{"id":"https://openalex.org/W4379791025","doi":"https://doi.org/10.1145/3591106.3592269","title":"TsP-Tran: Two-Stage Pure Transformer for Multi-Label Image Retrieval","display_name":"TsP-Tran: Two-Stage Pure Transformer for Multi-Label Image Retrieval","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379791025","doi":"https://doi.org/10.1145/3591106.3592269"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5100785621","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-5695-4706"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Li","raw_affiliation_strings":["School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-5695-4706","affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102961135","display_name":"Chunming Guan","orcid":"https://orcid.org/0009-0002-3498-3159"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Guan","raw_affiliation_strings":["School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China"],"raw_orcid":"https://orcid.org/0009-0002-3498-3159","affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047780118","display_name":"Jiaquan Gao","orcid":"https://orcid.org/0000-0002-2983-9921"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaquan Gao","raw_affiliation_strings":["School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-2983-9921","affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information / School of Artificial Intelligence, Nanjing Normal University, China","institution_ids":["https://openalex.org/I152031979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100785621"],"corresponding_institution_ids":["https://openalex.org/I152031979"],"apc_list":null,"apc_paid":null,"fwci":0.471,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63520921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"425","last_page":"433"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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":0.9969000220298767,"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":0.7224409580230713},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.673110842704773},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6377319097518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6269145607948303},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6215870976448059},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6088293790817261},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4957936704158783},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.487016499042511},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4203811585903168},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.282645583152771},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06557950377464294},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06304088234901428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224409580230713},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.673110842704773},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6377319097518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269145607948303},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6215870976448059},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6088293790817261},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4957936704158783},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.487016499042511},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4203811585903168},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.282645583152771},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06557950377464294},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06304088234901428},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4406913046","display_name":null,"funder_award_id":"62102186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7759787049","display_name":null,"funder_award_id":"BK20200725","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1910300841","https://openalex.org/W1974647172","https://openalex.org/W1996936615","https://openalex.org/W2007972815","https://openalex.org/W2108598243","https://openalex.org/W2153273131","https://openalex.org/W2194775991","https://openalex.org/W2296096135","https://openalex.org/W2296447001","https://openalex.org/W2493727926","https://openalex.org/W2508837377","https://openalex.org/W2510911086","https://openalex.org/W2562121867","https://openalex.org/W2592249290","https://openalex.org/W2618604876","https://openalex.org/W2767252287","https://openalex.org/W2798834175","https://openalex.org/W2808254576","https://openalex.org/W2891071241","https://openalex.org/W2897656415","https://openalex.org/W2949591657","https://openalex.org/W2962786441","https://openalex.org/W2963563276","https://openalex.org/W2964280870","https://openalex.org/W3033025737","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159460504","https://openalex.org/W3199632061","https://openalex.org/W3205765174","https://openalex.org/W4214493665","https://openalex.org/W4225654135","https://openalex.org/W4234552385","https://openalex.org/W4312349930","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Image":[0],"retrieval":[1,13,64,220,251],"aims":[2],"to":[3,53,94,190,194,237],"find":[4,196],"similar":[5,199],"images":[6,197,223],"given":[7],"the":[8,18,27,36,46,54,61,72,96,106,109,121,137,171,180,202,205,209,213,219,229,239,248,274],"query.":[9],"Most":[10],"of":[11,21,48,136,142,165,269],"existing":[12],"works":[14],"are":[15,226,245,255],"based":[16,116],"on":[17,117,257],"pre-trained":[19],"model":[20,84,123,240],"single-label":[22,73],"image":[23,63,87,110,155,250,278],"classification.":[24],"In":[25,75,188],"practice,":[26],"query":[28,203],"usually":[29],"contains":[30],"more":[31],"than":[32],"one":[33],"instance,":[34],"and":[35,102,147,157,168,224,242,264],"single":[37],"label":[38,149,158],"is":[39,66,114],"far":[40],"from":[41,204],"enough":[42],"for":[43,85,105,228,276],"fully":[44,215],"depicting":[45],"attributes":[47],"an":[49,129,143,162],"open-world":[50],"image.":[51],"Due":[52],"complicated":[55],"similarity":[56],"relationships":[57],"between":[58],"multiple":[59],"semantics,":[60],"multi-label":[62,86,185,259,277],"task":[65],"not":[67],"so":[68,119],"well":[69],"solved":[70],"as":[71],"task.":[74],"this":[76],"work,":[77],"we":[78,207],"propose":[79],"a":[80,91,148,233],"two-stage":[81],"pure":[82],"Transformer":[83,92,107,138,145,173],"retrieval,":[88],"which":[89,152],"leverages":[90],"encoder":[93,139,174],"exploit":[95],"complex":[97],"dependencies":[98],"among":[99],"visual":[100,166],"features":[101,156,167],"labels.":[103],"Except":[104],"encoder,":[108],"feature":[111],"embedding":[112,150],"module":[113],"also":[115],"Transformer,":[118],"that":[120],"optimal":[122],"weights":[124],"could":[125,175],"be":[126,133,176],"learned":[127],"in":[128,179,218,232,247],"end-to-end":[130],"manner.":[131],"To":[132],"specific,":[134],"inputs":[135],"mainly":[140],"consist":[141],"Vision":[144],"branch":[146],"branch,":[151],"generates":[153],"suitable":[154],"descriptions,":[159],"respectively.":[160],"Given":[161],"input":[163],"set":[164],"text":[169],"labels,":[170],"developed":[172],"accordingly":[177],"optimized":[178],"training":[181,230],"stage":[182,231],"with":[183,201],"compressed":[184],"output":[186],"layer.":[187],"order":[189],"obtain":[191],"sufficient":[192],"outputs":[193],"accurately":[195],"containing":[198],"semantics":[200],"database,":[206],"adjust":[208],"network":[210],"by":[211],"removing":[212],"last":[214],"connected":[216],"layer":[217],"stage.":[221,252],"Specially,":[222],"labels":[225,244],"used":[227],"randomly":[234],"masked":[235],"manner":[236],"enhance":[238],"performance,":[241],"no":[243],"visible":[246],"content-based":[249],"Comprehensive":[253],"experiments":[254],"performed":[256],"three":[258],"datasets":[260],"including":[261],"MS-COCO,":[262],"NUS-WIDE":[263],"VOC2007,":[265],"demonstrating":[266],"promising":[267],"results":[268],"our":[270],"proposed":[271],"method":[272],"against":[273],"state-of-the-arts":[275],"retrieval.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}