{"id":"https://openalex.org/W4383879019","doi":"https://doi.org/10.1007/s11042-023-15779-y","title":"Multimodal query-guided object localization","display_name":"Multimodal query-guided object localization","publication_year":2023,"publication_date":"2023-07-11","ids":{"openalex":"https://openalex.org/W4383879019","doi":"https://doi.org/10.1007/s11042-023-15779-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-023-15779-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-023-15779-y","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://mpra.ub.uni-muenchen.de/82606/1/MPRA_paper_82606.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019078651","display_name":"Aditay Tripathi","orcid":"https://orcid.org/0000-0002-1667-9623"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditay Tripathi","raw_affiliation_strings":["CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055538076","display_name":"Rajath R Dani","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajath R Dani","raw_affiliation_strings":["CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075621328","display_name":"Anand Mishra","orcid":"https://orcid.org/0000-0002-7806-2557"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anand Mishra","raw_affiliation_strings":["CSE, Indian Institute of Technology, 342037, Jodhpur, Rajasthan, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSE, Indian Institute of Technology, 342037, Jodhpur, Rajasthan, India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101611838","display_name":"Anirban Chakraborty","orcid":"https://orcid.org/0000-0002-6946-9152"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anirban Chakraborty","raw_affiliation_strings":["CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0002-6946-9152","affiliations":[{"raw_affiliation_string":"CDS, Indian Institute of Science, 560012, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101611838"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0953,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36174849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"83","issue":"5","first_page":"14857","last_page":"14881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.9276406168937683},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6225076913833618},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6021678447723389},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5734437108039856},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.5621945858001709},{"id":"https://openalex.org/keywords/laptop","display_name":"Laptop","score":0.5459304451942444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313801169395447},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.528769850730896},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5107653141021729},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5044692754745483},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4592961370944977},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4442504346370697},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4370886981487274},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39955857396125793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9276406168937683},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6225076913833618},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6021678447723389},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5734437108039856},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.5621945858001709},{"id":"https://openalex.org/C2780008327","wikidata":"https://www.wikidata.org/wiki/Q3962","display_name":"Laptop","level":2,"score":0.5459304451942444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313801169395447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.528769850730896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5107653141021729},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5044692754745483},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4592961370944977},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4442504346370697},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4370886981487274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39955857396125793},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11042-023-15779-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-023-15779-y","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai::82606","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/82606/1/MPRA_paper_82606.pdf","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai::82606","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/82606/1/MPRA_paper_82606.pdf","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383879019.pdf"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W318792885","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1651753422","https://openalex.org/W1816973747","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895722194","https://openalex.org/W1932779964","https://openalex.org/W1985975773","https://openalex.org/W2031489346","https://openalex.org/W2037651268","https://openalex.org/W2041658416","https://openalex.org/W2061116763","https://openalex.org/W2066667210","https://openalex.org/W2077395415","https://openalex.org/W2088049833","https://openalex.org/W2096391593","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2122563357","https://openalex.org/W2128543433","https://openalex.org/W2131846894","https://openalex.org/W2153404544","https://openalex.org/W2164699598","https://openalex.org/W2193145675","https://openalex.org/W2240536489","https://openalex.org/W2277195237","https://openalex.org/W2371838123","https://openalex.org/W2466618734","https://openalex.org/W2467281799","https://openalex.org/W2493181180","https://openalex.org/W2519656895","https://openalex.org/W2565639579","https://openalex.org/W2603445054","https://openalex.org/W2604653582","https://openalex.org/W2606473278","https://openalex.org/W2619383789","https://openalex.org/W2752782242","https://openalex.org/W2776402438","https://openalex.org/W2787581402","https://openalex.org/W2792265253","https://openalex.org/W2886970679","https://openalex.org/W2889167066","https://openalex.org/W2890862129","https://openalex.org/W2895403383","https://openalex.org/W2895687296","https://openalex.org/W2898012907","https://openalex.org/W2905544595","https://openalex.org/W2934198733","https://openalex.org/W2950557962","https://openalex.org/W2953092061","https://openalex.org/W2962990451","https://openalex.org/W2963028801","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963093690","https://openalex.org/W2963150697","https://openalex.org/W2963307918","https://openalex.org/W2963351448","https://openalex.org/W2963783181","https://openalex.org/W2963854535","https://openalex.org/W2963936013","https://openalex.org/W2964010806","https://openalex.org/W2964080601","https://openalex.org/W2964138017","https://openalex.org/W2964241181","https://openalex.org/W2978822778","https://openalex.org/W2996583130","https://openalex.org/W2998549611","https://openalex.org/W3037533539","https://openalex.org/W3106250896","https://openalex.org/W3106734767","https://openalex.org/W3125032682","https://openalex.org/W3193171560","https://openalex.org/W4205444062","https://openalex.org/W4312987526","https://openalex.org/W4313067071","https://openalex.org/W6609833400","https://openalex.org/W6635772677","https://openalex.org/W6685518012"],"related_works":["https://openalex.org/W2900382651","https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W1981879262","https://openalex.org/W2045444909","https://openalex.org/W3149739944","https://openalex.org/W2363417484","https://openalex.org/W2392363776"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"demonstrated":[3],"the":[4,85,109,119,130],"effectiveness":[5],"of":[6,10,37,71],"using":[7,115],"hand-drawn":[8,19,116],"sketches":[9,21,117],"objects":[11],"as":[12,127],"queries":[13,61,128],"for":[14,26,43,67],"one-shot":[15],"object":[16,27,56],"localization.":[17],"However,":[18],"crude":[20],"alone":[22],"can":[23],"be":[24,41],"ambiguous":[25],"localization,":[28],"which":[29],"could":[30,40],"result":[31],"in":[32,142],"misidentification,":[33],"e.g.,":[34],"a":[35,38,44,51,68,79],"sketch":[36,60],"laptop":[39],"confused":[42],"sofa.":[45],"To":[46],"overcome":[47],"this,":[48],"we":[49,94],"propose":[50,95],"novel":[52],"multimodal":[53],"approach":[54,77],"to":[55,89,108,139],"localization":[57],"that":[58,83,102],"combines":[59],"with":[62,106],"linguistic":[63],"category":[64],"definitions,":[65],"allowing":[66],"better":[69],"representation":[70],"visual":[72],"and":[73,123,134,145],"semantic":[74],"cues.":[75],"Our":[76],"employs":[78],"cross-modal":[80],"attention":[81],"scheme":[82],"guides":[84],"region":[86],"proposal":[87,99],"network":[88],"obtain":[90],"relevant":[91],"proposals.":[92],"Further,":[93],"an":[96],"orthogonal":[97],"projection-based":[98],"scoring":[100],"technique":[101],"effectively":[103],"ranks":[104],"proposals":[105],"respect":[107],"query.":[110],"We":[111],"evaluated":[112],"our":[113],"method":[114],"from":[118,125],"\u2018Quick,":[120],"Draw!\u2019":[121],"dataset":[122],"glosses":[124],"\u2018WordNet\u2019":[126],"on":[129],"widely-used":[131],"MS-COCO":[132],"dataset,":[133],"achieve":[135],"superior":[136],"performance":[137],"compared":[138],"related":[140],"baselines":[141],"both":[143],"open-":[144],"closed-set":[146],"settings.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}