{"id":"https://openalex.org/W2044542000","doi":"https://doi.org/10.1145/1101149.1101249","title":"Learning an image-word embedding for image auto-annotation on the nonlinear latent space","display_name":"Learning an image-word embedding for image auto-annotation on the nonlinear latent space","publication_year":2005,"publication_date":"2005-11-06","ids":{"openalex":"https://openalex.org/W2044542000","doi":"https://doi.org/10.1145/1101149.1101249","mag":"2044542000"},"language":"en","primary_location":{"id":"doi:10.1145/1101149.1101249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","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/A5101955284","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-2195-2310"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110380387","display_name":"Xiaoou Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Tang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101955284"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.4687,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83275024,"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":"451","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998000264167786,"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":0.9979000091552734,"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":0.987500011920929,"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":0.6993560791015625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619228720664978},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6405932903289795},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.6265950798988342},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5985040068626404},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.591867208480835},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5693328976631165},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5567095279693604},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47866734862327576},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4769945740699768},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4719015061855316},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4646669626235962},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4410315454006195},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43516743183135986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3544811010360718},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19299674034118652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993560791015625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619228720664978},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6405932903289795},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.6265950798988342},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5985040068626404},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.591867208480835},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5693328976631165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5567095279693604},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47866734862327576},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4769945740699768},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4719015061855316},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4646669626235962},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4410315454006195},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43516743183135986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3544811010360718},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19299674034118652},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1101149.1101249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","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":11,"referenced_works":["https://openalex.org/W2020842694","https://openalex.org/W2123241287","https://openalex.org/W2133598579","https://openalex.org/W2134731454","https://openalex.org/W2140095548","https://openalex.org/W2144407188","https://openalex.org/W2147152072","https://openalex.org/W2149175354","https://openalex.org/W2150692003","https://openalex.org/W4285719527","https://openalex.org/W6681764552"],"related_works":["https://openalex.org/W2588002110","https://openalex.org/W2111020819","https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2775171027","https://openalex.org/W2076896210","https://openalex.org/W4389358025","https://openalex.org/W2267563544","https://openalex.org/W2384288472","https://openalex.org/W1439405941"],"abstract_inverted_index":{"Latent":[0,25,51],"Semantic":[1],"Analysis":[2],"(LSA)":[3],"has":[4],"shown":[5],"encouraging":[6],"performance":[7],"for":[8,29,78],"the":[9,30,56,68,93,107],"problem":[10],"of":[11,34,59,67],"unsupervised":[12,113],"image":[13,37,79],"automatic":[14],"annotation.":[15],"LSA":[16],"conducts":[17],"annotation":[18,80,105,114],"by":[19],"keywords":[20],"propagation":[21,70],"on":[22,106],"a":[23,44,74,98],"linear":[24],"Space,":[26],"which":[27],"accounts":[28],"underlying":[31],"semantic":[32],"structure":[33],"word":[35,60],"and":[36,61,89,91],"features.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,72],"formulate":[43],"more":[45,64],"general":[46],"nonlinear":[47,108],"model,":[48,53],"called":[49],"Nonlinear":[50],"Space":[52],"to":[54],"reveal":[55],"latent":[57,109],"variables":[58],"visual":[62],"features":[63],"precisely.":[65],"Instead":[66],"basic":[69],"strategy,":[71],"present":[73],"novel":[75],"inference":[76],"strategy":[77],"via":[81],"Image-Word":[82],"Embedding":[83],"(IWE).":[84],"IWE":[85],"simultaneously":[86],"embeds":[87],"images":[88],"words":[90],"captures":[92],"dependencies":[94],"between":[95],"them":[96],"from":[97],"probabilistic":[99],"viewpoint.":[100],"Experiments":[101],"show":[102],"that":[103],"IWE-based":[104],"space":[110],"outperforms":[111],"previous":[112],"methods.":[115]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}