{"id":"https://openalex.org/W4280652284","doi":"https://doi.org/10.1109/tip.2022.3173815","title":"Augmented Multimodality Fusion for Generalized Zero-Shot Sketch-Based Visual Retrieval","display_name":"Augmented Multimodality Fusion for Generalized Zero-Shot Sketch-Based Visual Retrieval","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4280652284","doi":"https://doi.org/10.1109/tip.2022.3173815","pmid":"https://pubmed.ncbi.nlm.nih.gov/35576409"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3173815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3173815","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025221749","display_name":"Taotao Jing","orcid":"https://orcid.org/0000-0001-7597-6532"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taotao Jing","raw_affiliation_strings":["Department of Computer Science, Tulane University, New Orleans, LA, USA","Department of Computer Science, Tulane University, New Orleans, LA 70118, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051051967","display_name":"Haifeng Xia","orcid":"https://orcid.org/0000-0002-3317-0490"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haifeng Xia","raw_affiliation_strings":["Department of Computer Science, Tulane University, New Orleans, LA, USA","Department of Computer Science, Tulane University, New Orleans, LA 70118, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085659523","display_name":"Jihun Hamm","orcid":"https://orcid.org/0000-0002-0680-0901"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihun Hamm","raw_affiliation_strings":["Department of Computer Science, Tulane University, New Orleans, LA, USA","Department of Computer Science, Tulane University, New Orleans, LA 70118, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083458247","display_name":"Zhengming Ding","orcid":"https://orcid.org/0000-0002-6994-5278"},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengming Ding","raw_affiliation_strings":["Department of Computer Science, Tulane University, New Orleans, LA, USA","Department of Computer Science, Tulane University, New Orleans, LA 70118, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA, USA","institution_ids":["https://openalex.org/I114832834"]},{"raw_affiliation_string":"Department of Computer Science, Tulane University, New Orleans, LA 70118, USA","institution_ids":["https://openalex.org/I114832834"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025221749"],"corresponding_institution_ids":["https://openalex.org/I114832834"],"apc_list":null,"apc_paid":null,"fwci":2.4182,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90226993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"3657","last_page":"3668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8075430393218994},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.725790798664093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5822660326957703},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5517192482948303},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5278836488723755},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45245063304901123},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43087196350097656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39283034205436707},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2900850772857666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12008535861968994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10634329915046692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075430393218994},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.725790798664093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5822660326957703},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5517192482948303},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5278836488723755},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45245063304901123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43087196350097656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39283034205436707},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2900850772857666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12008535861968994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10634329915046692},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3173815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3173815","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:35576409","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35576409","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"},{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W43954826","https://openalex.org/W141352744","https://openalex.org/W1686810756","https://openalex.org/W1892078565","https://openalex.org/W1972420097","https://openalex.org/W1974647172","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2466618734","https://openalex.org/W2467281799","https://openalex.org/W2471581439","https://openalex.org/W2603445054","https://openalex.org/W2885402090","https://openalex.org/W2891193211","https://openalex.org/W2895716796","https://openalex.org/W2900953995","https://openalex.org/W2922521335","https://openalex.org/W2962747232","https://openalex.org/W2962990451","https://openalex.org/W2981720610","https://openalex.org/W2988772405","https://openalex.org/W2994818707","https://openalex.org/W2997310315","https://openalex.org/W2997645545","https://openalex.org/W2997918867","https://openalex.org/W2999606372","https://openalex.org/W3000538487","https://openalex.org/W3007443315","https://openalex.org/W3025895701","https://openalex.org/W3026458074","https://openalex.org/W3034277922","https://openalex.org/W3035705029","https://openalex.org/W3045735302","https://openalex.org/W3045735664","https://openalex.org/W3048489162","https://openalex.org/W3057906563","https://openalex.org/W3085694362","https://openalex.org/W3089741414","https://openalex.org/W3093349296","https://openalex.org/W3110214837","https://openalex.org/W3118617077","https://openalex.org/W3120312331","https://openalex.org/W3121601851","https://openalex.org/W3158065459","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3192443982","https://openalex.org/W3198918259","https://openalex.org/W3203055845","https://openalex.org/W3203460211","https://openalex.org/W3207182362","https://openalex.org/W3211258519","https://openalex.org/W3216759837","https://openalex.org/W4229482837","https://openalex.org/W6637373629","https://openalex.org/W6639480849","https://openalex.org/W6785403945"],"related_works":["https://openalex.org/W2500982737","https://openalex.org/W2305650600","https://openalex.org/W2106795979","https://openalex.org/W2551466753","https://openalex.org/W3097853387","https://openalex.org/W3165136521","https://openalex.org/W1926504679","https://openalex.org/W4298852638","https://openalex.org/W2353314619","https://openalex.org/W3173660168"],"abstract_inverted_index":{"Zero-shot":[0],"sketch-based":[1,16,71],"image":[2,72],"retrieval":[3,17,73],"(ZS-SBIR)":[4],"has":[5],"attracted":[6],"great":[7],"attention":[8],"recently,":[9],"due":[10],"to":[11,94,98,119,132,145,168,194],"the":[12,22,34,45,51,77,125,130,134,147,159,196,232,236,239],"potential":[13],"application":[14],"of":[15,24,79,161,238],"under":[18,41],"zero-shot":[19,70],"scenarios,":[20],"where":[21],"categories":[23],"query":[25,52],"sketches":[26,53],"and":[27,47,54,60,116,152,172,189,202,231],"gallery":[28,55],"photos":[29,56],"are":[30,183,208],"not":[31],"observed":[32],"in":[33,113,154,199],"training":[35,126],"stage.":[36],"However,":[37],"it":[38],"is":[39,66,76,111,129,143,248],"still":[40],"insufficient":[42],"exploration":[43],"for":[44,185,222],"general":[46],"practical":[48],"scenario":[49],"when":[50],"contain":[57],"both":[58,114,170,200],"seen":[59,96],"unseen":[61,123],"categories.":[62],"Such":[63],"a":[64,87,103,138,217],"problem":[65],"defined":[67],"as":[68,214,216],"generalized":[69],"(GZS-SBIR),":[74],"which":[75,128,192],"focus":[78],"this":[80,83],"work.":[81],"To":[82,157],"end,":[84],"we":[85,164],"propose":[86],"novel":[88,104,121],"Augmented":[89],"Multi-modality":[90],"Fusion":[91],"(AMF)":[92],"framework":[93],"generalize":[95],"concepts":[97],"unobserved":[99],"ones":[100],"efficiently.":[101],"Specifically,":[102],"knowledge":[105,122],"discovery":[106],"module":[107,142],"named":[108],"cross-domain":[109,148,197],"augmentation":[110],"designed":[112,221],"visual":[115,155,171,201],"semantic":[117,173,203],"space":[118],"mimic":[120],"from":[124,224],"stage,":[127],"key":[131],"handling":[133],"GZS-SBIR":[135,223],"challenge.":[136],"Moreover,":[137],"triplet":[139],"domain":[140,187],"alignment":[141,198],"proposed":[144,240],"couple":[146],"distribution":[149],"between":[150],"photo":[151],"sketch":[153],"space.":[156,205],"enhance":[158],"robustness":[160],"our":[162],"model,":[163],"explore":[165],"embedding":[166],"propagation":[167],"refine":[169],"features":[174],"by":[175],"removing":[176],"undesired":[177],"noise.":[178],"Eventually,":[179],"visual-semantic":[180],"fusion":[181],"representations":[182],"concatenated":[184],"further":[186],"discrimination":[188],"task-specific":[190],"recognition,":[191],"tend":[193],"trigger":[195],"feature":[204],"Experimental":[206],"evaluations":[207],"conducted":[209],"on":[210],"popular":[211],"ZS-SBIR":[212],"benchmarks":[213],"well":[215],"new":[218],"evaluation":[219],"protocol":[220],"DomainNet":[225],"dataset":[226],"with":[227],"more":[228],"diverse":[229],"sub-domains,":[230],"promising":[233],"results":[234],"demonstrate":[235],"superiority":[237],"solution":[241],"over":[242],"other":[243],"baselines.":[244],"The":[245],"source":[246],"code":[247],"available":[249],"at":[250],"https://github.com/scottjingtt/AMF_GZS_SBIR.git.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}