{"id":"https://openalex.org/W2902270960","doi":"https://doi.org/10.1109/icpr.2018.8545573","title":"Word Image Representation Based on Visual Embeddings and Spatial Constraints for Keyword Spotting on Historical Documents","display_name":"Word Image Representation Based on Visual Embeddings and Spatial Constraints for Keyword Spotting on Historical Documents","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2902270960","doi":"https://doi.org/10.1109/icpr.2018.8545573","mag":"2902270960"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8545573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","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/A5050639942","display_name":"Hongxi Wei","orcid":"https://orcid.org/0000-0002-2570-4544"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxi Wei","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323546","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0003-2569-1824"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3616","last_page":"3621"},"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991999864578247,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7041625380516052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641808748245239},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.6502239108085632},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6457220315933228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6055070161819458},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5342710614204407},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5155601501464844},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.509905219078064},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4752471446990967},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43815240263938904},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.434447705745697},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.41543397307395935},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4150261878967285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33602309226989746},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3036594092845917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2783282697200775},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.10493513941764832}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7041625380516052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641808748245239},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.6502239108085632},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6457220315933228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6055070161819458},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5342710614204407},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5155601501464844},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.509905219078064},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4752471446990967},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43815240263938904},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.434447705745697},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.41543397307395935},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4150261878967285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33602309226989746},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3036594092845917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2783282697200775},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.10493513941764832},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1109/icpr.2018.8545573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1969408022","https://openalex.org/W1976752808","https://openalex.org/W2055981215","https://openalex.org/W2056225014","https://openalex.org/W2100478624","https://openalex.org/W2126707722","https://openalex.org/W2153579005","https://openalex.org/W2156301828","https://openalex.org/W2158102958","https://openalex.org/W2162838084","https://openalex.org/W2162915993","https://openalex.org/W2250539671","https://openalex.org/W2270593706","https://openalex.org/W2515351093","https://openalex.org/W2524590779","https://openalex.org/W2575351849","https://openalex.org/W2594443378","https://openalex.org/W2734894366","https://openalex.org/W2752634058","https://openalex.org/W2765095615","https://openalex.org/W2785344374","https://openalex.org/W2786459439","https://openalex.org/W2799327278","https://openalex.org/W4238410424","https://openalex.org/W4294170691","https://openalex.org/W6682691769","https://openalex.org/W6694083279","https://openalex.org/W6727599421","https://openalex.org/W6732396895","https://openalex.org/W6750308545"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W2766495108","https://openalex.org/W2028757524","https://openalex.org/W2996463043","https://openalex.org/W1995462736","https://openalex.org/W2938717424","https://openalex.org/W2548286644","https://openalex.org/W2009049007","https://openalex.org/W2588241640","https://openalex.org/W2045213079"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposed":[2,145],"a":[3,24,34,48,115],"visual":[4,12,17,42,99,150,160],"embeddings":[5,162],"approach":[6,147],"to":[7,134],"capturing":[8],"semantic":[9,49],"relatedness":[10],"between":[11,137],"words.":[13],"To":[14,51],"be":[15,81,112,132],"specific,":[16],"words":[18,43,100],"are":[19],"extracted":[20],"and":[21,74,163],"collected":[22],"from":[23,125],"word":[25,59,62,109,138,161],"image":[26,63,110],"collection":[27],"under":[28],"the":[29,56,91,94,102,120,144],"Bag-of-Visual-Words":[30],"framework.":[31],"And":[32],"then,":[33],"deep":[35],"learning":[36],"procedure":[37],"is":[38,64,90],"used":[39],"for":[40],"mapping":[41],"into":[44,55,66,114],"embedding":[45,87,95,123],"vectors":[46,96,124],"in":[47],"space.":[50],"integrate":[52],"spatial":[53,153],"constraints":[54],"representation":[57,146],"of":[58,86,93,97],"images,":[60],"one":[61,108],"segmented":[65],"several":[67],"sub-regions":[68],"with":[69],"equal":[70],"size":[71],"along":[72],"rows":[73],"columns.":[75],"After":[76],"that,":[77],"each":[78],"sub-region":[79],"can":[80,111,131],"represented":[82],"as":[83],"an":[84],"average":[85,122,159],"vectors,":[88],"which":[89],"centroid":[92],"all":[98,127],"within":[101],"same":[103],"sub-region.":[104],"By":[105],"this":[106],"way,":[107],"converted":[113],"fixed-length":[116],"vector":[117],"by":[118],"concatenating":[119],"corresponding":[121],"its":[126],"sub-regions.":[128],"Euclidean":[129],"distance":[130],"calculated":[133],"measure":[135],"similarity":[136],"images.":[139],"Experimental":[140],"results":[141],"demonstrate":[142],"that":[143],"outperforms":[148],"Bag-of-Visual-Words,":[149],"language":[151],"model,":[152],"pyramid":[154],"matching,":[155],"latent":[156],"Dirichlet":[157],"allocation,":[158],"recurrent":[164],"neural":[165],"network.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}