{"id":"https://openalex.org/W4292829113","doi":"https://doi.org/10.1109/cvprw56347.2022.00505","title":"Semantically Grounded Visual Embeddings for Zero-Shot Learning","display_name":"Semantically Grounded Visual Embeddings for Zero-Shot Learning","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4292829113","doi":"https://doi.org/10.1109/cvprw56347.2022.00505"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw56347.2022.00505","doi":"https://doi.org/10.1109/cvprw56347.2022.00505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw56347.2022.00505","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.00577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016485532","display_name":"Shah Nawaz","orcid":"https://orcid.org/0000-0002-7715-4409","observed_orcids":["https://orcid.org/0000-0002-7715-4409"]},"institutions":[{"id":"https://openalex.org/I2801876189","display_name":"Deutsches Elektronen-Synchrotron DESY","ror":"https://ror.org/01js2sh04","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2801876189"]},{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["DE","IT"],"is_corresponding":false,"raw_author_name":"Shah Nawaz","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)","Deutsches Elektronen-Synchrotron (DESY)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Deutsches Elektronen-Synchrotron (DESY)","institution_ids":["https://openalex.org/I2801876189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043110801","display_name":"Jacopo Cavazza","orcid":"https://orcid.org/0000-0002-4912-6961","observed_orcids":["https://orcid.org/0000-0002-4912-6961"]},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Jacopo Cavazza","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046971342","display_name":"Alessio Del Bue","orcid":"https://orcid.org/0000-0002-2262-4872","observed_orcids":["https://orcid.org/0000-0002-2262-4872"]},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Del Bue","raw_affiliation_strings":["Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)","Visual Geometry & Modelling (VGM), Istituto Italiano di Tecnologia (IIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia (IIT),Pattern Analysis & Computer Vision (PAVIS)","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Visual Geometry & Modelling (VGM), Istituto Italiano di Tecnologia (IIT)","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7334,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72210014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4588","last_page":"4598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8363999724388123,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8363999724388123,"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":0.15449999272823334,"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":0.002899999963119626,"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/zero-shot-learning","display_name":"zero-shot learning","score":0.9829999804496765},{"id":"https://openalex.org/keywords/image-embeddings","display_name":"image embeddings","score":0.8370000123977661},{"id":"https://openalex.org/keywords/semantic-grounding","display_name":"semantic grounding","score":0.8349999785423279},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.781000018119812},{"id":"https://openalex.org/keywords/two-stream-network","display_name":"two-stream network","score":0.9580000042915344},{"id":"https://openalex.org/keywords/proxy-tasks","display_name":"proxy tasks","score":0.6790000200271606},{"id":"https://openalex.org/keywords/image-characteristics","display_name":"image characteristics","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863444685935974},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7564122080802917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408083200454712},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5125293731689453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4835905432701111},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46816015243530273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.455181360244751},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4469067454338074},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41295087337493896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39315178990364075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32124119997024536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvprw56347.2022.00505","doi":"https://doi.org/10.1109/cvprw56347.2022.00505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw56347.2022.00505","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.00577","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.00577","pdf_url":"https://arxiv.org/pdf/2201.00577","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2201.00577","doi":"https://doi.org/10.48550/arxiv.2201.00577","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2201.00577","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.00577","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.00577","pdf_url":"https://arxiv.org/pdf/2201.00577","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4292829113.pdf","grobid_xml":"https://content.openalex.org/works/W4292829113.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1933349210","https://openalex.org/W2044913453","https://openalex.org/W2098411764","https://openalex.org/W2123024445","https://openalex.org/W2150856297","https://openalex.org/W2153579005","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2289084343","https://openalex.org/W2334493732","https://openalex.org/W2398118205","https://openalex.org/W2533598788","https://openalex.org/W2611632661","https://openalex.org/W2619383789","https://openalex.org/W2737631482","https://openalex.org/W2748618181","https://openalex.org/W2774267535","https://openalex.org/W2786797739","https://openalex.org/W2883124384","https://openalex.org/W2886641317","https://openalex.org/W2887567284","https://openalex.org/W2896457183","https://openalex.org/W2899867883","https://openalex.org/W2902002028","https://openalex.org/W2905548899","https://openalex.org/W2924476266","https://openalex.org/W2928559975","https://openalex.org/W2962689421","https://openalex.org/W2962716320","https://openalex.org/W2963341956","https://openalex.org/W2963389687","https://openalex.org/W2963499153","https://openalex.org/W2963846885","https://openalex.org/W2963960318","https://openalex.org/W2964162033","https://openalex.org/W2968124245","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2971589527","https://openalex.org/W2972244714","https://openalex.org/W2990947836","https://openalex.org/W2998708909","https://openalex.org/W3000538487","https://openalex.org/W3001555892","https://openalex.org/W3002728158","https://openalex.org/W3034730995","https://openalex.org/W3035297600","https://openalex.org/W3090449556","https://openalex.org/W3109728025","https://openalex.org/W3143107425","https://openalex.org/W6600609147"],"related_works":["https://openalex.org/W4313009154","https://openalex.org/W4380685865","https://openalex.org/W3194611307","https://openalex.org/W3127987785","https://openalex.org/W4393866007","https://openalex.org/W7098329068","https://openalex.org/W2963955422","https://openalex.org/W2592773426","https://openalex.org/W93016980","https://openalex.org/W2962791511"],"abstract_inverted_index":{"Zero-shot":[0],"learning":[1,30,104],"methods":[2,117],"rely":[3],"on":[4,72,107,122,125,130,133],"fixed":[5],"visual":[6,40,58],"and":[7,14,41,56,65,82,127],"semantic":[8,47,95],"embeddings,":[9],"extracted":[10],"from":[11],"independent":[12],"vision":[13],"language":[15],"models,":[16],"both":[17,119],"pre-trained":[18],"for":[19,102],"other":[20],"large-scale":[21],"tasks.":[22],"This":[23],"is":[24,105],"a":[25,62,69,73],"weakness":[26],"of":[27,114],"current":[28],"zero-shot":[29,103,135],"frameworks":[31],"as":[32],"such":[33],"disjoint":[34],"embeddings":[35,101],"fail":[36],"to":[37,44,52,92],"adequately":[38],"associate":[39],"textual":[42,83],"information":[43,59],"their":[45],"shared":[46],"content.":[48],"Therefore,":[49],"we":[50,88],"propose":[51],"learn":[53],"semantically":[54],"grounded":[55,94],"enriched":[57],"by":[60,86],"computing":[61],"joint":[63,100],"image":[64,81],"text":[66],"model":[67],"with":[68],"two-stream":[70],"network":[71],"proxy":[74],"task.":[75],"To":[76],"improve":[77],"this":[78],"alignment":[79],"between":[80],"representations,":[84],"provided":[85],"attributes,":[87],"leverage":[89],"ancillary":[90],"captions":[91],"provide":[93],"information.":[96],"Our":[97],"method,":[98],"dubbed":[99],"evaluated":[106],"several":[108],"benchmark":[109],"datasets,":[110],"improving":[111],"the":[112],"performance":[113],"existing":[115],"state-of-the-art":[116],"in":[118],"standard":[120],"(+1.6%":[121],"aPY,":[123],"+2.6%":[124],"FLO)":[126],"generalized":[128],"(+2.1%":[129],"AWA2,":[131],"+2.2%":[132],"CUB)":[134],"recognition.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-24T00:00:00"}