{"id":"https://openalex.org/W2949693283","doi":"https://doi.org/10.18653/v1/p19-1349","title":"Multi-grained Attention with Object-level Grounding for Visual Question Answering","display_name":"Multi-grained Attention with Object-level Grounding for Visual Question Answering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949693283","doi":"https://doi.org/10.18653/v1/p19-1349","mag":"2949693283"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1349","pdf_url":"https://www.aclweb.org/anthology/P19-1349.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1349.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036361611","display_name":"Pingping Huang","orcid":"https://orcid.org/0000-0003-3627-6335"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pingping Huang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859055","display_name":"Jianhui Huang","orcid":"https://orcid.org/0000-0002-5614-1019"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Huang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011601269","display_name":"Yuqing Guo","orcid":"https://orcid.org/0000-0001-5232-0629"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Guo","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102955887","display_name":"Min Qiao","orcid":"https://orcid.org/0000-0002-2168-0485"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Qiao","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000312734","display_name":"Yong Zhu","orcid":"https://orcid.org/0000-0002-9806-1965"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036361611"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.0244,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89665197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3595","last_page":"3600"},"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":0.9991000294685364,"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":0.9976000189781189,"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":0.8128536939620972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8065229058265686},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6809254884719849},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6659097671508789},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.6355165243148804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6144154667854309},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.590691328048706},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5873859524726868},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5185763835906982},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5093649625778198},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4659406244754791},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4653547406196594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3489767909049988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3225570321083069},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.14311820268630981},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0699496865272522},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06729918718338013}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8128536939620972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065229058265686},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6809254884719849},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6659097671508789},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.6355165243148804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144154667854309},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.590691328048706},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5873859524726868},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5185763835906982},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5093649625778198},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4659406244754791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4653547406196594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3489767909049988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3225570321083069},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.14311820268630981},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0699496865272522},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06729918718338013},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1349","pdf_url":"https://www.aclweb.org/anthology/P19-1349.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1349","pdf_url":"https://www.aclweb.org/anthology/P19-1349.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 the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949693283.pdf","grobid_xml":"https://content.openalex.org/works/W2949693283.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1603133675","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2142192571","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2412400526","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2560920409","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2787560479","https://openalex.org/W2962739339","https://openalex.org/W2963383024","https://openalex.org/W2963954913","https://openalex.org/W2964121744","https://openalex.org/W2964345214","https://openalex.org/W3016211260"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2964061310","https://openalex.org/W2231285690","https://openalex.org/W2963477107","https://openalex.org/W3093385053","https://openalex.org/W4390091918","https://openalex.org/W2553418567","https://openalex.org/W4389682534","https://openalex.org/W3045060014"],"abstract_inverted_index":{"Attention":[0],"mechanisms":[1],"are":[2],"widely":[3],"used":[4],"in":[5],"Visual":[6],"Question":[7],"Answering":[8],"(VQA)":[9],"to":[10,16,34,65,96],"search":[11],"for":[12],"visual":[13],"clues":[14],"related":[15],"the":[17,66,71,74,85,101,105],"question.":[18],"Most":[19],"approaches":[20],"train":[21],"attention":[22,51,63,76,87],"models":[23],"from":[24],"a":[25,49,97],"coarsegrained":[26],"association":[27],"between":[28],"sentences":[29],"and":[30,103],"images,":[31],"which":[32],"tends":[33],"fail":[35],"on":[36,70],"small":[37],"objects":[38,107],"or":[39],"uncommon":[40],"concepts.":[41],"To":[42],"address":[43],"this":[44,46],"problem,":[45],"paper":[47],"proposes":[48],"multi-grained":[50,75],"method.":[52],"It":[53],"learns":[54],"explicit":[55],"wordobject":[56],"correspondence":[57],"by":[58],"two":[59],"types":[60],"of":[61,92,100],"wordlevel":[62],"complementary":[64],"sentenceimage":[67],"association.":[68],"Evaluated":[69],"VQA":[72],"benchmark,":[73],"model":[77],"achieves":[78],"competitive":[79],"performance":[80],"with":[81],"stateof-the-art":[82],"models.":[83],"And":[84],"visualized":[86],"maps":[88],"demonstrate":[89],"that":[90],"addition":[91],"objectlevel":[93],"groundings":[94],"leads":[95],"better":[98],"understanding":[99],"images":[102],"locates":[104],"attended":[106],"more":[108],"precisely.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}