{"id":"https://openalex.org/W2765926571","doi":"https://doi.org/10.1145/3126686.3126736","title":"Variation Robust Cross-Modal Metric Learning for Caricature Recognition","display_name":"Variation Robust Cross-Modal Metric Learning for Caricature Recognition","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2765926571","doi":"https://doi.org/10.1145/3126686.3126736","mag":"2765926571"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066091819","display_name":"Jing Huo","orcid":"https://orcid.org/0000-0002-8504-455X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huo","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055917015","display_name":"Yinghuan Shi","orcid":"https://orcid.org/0000-0003-4534-7318"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghuan Shi","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055149475","display_name":"Hujun Yin","orcid":"https://orcid.org/0000-0002-9198-5401"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hujun Yin","raw_affiliation_strings":["University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"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/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"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/T10057","display_name":"Face and Expression Recognition","score":0.989300012588501,"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":0.9843999743461609,"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/landmark","display_name":"Landmark","score":0.7810872793197632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7632448077201843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7286475896835327},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7196451425552368},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6431344747543335},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6320608258247375},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.629999577999115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6219972968101501},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6205751299858093},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5984015464782715},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5921058654785156},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5350049734115601},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5142135620117188},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.457495778799057},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41148772835731506},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4056554436683655},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15688881278038025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14810577034950256},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08066695928573608},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05309763550758362}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7810872793197632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632448077201843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7286475896835327},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7196451425552368},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6431344747543335},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6320608258247375},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.629999577999115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6219972968101501},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6205751299858093},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5984015464782715},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5921058654785156},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5350049734115601},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5142135620117188},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.457495778799057},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41148772835731506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4056554436683655},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15688881278038025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14810577034950256},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08066695928573608},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05309763550758362},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126686.3126736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1425104224","https://openalex.org/W1538281814","https://openalex.org/W1592934690","https://openalex.org/W1622965039","https://openalex.org/W1699277040","https://openalex.org/W2015635574","https://openalex.org/W2040825516","https://openalex.org/W2061273563","https://openalex.org/W2066852389","https://openalex.org/W2106890447","https://openalex.org/W2120824855","https://openalex.org/W2121647436","https://openalex.org/W2121949863","https://openalex.org/W2153288431","https://openalex.org/W2154671648","https://openalex.org/W2185498755","https://openalex.org/W2321727850","https://openalex.org/W2325939864","https://openalex.org/W2407624458","https://openalex.org/W2527301607","https://openalex.org/W2595360966","https://openalex.org/W2612133093","https://openalex.org/W2749314600"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W4243161226","https://openalex.org/W2010533810","https://openalex.org/W2950647290","https://openalex.org/W2356918560","https://openalex.org/W1968481813","https://openalex.org/W627697492"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,24,27,71],"variation":[4],"robust":[5,192],"cross-modal":[6,130,157],"metric":[7,158,172],"learning":[8,189],"(VR-CM2L)":[9],"method":[10,190,203],"is":[11,21,80,159,169],"proposed":[12,202],"for":[13],"caricature":[14,19,25,206],"recognition.":[15],"The":[16,183],"goal":[17],"of":[18,38,62,84,100,112,126,179,200],"recognition":[20,30],"to":[22,33,57,142,161,174,193],"match":[23],"with":[26,35,68,104,116,208],"photo.":[28],"This":[29],"process":[31],"needs":[32],"deal":[34,67],"all":[36],"kind":[37],"variations":[39,55],"including":[40],"different":[41,91,117,135],"modalities,":[42],"facial":[43,74,97,136],"appearance":[44],"exaggerations,":[45],"changes":[46],"in":[47,138],"viewpoint,":[48],"expression,":[49],"and":[50,64,86,108,119,155,181],"illumination,":[51],"etc.":[52],"All":[53],"these":[54,69,127],"lead":[56],"severe":[58],"misalignment":[59],"between":[60],"features":[61,83,99,111,149,178],"caricatures":[63,85,113,180],"photos.":[65,182],"To":[66,122],"problems,":[70],"specifically":[72],"designed":[73],"landmark":[75],"based":[76],"feature":[77,92],"extraction":[78,93],"scheme":[79],"proposed,":[81],"where":[82],"photos":[87,101],"are":[88,102,114,132,150],"extracted":[89,103,115],"using":[90],"steps.":[94],"At":[95],"each":[96],"landmark,":[98],"fixed":[105],"viewing":[106,120],"angle":[107],"scale,":[109],"while":[110],"scales":[118],"angles.":[121],"measure":[123],"the":[124,147,177,188,198,201],"similarity":[125],"features,":[128],"multiple":[129],"metrics":[131],"learned":[133],"at":[134,166],"landmarks":[137],"one":[139],"optimization":[140,173],"framework":[141],"guarantee":[143],"global":[144],"optimum.":[145],"As":[146],"measured":[148],"from":[151],"two":[152,205],"modalities":[153],"(caricature":[154],"photo),":[156],"used":[160,170],"remove":[162],"modality":[163],"variations.":[164,194,210],"Pooling":[165],"distance":[167],"level":[168],"during":[171],"further":[175],"align":[176],"introduced":[184],"pooling":[185],"step":[186],"makes":[187],"more":[191],"Experimental":[195],"results":[196],"demonstrate":[197],"effectiveness":[199],"on":[204],"datasets":[207],"various":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}