{"id":"https://openalex.org/W4313316189","doi":"https://doi.org/10.1109/tcsvt.2022.3233369","title":"Describe Fashion Products via Local Sparse Self-Attention Mechanism and Attribute-Based Re-Sampling Strategy","display_name":"Describe Fashion Products via Local Sparse Self-Attention Mechanism and Attribute-Based Re-Sampling Strategy","publication_year":2022,"publication_date":"2022-12-30","ids":{"openalex":"https://openalex.org/W4313316189","doi":"https://doi.org/10.1109/tcsvt.2022.3233369"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3233369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3233369","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5027847338","display_name":"Yuhao Tang","orcid":"https://orcid.org/0000-0001-6026-0769"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhao Tang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618147","display_name":"Liyan Zhang","orcid":"https://orcid.org/0000-0002-1549-3317"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334813","display_name":"Ye Yuan","orcid":"https://orcid.org/0009-0005-3886-3527"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029561060","display_name":"Zhixian Chen","orcid":"https://orcid.org/0000-0003-4006-022X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixian Chen","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027847338"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.5033,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64758941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"33","issue":"7","first_page":"3409","last_page":"3424"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9833999872207642,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9799000024795532,"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/closed-captioning","display_name":"Closed captioning","score":0.9608645439147949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8446775674819946},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6014392375946045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448087453842163},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5130695104598999},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49472543597221375},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4725325405597687},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4639686346054077},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4294590353965759},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.41550368070602417},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4122036099433899},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41187116503715515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38208064436912537},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35221725702285767},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18295526504516602}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9608645439147949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446775674819946},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6014392375946045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448087453842163},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5130695104598999},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49472543597221375},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4725325405597687},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4639686346054077},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4294590353965759},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.41550368070602417},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4122036099433899},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41187116503715515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38208064436912537},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35221725702285767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18295526504516602},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3233369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3233369","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1873612269","display_name":null,"funder_award_id":"61720106006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7255707686","display_name":null,"funder_award_id":"62172212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":52,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1949942966","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2133280805","https://openalex.org/W2154652894","https://openalex.org/W2471768434","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2769033722","https://openalex.org/W2788676105","https://openalex.org/W2808747415","https://openalex.org/W2867270703","https://openalex.org/W2919631354","https://openalex.org/W2963084599","https://openalex.org/W2970127347","https://openalex.org/W2986670728","https://openalex.org/W2995197345","https://openalex.org/W3019301826","https://openalex.org/W3034541562","https://openalex.org/W3034655362","https://openalex.org/W3034682719","https://openalex.org/W3034984754","https://openalex.org/W3035485997","https://openalex.org/W3035726724","https://openalex.org/W3096965663","https://openalex.org/W3106925514","https://openalex.org/W3107492437","https://openalex.org/W3118811961","https://openalex.org/W3130073172","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3165938948","https://openalex.org/W3167939936","https://openalex.org/W3172514680","https://openalex.org/W3174366534","https://openalex.org/W3176470992","https://openalex.org/W3195680250","https://openalex.org/W3195866476","https://openalex.org/W3215720729","https://openalex.org/W4285197287","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6679915538","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6752422777","https://openalex.org/W6768920361","https://openalex.org/W6804880574","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W2354515814"],"abstract_inverted_index":{"In":[0],"this":[1,119],"paper,":[2],"we":[3,49,121,166],"convert":[4],"conventional":[5],"image":[6],"captioning":[7,187],"task":[8,21],"into":[9],"a":[10,27,34,45,51,71,123,137],"new":[11],"paradigm":[12],"in":[13,44,65,108],"the":[14,23,66,83,93,109,141,177,195,223,240],"fashion":[15,17,104,115,127,143,185],"domain,":[16],"item":[18,30,128,186],"captioning.":[19],"This":[20],"requires":[22],"ability":[24],"of":[25,29,82,111,225],"associating":[26],"group":[28],"angles":[31],"and":[32,36,69,113,159,209,236],"generating":[33],"longer":[35],"more":[37,46,79,200],"fine-grained":[38],"description.":[39],"To":[40,77,117],"link":[41],"several":[42],"images":[43],"efficient":[47],"way,":[48],"propose":[50,122],"local":[52],"sparse":[53],"self-attention":[54],"mechanism(LSAM),":[55],"which":[56,145,175],"only":[57,183],"enables":[58,176],"one":[59],"region":[60],"to":[61,91,140,179,204,247,250],"interact":[62],"with":[63,74,153,216,239],"those":[64,96],"adjacent":[67],"area":[68],"allows":[70],"lighter":[72],"architecture":[73],"fewer":[75],"layers.":[76],"capture":[78],"subtle":[80],"details":[81],"item,":[84,174],"an":[85,169,217],"attribute-based":[86],"re-sampling":[87],"strategy(ARS)":[88],"is":[89,162,198,213],"introduced":[90],"enhance":[92],"learning":[94],"on":[95,234],"low-frequency":[97],"but":[98,188],"content-related":[99],"attribute":[100],"words.":[101],"Besides,":[102],"existing":[103,142],"datasets":[105],"are":[106],"limited":[107],"quality":[110],"annotations":[112],"single":[114],"style.":[116],"bridge":[118],"gap,":[120],"novel":[124],"dataset":[125],"for":[126,172,184,190,202],"captioning,":[129],"termed":[130],"Fashion":[131],"Item":[132],"Captioning":[133],"Dataset(FICD).":[134],"FICD":[135,178,237],"provides":[136],"meaningful":[138],"complement":[139],"datasets,":[144,238],"comprises":[146],"294K":[147],"images,":[148],"62K":[149],"real-world":[150,205],"product":[151],"descriptions":[152],"diverse":[154],"linguistic":[155],"styles,":[156],"rich":[157],"attributes":[158],"categories.":[160],"It":[161],"worth":[163],"mentioning":[164],"that":[165],"also":[167,189],"annotate":[168],"attribute-level":[170],"sentence":[171],"each":[173],"be":[180],"used":[181],"not":[182],"other":[191],"fashion-related":[192],"tasks.":[193],"Moreover,":[194],"complex":[196],"structure":[197],"even":[199],"restrictive":[201],"application":[203],"scenarios.":[206],"Without":[207],"bells":[208],"whistles,":[210],"our":[211,226],"framework":[212],"simply":[214],"designed":[215],"end-to-end":[218],"manner.":[219],"Extensive":[220],"experiments":[221],"demonstrate":[222],"effectiveness":[224],"LSAM-ARS.":[227],"More":[228],"remarkably,":[229],"LSAM-ARS":[230],"achieves":[231],"state-of-the-art":[232],"performance":[233],"FACAD":[235],"CIDEr-D":[241],"score":[242],"being":[243],"increased":[244],"from":[245],"65.4%":[246],"81.8%,":[248],"69.8%":[249],"77.4%,":[251],"respectively.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
