{"id":"https://openalex.org/W2807948597","doi":"https://doi.org/10.1145/3206025.3206061","title":"Multi-label Triplet Embeddings for Image Annotation from User-Generated Tags","display_name":"Multi-label Triplet Embeddings for Image Annotation from User-Generated Tags","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2807948597","doi":"https://doi.org/10.1145/3206025.3206061","mag":"2807948597"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","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/A5041760616","display_name":"Zachary Seymour","orcid":"https://orcid.org/0000-0002-7117-1638"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Seymour","raw_affiliation_strings":["SUNY Binghamton, Binghamton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUNY Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036747535","display_name":"Zhongfei Zhang","orcid":"https://orcid.org/0000-0001-5098-2506"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongfei (Mark) Zhang","raw_affiliation_strings":["SUNY Binghamton, Binghamton, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUNY Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":0.212,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54623572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"256"},"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":0.9997000098228455,"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":0.9984999895095825,"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":0.849479079246521},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6748122572898865},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5965107083320618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5860264301300049},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5480291843414307},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5346165299415588},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5334696173667908},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4975147545337677},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4887521266937256},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.46514996886253357},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44966354966163635},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4255809783935547},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4071934223175049},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.344920814037323},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.337123841047287},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10673710703849792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849479079246521},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6748122572898865},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5965107083320618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860264301300049},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5480291843414307},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5346165299415588},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5334696173667908},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4975147545337677},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4887521266937256},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46514996886253357},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44966354966163635},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4255809783935547},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4071934223175049},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.344920814037323},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.337123841047287},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10673710703849792},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206025.3206061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","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":31,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W1514027499","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W1987549167","https://openalex.org/W1988719066","https://openalex.org/W2007972815","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2151691375","https://openalex.org/W2155803963","https://openalex.org/W2250384498","https://openalex.org/W2325939864","https://openalex.org/W2413850928","https://openalex.org/W2473594146","https://openalex.org/W2549365021","https://openalex.org/W2553988549","https://openalex.org/W2618530766","https://openalex.org/W2949541494","https://openalex.org/W2950133940","https://openalex.org/W2963132412","https://openalex.org/W2963389687","https://openalex.org/W2963702081","https://openalex.org/W2963745697","https://openalex.org/W2963908715","https://openalex.org/W3099206234","https://openalex.org/W3104069527","https://openalex.org/W4231464604"],"related_works":["https://openalex.org/W2566406229","https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2119028572","https://openalex.org/W2376984068","https://openalex.org/W2152482390","https://openalex.org/W2365617273","https://openalex.org/W2076896210","https://openalex.org/W2506386910","https://openalex.org/W2117928543"],"abstract_inverted_index":{"This":[0],"work":[1,79],"studies":[2],"the":[3,12,22,28,38,81,89,107,129,142,162,177,184,189,203,209,222,235],"representational":[4,223],"embedding":[5,200],"of":[6,14,21,37,83,91,138,156,191,211,221,225,237],"images":[7,204],"and":[8,51,94,115,148,205],"their":[9,206],"corresponding":[10,29],"annotations--in":[11],"form":[13],"tag":[15],"metadata--such":[16],"that,":[17],"given":[18],"a":[19,154,192,198],"piece":[20],"raw":[23,39],"data":[24,40,139],"in":[25,35,41,54,75,88,165,208],"one":[26],"modality,":[27],"semantic":[30],"description":[31],"can":[32],"be":[33,72,161],"retrieved":[34],"terms":[36],"another.":[42],"While":[43],"convolutional":[44,147],"neural":[45,150],"networks":[46],"(CNNs)":[47],"have":[48,170],"been":[49,171],"widely":[50,98],"successfully":[52],"applied":[53],"this":[55,78,105,136,166,238],"domain":[56],"with":[57,85],"regards":[58],"to":[59,120,173,196,233],"detecting":[60],"semantically":[61,95],"simple":[62],"scenes":[63],"or":[64,126],"categories":[65],"(even":[66],"though":[67,168],"many":[68],"such":[69],"objects":[70],"may":[71,159],"simultaneously":[73],"present":[74,218],"an":[76,110,121],"image),":[77],"approaches":[80],"task":[82],"dealing":[84],"image":[86,111,132,230],"annotations":[87],"context":[90],"noisy,":[92,114],"user-generated,":[93],"complex":[96],"multi-labels,":[97],"available":[99],"from":[100],"social":[101],"media":[102],"sites.":[103],"In":[104],"case,":[106,167],"labels":[108],"for":[109,202],"are":[112],"diverse,":[113],"often":[116],"not":[117,160],"specifically":[118],"related":[119],"object,":[122],"but":[123],"rather":[124],"descriptive":[125],"user-specific.":[127],"Furthermore,":[128],"existing":[130],"deep":[131],"annotation":[133,231],"literature":[134],"using":[135],"type":[137],"typically":[140],"utilizes":[141],"so-called":[143],"CNN-RNN":[144],"framework,":[145],"combining":[146],"recurrent":[149],"networks.":[151],"We":[152,217],"offer":[153],"discussion":[155],"why":[157],"RNNs":[158],"best":[163],"choice":[164],"they":[169],"shown":[172],"perform":[174],"well":[175],"on":[176,228],"similar":[178],"captioning":[179],"tasks.":[180],"Our":[181],"model":[182],"exploits":[183],"latent":[185],"image-text":[186],"space":[187,201],"through":[188],"use":[190],"triplet":[193],"loss":[194],"framework":[195],"learn":[197],"joint":[199],"tags,":[207],"presence":[210],"multiple,":[212],"potentially":[213],"positive":[214],"exemplar":[215],"classes.":[216],"state-of-the-art":[219],"results":[220],"properties":[224],"these":[226],"embeddings":[227],"several":[229],"datasets":[232],"show":[234],"promise":[236],"approach.":[239]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}