{"id":"https://openalex.org/W3028797339","doi":"https://doi.org/10.1109/tip.2020.2996736","title":"Bi-Modal Progressive Mask Attention for Fine-Grained Recognition","display_name":"Bi-Modal Progressive Mask Attention for Fine-Grained Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3028797339","doi":"https://doi.org/10.1109/tip.2020.2996736","mag":"3028797339"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.2996736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.2996736","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5028035527","display_name":"Kaitao Song","orcid":"https://orcid.org/0000-0002-4046-8594"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaitao Song","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4046-8594","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066964304","display_name":"Xiu-Shen Wei","orcid":"https://orcid.org/0000-0002-8200-1845"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu-Shen Wei","raw_affiliation_strings":["Jiangsu Key Lab of Image and Video Understanding for Social Security, and Technology, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8200-1845","affiliations":[{"raw_affiliation_string":"Jiangsu Key Lab of Image and Video Understanding for Social Security, and Technology, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779857","display_name":"Renjie Song","orcid":"https://orcid.org/0000-0003-3076-1786"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren-Jie Song","raw_affiliation_strings":["Megvii Research Nanjing, Megvii Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3076-1786","affiliations":[{"raw_affiliation_string":"Megvii Research Nanjing, Megvii Technology, Nanjing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037595310","display_name":"Jianfeng Lu","orcid":"https://orcid.org/0000-0002-9190-507X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9190-507X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1208,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.95235901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"7006","last_page":"7018"},"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":0.9993000030517578,"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":0.996399998664856,"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":0.8297343254089355},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7293450832366943},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6891119480133057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6500124335289001},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.590656042098999},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.572731614112854},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5451182723045349},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5300787687301636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48638680577278137},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4609431028366089},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4403388202190399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3904949128627777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3353995680809021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297343254089355},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7293450832366943},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6891119480133057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500124335289001},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.590656042098999},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.572731614112854},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5451182723045349},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5300787687301636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48638680577278137},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4609431028366089},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4403388202190399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3904949128627777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3353995680809021},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tip.2020.2996736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.2996736","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1551392165","display_name":null,"funder_award_id":"BK20170856","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5081564818","display_name":null,"funder_award_id":"2017YFB1300205","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6980578983","display_name":null,"funder_award_id":"61702265","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"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W603908379","https://openalex.org/W1496650988","https://openalex.org/W1514535095","https://openalex.org/W1616462885","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1846799578","https://openalex.org/W1898560071","https://openalex.org/W1920702274","https://openalex.org/W1928906481","https://openalex.org/W1933349210","https://openalex.org/W2050398567","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2104657103","https://openalex.org/W2108598243","https://openalex.org/W2133564696","https://openalex.org/W2138011018","https://openalex.org/W2183182206","https://openalex.org/W2194775991","https://openalex.org/W2207849498","https://openalex.org/W2250539671","https://openalex.org/W2289708887","https://openalex.org/W2306952455","https://openalex.org/W2398118205","https://openalex.org/W2462457117","https://openalex.org/W2479109623","https://openalex.org/W2533598788","https://openalex.org/W2555741539","https://openalex.org/W2558914813","https://openalex.org/W2566811487","https://openalex.org/W2597655663","https://openalex.org/W2606128082","https://openalex.org/W2614580201","https://openalex.org/W2737725206","https://openalex.org/W2740620254","https://openalex.org/W2763070548","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2808178187","https://openalex.org/W2883502031","https://openalex.org/W2883805248","https://openalex.org/W2896328740","https://openalex.org/W2905546508","https://openalex.org/W2914924014","https://openalex.org/W2940925558","https://openalex.org/W2957105406","https://openalex.org/W2961018736","https://openalex.org/W2962835968","https://openalex.org/W2963015611","https://openalex.org/W2963090248","https://openalex.org/W2963148524","https://openalex.org/W2963386218","https://openalex.org/W2963407932","https://openalex.org/W2964036919","https://openalex.org/W2964308564","https://openalex.org/W2974686944","https://openalex.org/W3099903704","https://openalex.org/W4285719527","https://openalex.org/W6600609147","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6636475194","https://openalex.org/W6637242042","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6638677478","https://openalex.org/W6640376812","https://openalex.org/W6674330103","https://openalex.org/W6679434410","https://openalex.org/W6698041030","https://openalex.org/W6735377749","https://openalex.org/W6757433256","https://openalex.org/W6759022161"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Traditional":[0],"fine-grained":[1,49,83,216],"image":[2],"recognition":[3,65,84],"is":[4,33,44,135,152],"required":[5],"to":[6,23,35,62,137,139,154],"distinguish":[7],"different":[8],"subordinate":[9],"categories":[10],"(e.g.,":[11],"birds":[12],"species)":[13],"based":[14],"on":[15,215,232],"the":[16,37,67,101,106,116,120,140,156,164,170,181,222,229],"visual":[17,64,88,107,240],"cues":[18],"beneath":[19],"raw":[20,192,195],"images.":[21],"Due":[22],"both":[24,87],"small":[25],"inter-class":[26],"variations":[27],"and":[28,89,161,194,235],"large":[29],"intra-class":[30],"variations,":[31],"it":[32],"desirable":[34],"capture":[36,100],"subtle":[38],"differences":[39],"between":[40,166],"these":[41],"sub-categories,":[42],"which":[43],"crucial":[45],"but":[46,113],"challenging":[47],"for":[48,82,184],"recognition.":[50,185],"Recently,":[51],"language":[52,90,121,236],"modality":[53,108,122],"aggregation":[54],"has":[55],"been":[56],"proved":[57],"as":[58,180],"a":[59,132,149],"successful":[60],"technique":[61],"improve":[63],"in":[66,105,123,203,209],"experience.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,219],"introduce":[73],"an":[74,124],"end-to-end":[75],"trainable":[76],"Progressive":[77],"Mask":[78],"Attention":[79],"(PMA)":[80],"model":[81,95,189],"by":[85,109],"leveraging":[86],"modalities.":[91,168],"Our":[92,186],"Bi-Modal":[93,187],"PMA":[94,188],"can":[96],"not":[97],"only":[98,190],"stage-by-stage":[99],"most":[102],"discriminative":[103],"part":[104],"our":[110],"mask-based":[111],"fashion,":[112],"also":[114],"explore":[115],"out-of-visual-domain":[117],"knowledge":[118],"from":[119,143,175],"interactional":[125],"alignment":[126],"paradigm.":[127],"Specifically,":[128],"at":[129],"each":[130],"stage,":[131],"self-attention":[133],"module":[134,151],"proposed":[136,223],"attend":[138],"key":[141,157,206],"patch":[142],"images":[144,193,204],"or":[145,205,238],"text":[146,196],"descriptions.":[147],"Besides,":[148],"query-relational":[150],"designed":[153],"seize":[155],"words/phrases":[158],"of":[159,173],"texts":[160],"further":[162],"bridge":[163],"connection":[165],"two":[167],"Later,":[169],"learned":[171],"representations":[172],"bi-modality":[174,237],"multiple":[176],"stages":[177],"are":[178],"aggregated":[179],"final":[182],"features":[183],"needs":[191],"descriptions,":[197],"without":[198],"requiring":[199],"bounding":[200],"boxes/part":[201],"annotations":[202,208],"word":[207],"texts.":[210],"By":[211],"conducting":[212],"comprehensive":[213],"experiments":[214],"benchmark":[217],"datasets,":[218],"demonstrate":[220],"that":[221],"method":[224],"achieves":[225],"superior":[226],"performance":[227],"over":[228],"competing":[230],"baselines,":[231],"either":[233],"vision":[234],"single":[239],"modality.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}