{"id":"https://openalex.org/W3207547653","doi":"https://doi.org/10.1145/3462244.3479904","title":"A Contrastive Learning Approach for Compositional Zero-Shot Learning","display_name":"A Contrastive Learning Approach for Compositional Zero-Shot Learning","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207547653","doi":"https://doi.org/10.1145/3462244.3479904","mag":"3207547653"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3479904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5105369758","display_name":"Muhammad Umer Anwaar","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammad Umer Anwaar","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054085787","display_name":"Rayyan Ahmad Khan","orcid":"https://orcid.org/0000-0002-1860-0464"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rayyan Ahmad Khan","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042360856","display_name":"Zhihui Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhihui Pan","raw_affiliation_strings":["Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055847035","display_name":"Martin Kleinsteuber","orcid":"https://orcid.org/0000-0002-4323-9260"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Kleinsteuber","raw_affiliation_strings":["Mercateo AG, Germany and Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Mercateo AG, Germany and Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105369758"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76132036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"42"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"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":0.7603739500045776},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7558498382568359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6407682299613953},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6367215514183044},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5660517811775208},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5660433769226074},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5400752425193787},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5334330797195435},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44892004132270813},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4421881139278412},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4166503846645355},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38359755277633667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3808830976486206},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34994351863861084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33425405621528625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3338545560836792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603739500045776},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7558498382568359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407682299613953},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6367215514183044},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5660517811775208},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5660433769226074},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5400752425193787},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5334330797195435},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44892004132270813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4421881139278412},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4166503846645355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38359755277633667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3808830976486206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34994351863861084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33425405621528625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3338545560836792},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3462244.3479904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1599238028","https://openalex.org/W1834627138","https://openalex.org/W1948251820","https://openalex.org/W2098411764","https://openalex.org/W2108598243","https://openalex.org/W2157423479","https://openalex.org/W2250539671","https://openalex.org/W2479919622","https://openalex.org/W2598634450","https://openalex.org/W2610366607","https://openalex.org/W2735001949","https://openalex.org/W2736809457","https://openalex.org/W2798503981","https://openalex.org/W2842511635","https://openalex.org/W2889167066","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2905544595","https://openalex.org/W2913668833","https://openalex.org/W2940256401","https://openalex.org/W2949823873","https://openalex.org/W2950133940","https://openalex.org/W2963389687","https://openalex.org/W2964121744","https://openalex.org/W2964211610","https://openalex.org/W2970944013","https://openalex.org/W2986385672","https://openalex.org/W2987283559","https://openalex.org/W2989883423","https://openalex.org/W3005680577","https://openalex.org/W3014456758","https://openalex.org/W3091546937","https://openalex.org/W3119510203","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W4389832810","https://openalex.org/W3133533225"],"abstract_inverted_index":{"An":[0],"object":[1,12],"can":[2],"be":[3,38,49],"in":[4,88],"several":[5],"states.":[6],"For":[7,179],"different":[8,117],"states":[9],"(attributes)":[10],"the":[11,18,24,60,78,82,124,144,149,158,180,186],"could":[13],"look":[14],"dramatically":[15],"different.":[16],"Thus,":[17],"smart":[19],"information":[20],"retrieval":[21,182],"systems":[22],"of":[23,81,127,143,160],"future":[25],"need":[26],"to":[27,40,51,84,111],"learn":[28,85,100],"good":[29],"state-object":[30,42,83,161],"representations.":[31],"Such":[32],"a":[33,72,89,94,101],"system":[34],"should":[35],"not":[36],"only":[37],"able":[39,50],"recognize":[41],"compositions":[43],"unseen":[44],"during":[45],"training":[46],"but":[47],"also":[48],"retrieve":[52],"images":[53,107],"based":[54,121],"on":[55,153,157,170,174,191,195],"multi-modal":[56],"(image-text)":[57],"query.":[58],"In":[59,67],"literature,":[61],"these":[62],"tasks":[63],"are":[64],"treated":[65],"separately.":[66],"this":[68],"work,":[69],"we":[70],"propose":[71],"unified":[73],"model,":[74],"ContraNet,":[75],"which":[76,129],"leverages":[77],"rich":[79],"semantics":[80],"multimodal":[86,102],"representation":[87,103,126],"contrastive":[90],"manner.":[91],"We":[92],"adopt":[93],"deep":[95],"metric":[96],"learning":[97,142],"approach":[98,147],"and":[99,108,114,166,172,193],"by":[104,189],"pulling":[105],"similar":[106],"texts":[109],"closer":[110],"each":[112],"other":[113],"pushing":[115],"apart":[116],"ones.":[118],"Our":[119,146],"autoencoder":[120],"model":[122],"learns":[123],"text-aware":[125],"image":[128,181],"is":[130],"suitable":[131],"for":[132,141],"both":[133],"tasks.":[134],"The":[135],"reconstruction":[136],"losses":[137],"provide":[138],"additional":[139],"regularization":[140],"representation.":[145],"outperforms":[148],"state-of-the-art":[150],"(SOTA)":[151],"methods":[152],"widely-used":[154],"benchmarks.":[155],"Specifically,":[156],"task":[159],"composition,":[162],"ContraNet":[163,184],"achieves":[164],"8.7%":[165],"8.1%":[167],"performance":[168,188],"gain":[169],"UT-Zappos":[171],"MIT-States":[173,192],"best":[175],"HM":[176],"metric,":[177],"respectively.":[178],"task,":[183],"surpasses":[185],"SOTA":[187],"4%":[190],"5.3%":[194],"Fashion200k.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}