{"id":"https://openalex.org/W4200633094","doi":"https://doi.org/10.1109/icassp43922.2022.9746846","title":"Learning Semantic-Aligned Feature Representation for Text-Based Person Search","display_name":"Learning Semantic-Aligned Feature Representation for Text-Based Person Search","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4200633094","doi":"https://doi.org/10.1109/icassp43922.2022.9746846"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746846","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5009555060","display_name":"Shiping Li","orcid":"https://orcid.org/0000-0001-7639-2985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiping Li","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["Soochow University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen","Harbin Institute of Technology, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2724","last_page":"2728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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":0.8416327238082886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6545898914337158},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6536059379577637},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6133582592010498},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5825685262680054},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5779646635055542},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5413991212844849},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49289441108703613},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4843662679195404},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48272988200187683},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4569563865661621},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44899410009384155},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4477875828742981},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4233786463737488},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3965226709842682},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36993128061294556},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22224515676498413},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.19593626260757446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416327238082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6545898914337158},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6536059379577637},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6133582592010498},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5825685262680054},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5779646635055542},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5413991212844849},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49289441108703613},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4843662679195404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48272988200187683},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4569563865661621},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44899410009384155},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4477875828742981},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4233786463737488},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3965226709842682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36993128061294556},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22224515676498413},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.19593626260757446},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746846","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2883311563","https://openalex.org/W2885709146","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2938085446","https://openalex.org/W2963449390","https://openalex.org/W2963882743","https://openalex.org/W2981384185","https://openalex.org/W2997421053","https://openalex.org/W3005530336","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3093025987","https://openalex.org/W3094502228","https://openalex.org/W3095440956","https://openalex.org/W3184033217","https://openalex.org/W3189221782","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6798810632"],"related_works":["https://openalex.org/W2473933584","https://openalex.org/W2932687906","https://openalex.org/W2384506582","https://openalex.org/W1999004178","https://openalex.org/W2280723418","https://openalex.org/W2350165951","https://openalex.org/W2389537640","https://openalex.org/W1898182388","https://openalex.org/W2082085186","https://openalex.org/W2369105423"],"abstract_inverted_index":{"Text-based":[0],"person":[1,45],"search":[2],"aims":[3],"to":[4,22,72,90],"retrieve":[5],"images":[6,79],"of":[7,18,77],"a":[8,12,39,85,107,113,119],"certain":[9],"pedestrian":[10],"by":[11,56,106,112],"textual":[13,64],"description.":[14],"The":[15],"key":[16],"challenge":[17],"this":[19,35],"task":[20],"is":[21,54,104],"eliminate":[23],"the":[24,29,49,59,78,97,125],"inter-modality":[25],"gap":[26],"and":[27,63,80,93,118,127],"achieve":[28],"feature":[30,50,75,87],"alignment":[31,51,116],"across":[32,52],"modalities.":[33],"In":[34],"paper,":[36],"we":[37,67,83],"propose":[38],"semantic-aligned":[40,60,86],"embedding":[41],"method":[42,133],"for":[43],"text-based":[44],"search,":[46],"in":[47],"which":[48,103],"modalities":[53],"achieved":[55,105],"automatically":[57],"learning":[58],"visual":[61],"features":[62,95],"features.":[65],"First,":[66],"introduce":[68],"two":[69],"Transformer-based":[70],"backbones":[71],"encode":[73],"robust":[74],"representations":[76],"texts.":[81],"Second,":[82],"design":[84],"aggregation":[88],"network":[89],"adaptively":[91],"select":[92],"aggregate":[94],"with":[96],"same":[98],"semantics":[99],"into":[100],"part-aware":[101],"features,":[102],"multi-head":[108],"attention":[109],"module":[110],"constrained":[111],"cross-modality":[114],"part":[115],"loss":[117],"diversity":[120],"loss.":[121],"Experimental":[122],"results":[123],"on":[124],"CUHK-PEDES":[126],"Flickr30K":[128],"datasets":[129],"show":[130],"that":[131],"our":[132],"achieves":[134],"state-of-the-art":[135],"performances.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}