{"id":"https://openalex.org/W3199057355","doi":"https://doi.org/10.48550/arxiv.2109.08847","title":"Towards High-Quality Temporal Action Detection with Sparse Proposals","display_name":"Towards High-Quality Temporal Action Detection with Sparse Proposals","publication_year":2021,"publication_date":"2021-09-18","ids":{"openalex":"https://openalex.org/W3199057355","doi":"https://doi.org/10.48550/arxiv.2109.08847","mag":"3199057355"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2109.08847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.08847","pdf_url":"https://arxiv.org/pdf/2109.08847","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.08847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032789289","display_name":"Jiannan Wu","orcid":"https://orcid.org/0009-0001-6367-6994","observed_orcids":["https://orcid.org/0009-0001-6367-6994"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002942097","display_name":"Peize Sun","orcid":"https://orcid.org/0000-0003-0636-2224","observed_orcids":["https://orcid.org/0000-0003-0636-2224"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Peize","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010085734","display_name":"Shoufa Chen","orcid":"https://orcid.org/0000-0002-6126-2595","observed_orcids":["https://orcid.org/0000-0002-6126-2595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shoufa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106671776","display_name":"Jiewen Yang","orcid":"https://orcid.org/0009-0004-1500-1556","observed_orcids":["https://orcid.org/0009-0004-1500-1556"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiewen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020877838","display_name":"Zihao Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071864144","display_name":"Lan Ma","orcid":"https://orcid.org/0000-0003-1929-6422","observed_orcids":["https://orcid.org/0000-0003-1929-6422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950","observed_orcids":["https://orcid.org/0000-0002-6685-7950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":9.999999747378752e-05,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/temporal-action-localization","display_name":"temporal action localization","score":1.0},{"id":"https://openalex.org/keywords/duration-of-action","display_name":"duration of action","score":0.3310000002384186},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5941084027290344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5180842876434326},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.509907603263855},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08917450904846191},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07444974780082703},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0616796612739563},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2109.08847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.08847","pdf_url":"https://arxiv.org/pdf/2109.08847","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2109.08847","doi":"https://doi.org/10.48550/arxiv.2109.08847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.08847","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.08847","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.08847","pdf_url":"https://arxiv.org/pdf/2109.08847","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1947481528","https://openalex.org/W2156303437","https://openalex.org/W2507009361","https://openalex.org/W2565639579","https://openalex.org/W2597958930","https://openalex.org/W2619082050","https://openalex.org/W2619947201","https://openalex.org/W2626778328","https://openalex.org/W2743706233","https://openalex.org/W2766402183","https://openalex.org/W2768282280","https://openalex.org/W2883429621","https://openalex.org/W2893390896","https://openalex.org/W2950628590","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962876901","https://openalex.org/W2963155035","https://openalex.org/W2963247196","https://openalex.org/W2963351448","https://openalex.org/W2964107628","https://openalex.org/W2964216549","https://openalex.org/W2964241181","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2990503944","https://openalex.org/W2997314266","https://openalex.org/W2997706915","https://openalex.org/W2998582438","https://openalex.org/W3034623254","https://openalex.org/W3069380482","https://openalex.org/W3092462694","https://openalex.org/W3110589170","https://openalex.org/W3119786062","https://openalex.org/W3128626728","https://openalex.org/W3131500599","https://openalex.org/W3145586615","https://openalex.org/W3164690902","https://openalex.org/W3172752666","https://openalex.org/W3173459793","https://openalex.org/W3174569083","https://openalex.org/W3176444885","https://openalex.org/W3179107710"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Temporal":[0],"Action":[1],"Detection":[2],"(TAD)":[3],"is":[4],"an":[5],"essential":[6],"and":[7,23,58,80,92,111,204,208],"challenging":[8],"topic":[9],"in":[10,104,159],"video":[11,49],"understanding,":[12],"aiming":[13],"to":[14,55,72,126,140,154,172],"localize":[15],"the":[16,25,44,64,74,100,105,112,143,160,180,193],"temporal":[17,133,161],"segments":[18],"containing":[19],"human":[20],"action":[21,26,109,117,134,174],"instances":[22,175],"predict":[24],"categories.":[27],"The":[28,164],"previous":[29],"works":[30],"greatly":[31],"rely":[32],"upon":[33],"dense":[34],"candidates":[35],"either":[36],"by":[37],"designing":[38],"varying":[39],"anchors":[40],"or":[41],"enumerating":[42],"all":[43],"combinations":[45],"of":[46,66,108,169,182],"boundaries":[47,114],"on":[48,196,199,202,206,211,214],"sequences;":[50],"therefore,":[51],"they":[52],"are":[53],"related":[54],"complicated":[56],"pipelines":[57],"sensitive":[59],"hand-crafted":[60],"designs.":[61],"Recently,":[62],"with":[63,142],"resurgence":[65],"Transformer,":[67],"query-based":[68,90,124],"methods":[69,91,125],"have":[70],"tended":[71],"become":[73],"rising":[75],"solutions":[76],"for":[77,115],"their":[78],"simplicity":[79],"flexibility.":[81],"However,":[82],"there":[83],"still":[84],"exists":[85],"a":[86,155],"performance":[87,195],"gap":[88],"between":[89],"well-established":[93],"methods.":[94],"In":[95,146],"this":[96],"paper,":[97],"we":[98,136,191],"identify":[99],"main":[101],"challenge":[102],"lies":[103],"large":[106],"variants":[107],"duration":[110],"ambiguous":[113],"short":[116],"instances;":[118],"nevertheless,":[119],"quadratic-computational":[120],"global":[121],"attention":[122],"prevents":[123],"build":[127],"multi-scale":[128],"feature":[129,158,162],"maps.":[130],"Towards":[131],"high-quality":[132],"detection,":[135],"introduce":[137],"Sparse":[138],"Proposals":[139],"interact":[141],"hierarchical":[144],"features.":[145],"our":[147,183],"method,":[148,184],"named":[149],"SP-TAD,":[150],"each":[151],"proposal":[152],"attends":[153],"local":[156,165],"segment":[157],"pyramid.":[163],"interaction":[166],"enables":[167],"utilization":[168],"high-resolution":[170],"features":[171],"preserve":[173],"details.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"effectiveness":[181],"especially":[185],"under":[186],"high":[187],"tIoU":[188],"thresholds.":[189],"E.g.,":[190],"achieve":[192],"state-of-the-art":[194],"THUMOS14":[197],"(45.7%":[198],"mAP@0.6,":[200],"33.4%":[201],"mAP@0.7":[203],"53.5%":[205],"mAP@Avg)":[207],"competitive":[209],"results":[210],"ActivityNet-1.3":[212],"(32.99%":[213],"mAP@Avg).":[215],"Code":[216],"will":[217],"be":[218],"made":[219],"available":[220],"at":[221],"https://github.com/wjn922/SP-TAD.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}