{"id":"https://openalex.org/W3034927684","doi":"https://doi.org/10.1109/icme46284.2020.9102757","title":"Multi-Task Learning Via Co-Attentive Sharing For Pedestrian Attribute Recognition","display_name":"Multi-Task Learning Via Co-Attentive Sharing For Pedestrian Attribute Recognition","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3034927684","doi":"https://doi.org/10.1109/icme46284.2020.9102757","mag":"3034927684"},"language":"en","primary_location":{"id":"doi:10.1109/icme46284.2020.9102757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"preprint","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/A5016262838","display_name":"Haitian Zeng","orcid":"https://orcid.org/0000-0001-6552-3505"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitian Zeng","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074577884","display_name":"Haizhou Ai","orcid":"https://orcid.org/0000-0002-0166-5755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Ai","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069706571","display_name":"Zijie Zhuang","orcid":"https://orcid.org/0000-0003-2132-4197"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Zhuang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016262838"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.96520781,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94065876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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":0.7775900959968567},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.694195568561554},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6558794975280762},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6272063255310059},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6230953931808472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001338958740234},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5708234310150146},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5480130910873413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5285999774932861},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.5003046989440918},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48599132895469666},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.47844910621643066},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.45124244689941406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10839542746543884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775900959968567},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.694195568561554},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6558794975280762},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6272063255310059},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6230953931808472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001338958740234},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5708234310150146},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5480130910873413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5285999774932861},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.5003046989440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48599132895469666},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.47844910621643066},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.45124244689941406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10839542746543884},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme46284.2020.9102757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme46284.2020.9102757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W262462045","https://openalex.org/W2111025459","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2410968923","https://openalex.org/W2604463754","https://openalex.org/W2605124728","https://openalex.org/W2617039999","https://openalex.org/W2624871570","https://openalex.org/W2739088263","https://openalex.org/W2752782242","https://openalex.org/W2766111649","https://openalex.org/W2798685991","https://openalex.org/W2884585870","https://openalex.org/W2896249043","https://openalex.org/W2913340405","https://openalex.org/W2914278669","https://openalex.org/W2963365374","https://openalex.org/W2963420686","https://openalex.org/W2963620099","https://openalex.org/W2963790258","https://openalex.org/W2963843116","https://openalex.org/W2963877604","https://openalex.org/W2964130064","https://openalex.org/W2964248351","https://openalex.org/W2980113592","https://openalex.org/W4297810817","https://openalex.org/W6609767918","https://openalex.org/W6684191040","https://openalex.org/W6738491513","https://openalex.org/W6739365718","https://openalex.org/W6753038380","https://openalex.org/W6754364688"],"related_works":["https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W3119773509","https://openalex.org/W4301248618","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W2165343651"],"abstract_inverted_index":{"Learning":[0],"to":[1,124],"predict":[2],"multiple":[3],"attributes":[4],"of":[5,35,85],"a":[6,9,32,61],"pedestrian":[7,106],"is":[8,54],"multi-task":[10,80],"learning":[11],"problem.":[12],"To":[13],"share":[14],"feature":[15,38,77,94,100],"representation":[16],"between":[17,48],"two":[18,105],"individual":[19],"task":[20],"networks,":[21],"conventional":[22,116],"methods":[23],"like":[24],"Cross-Stitch":[25],"[1]":[26],"and":[27,71,98,119],"Sluice":[28],"[2]":[29],"network":[30],"learn":[31],"linear":[33,41],"combination":[34,42],"features":[36],"or":[37],"subspaces.":[39],"However,":[40],"rules":[43],"out":[44],"the":[45,115,125],"complex":[46],"interdependency":[47],"channels.":[49],"Moreover,":[50],"spatial":[51,72],"information":[52],"exchanging":[53],"less-considered.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"novel":[62],"Co-Attentive":[63],"Sharing":[64],"(CAS)":[65],"module":[66,83,113],"which":[67,88],"extracts":[68],"discriminative":[69],"channels":[70,91],"regions":[73],"for":[74,92],"more":[75],"effective":[76],"sharing":[78,117],"in":[79],"learning.":[81],"The":[82],"consists":[84],"three":[86],"branches,":[87],"leverage":[89],"different":[90],"between-task":[93],"fusing,":[95],"attention":[96],"generation":[97],"task-specific":[99],"enhancing,":[101],"respectively.":[102],"Experiments":[103],"on":[104],"attribute":[107],"recognition":[108],"datasets":[109],"show":[110],"that":[111],"our":[112],"outperforms":[114],"units":[118],"achieves":[120],"superior":[121],"results":[122],"compared":[123],"state-of-the-art":[126],"approaches":[127],"using":[128],"many":[129],"metrics.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}