],"attention":[19,42,48,68,147,155],"based":[20],"network":[21,75],"which":[22],"call":[24],"SegAttend-Net.":[25],"We":[26,82,102,142],"use":[27,45],"image":[28,61],"maps,":[30],"generated":[31,146,157],"Fully":[34],"Convolutional":[35],"Deep":[36],"Neural":[37],"Network":[38],"refine":[40],"our":[41,85,145],"maps":[43,49,69,148,156],"and":[44,91,112,133,149],"these":[46],"refined":[47,67],"make":[51],"model":[53,86],"focus":[54],"on":[55,87,109,117],"relevant":[57],"parts":[58],"answer":[63],"question.":[65],"The":[66],"are":[70],"used":[71],"LSTM":[74],"learn":[77],"produce":[79],"answer.":[81],"presently":[83],"train":[84],"visual7W":[89],"dataset":[90,111,119],"do":[92],"category":[94],"wise":[95],"evaluation":[96],"7":[99],"question":[100,126,140],"categories.":[101,141],"achieve":[103],"state":[104],"art":[107],"results":[108],"beat":[113],"previous":[115,160],"benchmark":[116],"1.5%":[122],"margin":[123],"improving":[124],"answering":[127],"accuracy":[128],"from":[129],"54.1%":[130],"55.6%":[132],"demonstrate":[134],"improvements":[135],"in":[136],"each":[137],"also":[143],"visualize":[144],"note":[150],"their":[151],"improvement":[152],"over":[153],"best":[161],"approach.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}