{"id":"https://openalex.org/W3092721023","doi":"https://doi.org/10.1145/3394171.3413638","title":"Text-Embedded Bilinear Model for Fine-Grained Visual Recognition","display_name":"Text-Embedded Bilinear Model for Fine-Grained Visual Recognition","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092721023","doi":"https://doi.org/10.1145/3394171.3413638","mag":"3092721023"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5021834892","display_name":"Liang Sun","orcid":"https://orcid.org/0000-0003-2794-8654"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Cheng Du, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Cheng Du, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017441954","display_name":"Xiang Guan","orcid":"https://orcid.org/0000-0002-5162-453X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Guan","raw_affiliation_strings":["University of Electronic Science and Technology of China, Cheng Du, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Cheng Du, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Cheng Du, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Cheng Du, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106578837","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-5305-8543"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Chongqing University, Chong Qing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University, Chong Qing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3417,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.641979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"219"},"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":0.9987000226974487,"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":0.9987000226974487,"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":0.9983999729156494,"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":0.9983999729156494,"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":0.7881206274032593},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7864243984222412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7286726832389832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6721352338790894},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6030920743942261},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5797348022460938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5466575622558594},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5224134922027588},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.4866207540035248},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47819021344184875},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44678109884262085},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4429969787597656},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43558192253112793},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3883756101131439},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24078994989395142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881206274032593},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7864243984222412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7286726832389832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6721352338790894},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6030920743942261},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5797348022460938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5466575622558594},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5224134922027588},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4866207540035248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47819021344184875},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44678109884262085},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4429969787597656},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43558192253112793},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3883756101131439},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24078994989395142},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1145/3394171.3413638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1496650988","https://openalex.org/W1552847225","https://openalex.org/W1616462885","https://openalex.org/W1797268635","https://openalex.org/W1898560071","https://openalex.org/W1920702274","https://openalex.org/W1955942245","https://openalex.org/W1984514441","https://openalex.org/W2062118960","https://openalex.org/W2104657103","https://openalex.org/W2117539524","https://openalex.org/W2146897752","https://openalex.org/W2194775991","https://openalex.org/W2196615847","https://openalex.org/W2202499615","https://openalex.org/W2207849498","https://openalex.org/W2398118205","https://openalex.org/W2533598788","https://openalex.org/W2551829638","https://openalex.org/W2554320282","https://openalex.org/W2558914813","https://openalex.org/W2737725206","https://openalex.org/W2741910023","https://openalex.org/W2752782242","https://openalex.org/W2763070548","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2789209438","https://openalex.org/W2798365843","https://openalex.org/W2807931652","https://openalex.org/W2882999943","https://openalex.org/W2883502031","https://openalex.org/W2891951760","https://openalex.org/W2909384861","https://openalex.org/W2954924421","https://openalex.org/W2961018736","https://openalex.org/W2962798895","https://openalex.org/W2963066927","https://openalex.org/W2963148524","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2963420686","https://openalex.org/W2963676620","https://openalex.org/W2963869273","https://openalex.org/W2964176323","https://openalex.org/W2981578638","https://openalex.org/W3008809756","https://openalex.org/W3009073662","https://openalex.org/W3035031253","https://openalex.org/W3099903704","https://openalex.org/W6602324145","https://openalex.org/W6607687417","https://openalex.org/W6754854709"],"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/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1,39,76],"recognition,":[2,206],"which":[3,57,97],"aims":[4],"to":[5,62,75,83,113,123,169,183],"identify":[6],"subcategories":[7],"of":[8,18,165],"the":[9,38,43,52,60,118,131,155,162,166,185,194,207,215],"same":[10],"base-level":[11],"category,":[12],"is":[13,67],"a":[14,92,110,125,151,179],"challenging":[15],"task":[16,33],"because":[17],"its":[19],"large":[20],"intra-class":[21],"variances":[22],"and":[23,136,143,158,199],"small":[24],"inter-class":[25],"variances.":[26],"Human":[27],"beings":[28],"can":[29,49,144],"perform":[30],"object":[31],"recognition":[32],"based":[34],"on":[35,193],"not":[36],"only":[37],"appearance":[40],"but":[41],"also":[42,149],"knowledge":[44],"from":[45,71,154],"texts,":[46],"as":[47,100],"texts":[48,80,99],"point":[50],"out":[51],"discriminative":[53,119],"parts":[54],"or":[55],"characteristics":[56],"are":[58,81,140],"always":[59],"key":[61],"distinguishing":[63],"different":[64],"subcategories.":[65],"This":[66],"an":[68,171],"involuntary":[69],"transfer":[70],"human":[72],"textual":[73],"attention":[74],"attention,":[77],"suggesting":[78],"that":[79],"able":[82],"assist":[84],"fine-grained":[85,104,137,204],"recognition.":[86,105],"In":[87,128],"this":[88],"paper,":[89],"we":[90,107,148,177],"propose":[91],"Text-Embedded":[93],"Bilinear":[94],"(TEB)":[95],"model":[96,213],"incorporates":[98],"extra":[101],"guidance":[102],"for":[103,203],"Specially,":[106],"first":[108],"conduct":[109],"text-embedded":[111],"network":[112,182],"embed":[114,159],"text":[115,156],"feature":[116,121,134,138,153,164],"into":[117,161],"image":[120,167,205],"learning":[122,139],"get":[124,170],"embedded":[126,172,187],"feature.":[127,174],"addition,":[129],"since":[130],"cross-layer":[132,180],"part":[133],"interaction":[135],"mutually":[141],"correlated":[142],"reinforce":[145],"each":[146],"other,":[147],"extract":[150],"candidate":[152,173],"encoder":[157,168],"it":[160],"inter-layer":[163],"At":[175],"last":[176],"utilize":[178],"bilinear":[181],"fuse":[184],"two":[186],"features.":[188],"Comparing":[189],"with":[190],"state-of-the-art":[191],"methods":[192],"widely":[195],"used":[196],"CUB-200-2011":[197],"dataset":[198,202],"Oxford":[200],"Flowers-102":[201],"experimental":[208],"results":[209],"demonstrate":[210],"our":[211],"TEB":[212],"achieves":[214],"best":[216],"performance.":[217]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}