{"id":"https://openalex.org/W7223943154","doi":"https://doi.org/10.48550/arxiv.2610.35516","title":"Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization","display_name":"Learning High-Quality Pseudo-Labels for Point-Supervised Temporal Action Localization","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7223943154","doi":"https://doi.org/10.48550/arxiv.2610.35516"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.35516","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35516","pdf_url":"https://arxiv.org/pdf/2610.35516","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/2610.35516","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043133170","display_name":"Zhenying Fang","orcid":"https://orcid.org/0009-0004-2002-7267","observed_orcids":["https://orcid.org/0009-0004-2002-7267"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fang, Zhenying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5043133170"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9980000257492065,"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":0.9980000257492065,"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":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00019999999494757503,"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/pseudo-label-refinement","display_name":"pseudo-label refinement","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8920000195503235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6417999863624573},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5720999836921692},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5224999785423279},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4607999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43630000948905945},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.35516","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35516","pdf_url":"https://arxiv.org/pdf/2610.35516","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.2610.35516","doi":"https://doi.org/10.48550/arxiv.2610.35516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.35516","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.35516","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35516","pdf_url":"https://arxiv.org/pdf/2610.35516","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223943154.pdf","grobid_xml":"https://content.openalex.org/works/W7223943154.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7085175231","https://openalex.org/W4387560098","https://openalex.org/W4407170463","https://openalex.org/W4413147719","https://openalex.org/W4402114907","https://openalex.org/W4399107858","https://openalex.org/W4393159954","https://openalex.org/W4385361796","https://openalex.org/W4412408187","https://openalex.org/W4386071527"],"abstract_inverted_index":{"Point-supervised":[0],"temporal":[1],"action":[2,10],"localization":[3],"(PTAL)":[4],"aims":[5],"to":[6,105,123,134],"recognize":[7],"and":[8,94,113],"localize":[9],"instances":[11],"in":[12,26],"untrimmed":[13],"videos":[14],"using":[15],"only":[16],"point-level":[17],"annotations.":[18],"Existing":[19],"pseudo-label-based":[20],"methods":[21,37],"have":[22],"made":[23],"substantial":[24],"progress":[25],"PTAL.":[27],"However,":[28],"confidence-based":[29],"initialization":[30,79],"can":[31],"overlook":[32],"well-localized":[33],"proposals.":[34],"Meanwhile,":[35],"existing":[36,153],"either":[38],"keep":[39],"pseudo-labels":[40,136],"fixed":[41],"during":[42,83],"detector":[43,84,132],"training":[44],"or":[45],"update":[46],"them":[47],"without":[48],"fully":[49],"exploiting":[50],"alternative":[51],"boundary":[52,125],"evidence":[53],"from":[54],"the":[55,119],"original":[56,121],"proposal":[57,100],"pool.":[58],"These":[59],"limitations":[60],"constrain":[61],"supervision":[62],"quality,":[63],"thereby":[64],"hindering":[65],"detection":[66,149],"performance.":[67],"To":[68],"learn":[69],"high-quality":[70],"pseudo-labels,":[71],"we":[72],"propose":[73],"a":[74],"framework":[75,87],"that":[76,144],"integrates":[77],"prior-guided":[78],"with":[80,102,130,152],"consensus-guided":[81],"refinement":[82],"training.":[85,138],"Our":[86],"comprises":[88],"two":[89],"modules:":[90],"Prior-Guided":[91],"Initialization":[92],"(PGI)":[93],"Consensus-Guided":[95],"Refinement":[96],"(CGR).":[97],"PGI":[98],"combines":[99],"confidence":[101],"point-derived":[103],"priors":[104],"establish":[106],"instance-specific":[107],"reliability":[108],"for":[109],"initial":[110],"pseudo-label":[111],"selection":[112],"candidate":[114],"retention.":[115],"CGR":[116],"continually":[117],"uses":[118],"retained":[120],"candidates":[122],"construct":[124],"targets,":[126],"combining":[127],"their":[128],"consensus":[129],"evolving":[131],"predictions":[133],"refine":[135],"throughout":[137],"Experiments":[139],"on":[140,167],"four":[141],"benchmarks":[142],"demonstrate":[143],"our":[145,157],"method":[146,158],"achieves":[147,159],"competitive":[148],"performance":[150],"compared":[151],"methods.":[154],"In":[155],"particular,":[156],"68.5\\%":[160],"average":[161],"mAP":[162],"over":[163],"tIoU":[164],"thresholds":[165],"0.1--0.7":[166],"THUMOS14,":[168],"surpassing":[169],"PseR":[170],"by":[171],"3.7":[172],"percentage":[173],"points.":[174],"Code":[175],"is":[176],"available":[177],"at":[178],"https://github.com/zhenyingfang/LHQP":[179]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-28T00:00:00"}