{"id":"https://openalex.org/W4376852446","doi":"https://doi.org/10.1145/3573942.3574065","title":"Image Description Generation Method Based on X-Linear Attention Mechanism","display_name":"Image Description Generation Method Based on X-Linear Attention Mechanism","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4376852446","doi":"https://doi.org/10.1145/3573942.3574065"},"language":"en","primary_location":{"id":"doi:10.1145/3573942.3574065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","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/A5005451272","display_name":"Pingan Qiao","orcid":"https://orcid.org/0000-0002-4821-2518"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pingan Qiao","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-4821-2518","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895506","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-3383-3573"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-3383-3573","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868469","display_name":"Ruixue Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixue Shen","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-2705-1436","affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005451272"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17234828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"581","last_page":"586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384779453277588},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.652517557144165},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.5983431339263916},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.557328462600708},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5511316657066345},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5498020648956299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5446956753730774},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5443567037582397},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4841935932636261},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4709782600402832},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4415810704231262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4255569875240326},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32886362075805664},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.28660640120506287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384779453277588},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.652517557144165},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.5983431339263916},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.557328462600708},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5511316657066345},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5498020648956299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446956753730774},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5443567037582397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4841935932636261},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4709782600402832},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4415810704231262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4255569875240326},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32886362075805664},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28660640120506287},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573942.3574065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1676314349","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1981276685","https://openalex.org/W2104657103","https://openalex.org/W2745461083","https://openalex.org/W2752782242","https://openalex.org/W2963066927","https://openalex.org/W2963084599","https://openalex.org/W6600020421","https://openalex.org/W6638579582"],"related_works":["https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2261271299","https://openalex.org/W2963066927","https://openalex.org/W4280638452","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W2964944724","https://openalex.org/W4285020665","https://openalex.org/W3160506688"],"abstract_inverted_index":{"Aiming":[0],"at":[1],"the":[2,18,39,42,54,58,61,72],"problem":[3],"that":[4,77],"existing":[5],"image":[6,65],"description":[7,66],"models":[8],"cannot":[9],"model":[10,31,59],"high-order":[11,32],"multimodal":[12,36],"feature":[13,33],"interaction,":[14],"this":[15,78],"paper":[16],"introduces":[17],"X-Linear":[19,43],"attention":[20,44,50],"mechanism,":[21],"which":[22],"uses":[23,46],"bilinear":[24],"pooling":[25],"and":[26,48,60,82],"ELU":[27],"activation":[28],"function":[29],"to":[30,52,63],"interaction":[34],"between":[35],"features.":[37],"At":[38],"same":[40],"time,":[41],"mechanism":[45],"spatial":[47],"channel":[49],"mechanisms":[51],"enhance":[53],"expression":[55],"ability":[56,62],"of":[57],"generate":[64],"sentences.":[67],"The":[68],"experimental":[69],"results":[70],"on":[71],"MSCOCO":[73],"data":[74],"set":[75],"show":[76],"method":[79],"is":[80],"effective":[81],"has":[83],"a":[84],"great":[85],"improvement":[86],"in":[87],"each":[88],"evaluation":[89],"metric.":[90]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}