{"id":"https://openalex.org/W7152432816","doi":"https://doi.org/10.1145/3774904.3792134","title":"Pedestrian-Centric Discriminative and Fine-grained Semantic Mining for Text-based Person Retrieval","display_name":"Pedestrian-Centric Discriminative and Fine-grained Semantic Mining for Text-based Person Retrieval","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152432816","doi":"https://doi.org/10.1145/3774904.3792134"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792134","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792134","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101295462","display_name":"Yuheng Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuheng Liang","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0006-7322-1340","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133257143","display_name":"Haipeng Chen","orcid":"https://orcid.org/0000-0002-9410-4120"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Chen","raw_affiliation_strings":["Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-9410-4120","affiliations":[{"raw_affiliation_string":"Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102030960","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0003-3023-3027"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-3023-3027","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089018452","display_name":"Yingda Lyu","orcid":"https://orcid.org/0000-0002-2037-6692"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingda Lyu","raw_affiliation_strings":["Public Computer Education and Research Center, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-2037-6692","affiliations":[{"raw_affiliation_string":"Public Computer Education and Research Center, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133258952","display_name":"Xue Wang","orcid":"https://orcid.org/0009-0009-5382-2423"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Wang","raw_affiliation_strings":["School of Information Science and Technology, Northeast Normal University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0009-5382-2423","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northeast Normal University, Changchun, China","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50344022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1935","last_page":"1946"},"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":0.3594000041484833,"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":0.3594000041484833,"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":0.26100000739097595,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.04050000011920929,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6873000264167786},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34700000286102295},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33649998903274536},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2825999855995178}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6873000264167786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6200000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792134","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792134","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792134","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.8005982637405396,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2268194897","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2963449390","https://openalex.org/W3175888430","https://openalex.org/W3206868111","https://openalex.org/W4206471589","https://openalex.org/W4230405732","https://openalex.org/W4283818632","https://openalex.org/W4297821751","https://openalex.org/W4304087170","https://openalex.org/W4312290555","https://openalex.org/W4386065462","https://openalex.org/W4386066311","https://openalex.org/W4387968073","https://openalex.org/W4387968696","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4390874511","https://openalex.org/W4390874695","https://openalex.org/W4393148792","https://openalex.org/W4393154149","https://openalex.org/W4393158793","https://openalex.org/W4393160134","https://openalex.org/W4395027807","https://openalex.org/W4399377915","https://openalex.org/W4402702979","https://openalex.org/W4402753821","https://openalex.org/W4402753981","https://openalex.org/W4409366125","https://openalex.org/W4413145788","https://openalex.org/W4413146183","https://openalex.org/W4413155886","https://openalex.org/W7125677483"],"related_works":[],"abstract_inverted_index":{"Text-based":[0],"Person":[1],"Retrieval":[2],"(TPR)":[3],"aims":[4],"to":[5,40],"retrieve":[6],"specific":[7],"pedestrian":[8],"images":[9],"from":[10,61,78],"a":[11,21,104,166],"gallery":[12],"based":[13],"on":[14,27,182],"the":[15,28,62,79,156,186],"given":[16],"textual":[17,139],"descriptions,":[18],"serving":[19],"as":[20,165],"fine-grained":[22,173],"instance":[23,178],"of":[24,82,188,192],"cross-modal":[25],"retrieval":[26,97,193],"Web.":[29],"Current":[30],"mainstream":[31],"approaches":[32],"primarily":[33],"leverage":[34],"pre-trained":[35],"models":[36],"and":[37,71,95,108,141,147,162,176,195],"attention":[38],"mechanisms":[39],"enhance":[41],"multi-modal":[42],"representations.":[43],"Despite":[44],"notable":[45],"progress,":[46],"they":[47],"still":[48],"struggle":[49],"with":[50,85],"two":[51,121],"major":[52],"challenges:":[53],"1)":[54,124],"Intra-instance":[55],"semantic":[56,64,74,93,174],"asymmetry,":[57],"which":[58,76,129,154],"mainly":[59],"derives":[60],"partial":[63],"relevance":[65],"conveyed":[66],"by":[67,133],"each":[68],"image-text":[69,83],"pair;":[70],"2)":[72,149],"Inter-instance":[73],"ambiguity,":[75],"arises":[77],"high":[80],"similarity":[81],"pairs":[84],"different":[86],"identities.":[87],"These":[88],"issues":[89],"result":[90],"in":[91,190],"suboptimal":[92],"alignment":[94],"degraded":[96],"accuracy.":[98],"To":[99],"this":[100],"end,":[101],"we":[102],"propose":[103],"novel":[105],"Pedestrian-Centric":[106],"Discriminative":[107],"Fine-grained":[109],"Semantic":[110,151],"Mining":[111],"(DFSM)":[112],"framework":[113],"for":[114],"TPR.":[115],"Specifically,":[116],"our":[117],"DFSM":[118,189],"method":[119],"comprises":[120],"essential":[122],"components:":[123],"Text-aware":[125],"Visual":[126],"Refinement":[127],"(TVR),":[128],"mitigates":[130],"visual":[131,196],"redundancy":[132],"selecting":[134],"semantically":[135],"relevant":[136],"patches":[137],"under":[138],"guidance,":[140],"refines":[142],"them":[143],"via":[144],"adaptive":[145],"clustering":[146],"merging;":[148],"Token-level":[150],"Alignment":[152],"(TSA),":[153],"formulates":[155],"matching":[157],"relationship":[158],"between":[159],"image":[160],"regions":[161],"text":[163],"words":[164],"conditional":[167],"transport":[168],"(CT)":[169],"problem,":[170],"effectively":[171],"mining":[172],"differences":[175],"enhancing":[177],"discrimination.":[179],"Extensive":[180],"experiments":[181],"four":[183],"benchmarks":[184],"validate":[185],"advantages":[187],"terms":[191],"accuracy":[194],"interpretability.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}