{"id":"https://openalex.org/W4408354395","doi":"https://doi.org/10.1109/icassp49660.2025.10887901","title":"Object-Centric Discriminative Learning for Text-Based Person Retrieval","display_name":"Object-Centric Discriminative Learning for Text-Based Person Retrieval","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354395","doi":"https://doi.org/10.1109/icassp49660.2025.10887901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091626025","display_name":"Haiwen Li","orcid":"https://orcid.org/0000-0001-7223-1754"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwen Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101753965","display_name":"Delong Liu","orcid":"https://orcid.org/0000-0003-2190-1644"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Delong Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101754632","display_name":"Fei Su","orcid":"https://orcid.org/0000-0003-4245-4687"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113395474","display_name":"Zhicheng Zhao","orcid":"https://orcid.org/0009-0002-5354-8515"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.8611000180244446,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.8611000180244446,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8561999797821045,"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/T11719","display_name":"Data Quality and Management","score":0.8323000073432922,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129940032958984},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8071095943450928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6569306254386902},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5912001132965088},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38789501786231995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35688650608062744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3463078737258911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129940032958984},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8071095943450928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6569306254386902},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5912001132965088},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38789501786231995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35688650608062744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3463078737258911}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2255466643","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2963449390","https://openalex.org/W2967515867","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W3095440956","https://openalex.org/W3138516171","https://openalex.org/W3165835426","https://openalex.org/W3206868111","https://openalex.org/W4214736485","https://openalex.org/W4285296644","https://openalex.org/W4304087170","https://openalex.org/W4386065462","https://openalex.org/W4387968073","https://openalex.org/W4387968135","https://openalex.org/W4388145471","https://openalex.org/W4389331836","https://openalex.org/W4390874575","https://openalex.org/W4392909319","https://openalex.org/W4393158793","https://openalex.org/W4402702979","https://openalex.org/W4402753899","https://openalex.org/W4404612908","https://openalex.org/W4405415055","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6728374919","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763342845","https://openalex.org/W6779809370","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6798810632","https://openalex.org/W6852806981"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427"],"abstract_inverted_index":{"Text-based":[0],"person":[1,75,84],"retrieval":[2],"(TBPR)":[3],"is":[4,117,141],"a":[5,15,38,70,106],"vision-language":[6],"task":[7],"that":[8],"aims":[9],"to":[10,25,86,119],"find":[11],"specific":[12],"pedestrians":[13,97],"in":[14,33,53,98],"large":[16],"image":[17],"gallery":[18],"using":[19],"the":[20,26,31,47,50,61,92,96,102,134],"textual":[21,124],"description.":[22],"However,":[23],"due":[24],"heterogeneity":[27],"between":[28],"modalities":[29],"and":[30,59,123],"redundancy":[32],"visual":[34,122],"representations,":[35],"it":[36],"remains":[37],"challenging":[39],"task.":[40],"Existing":[41],"methods":[42],"do":[43],"not":[44],"explicitly":[45],"reduce":[46],"influence":[48],"of":[49,136],"background":[51,103],"regions":[52],"images,":[54],"inevitably":[55],"decreasing":[56],"representation":[57],"ability":[58],"reducing":[60],"image-text":[62],"matching":[63,109],"performance.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"novel":[71,107],"framework":[72],"for":[73],"text-based":[74],"retrieval,":[76],"termed":[77],"Object-Centric":[78],"Discriminative":[79],"Learning":[80],"(OCDL),":[81],"which":[82],"incorporates":[83],"masks":[85],"indicate":[87],"attentive":[88],"regions,":[89],"thereby":[90],"enhancing":[91],"model\u2019s":[93],"focus":[94],"on":[95,128],"images":[99],"while":[100],"suppressing":[101],"noise.":[104],"Additionally,":[105],"crossmodal":[108],"loss,":[110],"namely":[111],"Soft":[112],"Angular":[113],"Distribution":[114],"Matching":[115],"(SADM),":[116],"introduced":[118],"learn":[120],"discriminative":[121],"representations.":[125],"Extensive":[126],"experiments":[127],"three":[129],"widely-used":[130],"TBPR":[131],"datasets":[132],"demonstrate":[133],"effectiveness":[135],"our":[137],"approach.":[138],"The":[139],"code":[140],"available":[142],"at":[143],"https://github.com/JThuge/OCDL.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}