{"id":"https://openalex.org/W4403780810","doi":"https://doi.org/10.1145/3664647.3681329","title":"Label Text-aided Hierarchical Semantics Mining for Panoramic Activity Recognition","display_name":"Label Text-aided Hierarchical Semantics Mining for Panoramic Activity Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780810","doi":"https://doi.org/10.1145/3664647.3681329"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5011105024","display_name":"Tianshan Liu","orcid":"https://orcid.org/0000-0003-3831-8893"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshan Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-8893","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kin-Man Lam","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0422-8454","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications & Peng Cheng Laboratory, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications & Peng Cheng Laboratory, Nanjing, China","institution_ids":["https://openalex.org/I41198531","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8139","last_page":"8148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/T12290","display_name":"Human Motion and Animation","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.7803211808204651},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7173778414726257},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.507689356803894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49990391731262207},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3272530436515808},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18266290426254272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803211808204651},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7173778414726257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.507689356803894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49990391731262207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3272530436515808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18266290426254272}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1522734439","https://openalex.org/W2250539671","https://openalex.org/W2259801182","https://openalex.org/W2593390416","https://openalex.org/W2810685774","https://openalex.org/W2883429621","https://openalex.org/W2896025697","https://openalex.org/W2897054934","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2974686944","https://openalex.org/W3093246508","https://openalex.org/W3095022195","https://openalex.org/W3096719817","https://openalex.org/W3105232955","https://openalex.org/W3110257409","https://openalex.org/W3144974485","https://openalex.org/W3175859725","https://openalex.org/W4246999471","https://openalex.org/W4304080498","https://openalex.org/W4312349914","https://openalex.org/W4312480274","https://openalex.org/W4312570179","https://openalex.org/W4387969092"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Panoramic":[0],"activity":[1],"recognition":[2],"is":[3,85,115],"a":[4,57,82,112],"comprehensive":[5],"yet":[6],"challenging":[7],"task":[8],"in":[9,49],"crowd":[10],"scene":[11],"understanding,":[12],"which":[13,65,118],"aims":[14],"to":[15,33,88],"concurrently":[16],"identify":[17],"multi-grained":[18],"human":[19],"behaviors,":[20],"including":[21],"individual":[22],"actions,":[23],"social":[24],"group":[25],"activities,":[26],"and":[27,78,92],"global":[28],"activities.":[29],"Previous":[30],"studies":[31],"tend":[32],"capture":[34],"cross-granularity":[35],"activity-semantics":[36],"relations":[37],"from":[38],"solely":[39],"the":[40,45,90,104,110,121,125,137,142,145],"video":[41],"input,":[42],"thus":[43],"ignoring":[44],"intrinsic":[46],"semantic":[47,73,106],"hierarchy":[48],"label-text":[50],"space.":[51],"To":[52,101],"this":[53],"end,":[54],"we":[55],"propose":[56],"label":[58,79],"text-aided":[59],"hierarchical":[60,72,83,113],"semantics":[61],"mining":[62],"(THSM)":[63],"framework,":[64],"explores":[66],"multi-level":[67],"cross-modal":[68,105],"associations":[69],"by":[70,109],"learning":[71],"alignment":[74],"between":[75],"visual":[76,91],"content":[77],"texts.":[80],"Specifically,":[81],"encoder":[84],"first":[86],"constructed":[87],"encode":[89],"text":[93],"inputs":[94],"into":[95],"semantics-aligned":[96],"representations":[97,123],"at":[98],"different":[99],"granularities.":[100],"fully":[102],"exploit":[103],"correspondence":[107],"learned":[108],"encoder,":[111],"decoder":[114],"further":[116],"developed,":[117],"progressively":[119],"integrates":[120],"lower-level":[122],"with":[124],"higher-level":[126],"contextual":[127],"knowledge":[128],"for":[129],"coarse-to-fine":[130],"action/activity":[131],"recognition.":[132],"Extensive":[133],"experimental":[134],"results":[135],"on":[136],"public":[138],"JRDB-PAR":[139],"benchmark":[140],"validate":[141],"superiority":[143],"of":[144],"proposed":[146],"THSM":[147],"framework":[148],"over":[149],"state-of-the-art":[150],"methods.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}