{"id":"https://openalex.org/W4324296295","doi":"https://doi.org/10.1145/3571600.3571653","title":"ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations","display_name":"ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4324296295","doi":"https://doi.org/10.1145/3571600.3571653"},"language":"en","primary_location":{"id":"doi:10.1145/3571600.3571653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3571600.3571653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"preprint","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/A5079705040","display_name":"Chanda Grover Kamra","orcid":"https://orcid.org/0000-0001-6038-8092"},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Chanda Grover","raw_affiliation_strings":["Ashoka University, India"],"affiliations":[{"raw_affiliation_string":"Ashoka University, India","institution_ids":["https://openalex.org/I347237974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020425550","display_name":"Indra Deep Mastan","orcid":"https://orcid.org/0000-0001-5033-9561"},"institutions":[{"id":"https://openalex.org/I33552525","display_name":"LNM Institute of Information Technology","ror":"https://ror.org/03jp7rg16","country_code":"IN","type":"education","lineage":["https://openalex.org/I33552525"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Indra Deep Mastan","raw_affiliation_strings":["The LNM Institute of Information Technology Jaipur, India"],"affiliations":[{"raw_affiliation_string":"The LNM Institute of Information Technology Jaipur, India","institution_ids":["https://openalex.org/I33552525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073351462","display_name":"Debayan Gupta","orcid":"https://orcid.org/0000-0002-4457-1556"},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debayan Gupta","raw_affiliation_strings":["Ashoka University, India"],"affiliations":[{"raw_affiliation_string":"Ashoka University, India","institution_ids":["https://openalex.org/I347237974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079705040"],"corresponding_institution_ids":["https://openalex.org/I347237974"],"apc_list":null,"apc_paid":null,"fwci":0.4951672,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61221147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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":0.9922000169754028,"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/mnist-database","display_name":"MNIST database","score":0.8819434642791748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7760868072509766},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7282718420028687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7165342569351196},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5816864967346191},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5673676133155823},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5579278469085693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5468567609786987},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4523431360721588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3784252405166626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3565746545791626},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.27174103260040283}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8819434642791748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760868072509766},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7282718420028687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7165342569351196},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5816864967346191},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5673676133155823},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5579278469085693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5468567609786987},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4523431360721588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3784252405166626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3565746545791626},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27174103260040283},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1145/3571600.3571653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3571600.3571653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1993309459","https://openalex.org/W2007339694","https://openalex.org/W2062118960","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2412782625","https://openalex.org/W2557728737","https://openalex.org/W2560674852","https://openalex.org/W2560741668","https://openalex.org/W2592962403","https://openalex.org/W2595002104","https://openalex.org/W2804935296","https://openalex.org/W2886641317","https://openalex.org/W2964309429","https://openalex.org/W2967116560","https://openalex.org/W3009299090","https://openalex.org/W3035524453","https://openalex.org/W3120472021","https://openalex.org/W3156636935","https://openalex.org/W3166304536","https://openalex.org/W3173220247","https://openalex.org/W3175781199","https://openalex.org/W3176463841","https://openalex.org/W3182683290","https://openalex.org/W4213100327","https://openalex.org/W4229042118"],"related_works":["https://openalex.org/W2901671134","https://openalex.org/W3183100063","https://openalex.org/W2312145515","https://openalex.org/W4206451978","https://openalex.org/W3195622388","https://openalex.org/W2759497208","https://openalex.org/W3041443116","https://openalex.org/W3176438653","https://openalex.org/W2981628807","https://openalex.org/W3012393889"],"abstract_inverted_index":{"State-of-the-art":[0],"empirical":[1],"work":[2],"has":[3],"shown":[4],"that":[5],"visual":[6,85],"representations":[7,86,105],"learned":[8],"by":[9,82,100],"deep":[10],"neural":[11],"networks":[12],"are":[13],"robust":[14,84],"in":[15,39,107],"nature":[16],"and":[17,46,61,71,103,121,133,141],"capable":[18],"of":[19,44,79],"performing":[20],"classification":[21,37,123,145],"tasks":[22,38,120],"on":[23,33,55,87,136],"diverse":[24],"datasets.":[25],"For":[26],"example,":[27],"CLIP":[28],"demonstrated":[29],"zero-shot":[30,131],"transfer":[31,53,132],"performance":[32,54,116],"multiple":[34],"datasets":[35,143],"for":[36,75,117,144],"a":[40,69],"joint":[41,109],"embedding":[42,110],"space":[43],"image":[45,104],"text":[47,102],"pairs.":[48],"However,":[49],"it":[50],"showed":[51,113],"negative":[52],"standard":[56],"datasets,":[57],"e.g.,":[58],"BirdsNAP,":[59],"RESISC45,":[60,140],"MNIST.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"ContextCLIP,":[68],"contextual":[70,77],"contrastive":[72],"learning":[73,83],"framework":[74,92],"the":[76,97,108],"alignment":[78,99],"image-text":[80,98],"pairs":[81],"Conceptual":[88],"Captions":[89],"dataset.":[90],"Our":[91],"was":[93],"observed":[94],"to":[95],"improve":[96],"aligning":[101],"contextually":[106],"space.":[111],"ContextCLIP":[112],"good":[114],"qualitative":[115],"text-to-image":[118],"retrieval":[119],"enhanced":[122],"accuracy.":[124],"We":[125],"evaluated":[126],"our":[127],"model":[128],"quantitatively":[129],"with":[130],"fine-tuning":[134],"experiments":[135],"CIFAR-10,":[137],"CIFAR-100,":[138],"Birdsnap,":[139],"MNIST":[142],"task.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}