{"id":"https://openalex.org/W7127450832","doi":"https://doi.org/10.48550/arxiv.2602.01257","title":"Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment","display_name":"Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127450832","doi":"https://doi.org/10.48550/arxiv.2602.01257"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.01257","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124890070","display_name":"Yunchuan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ma, Yunchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010557705","display_name":"Laiyun Qing","orcid":"https://orcid.org/0000-0001-9923-5034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing, Laiyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121900670","display_name":"Guorong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guorong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065478631","display_name":"Y. Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124874073","display_name":"Yuankai Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Yuankai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124910631","display_name":"Qingming Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Qingming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124890070"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7633000016212463,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7633000016212463,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.17100000381469727,"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":0.01640000008046627,"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/boosting","display_name":"Boosting (machine learning)","score":0.8633000254631042},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.49799999594688416},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4611999988555908},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.3968999981880188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37950000166893005},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37400001287460327},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8633000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176999807357788},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.49799999594688416},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4611999988555908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3968999981880188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.01257","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.01257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01257","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.01257","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.40718013048171997,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"point-supervised":[1,78],"temporal":[2],"action":[3,157],"localization":[4,17],"has":[5],"gained":[6],"significant":[7],"attention":[8],"for":[9,75,98,159],"its":[10,203],"effective":[11],"balance":[12],"between":[13,143],"labeling":[14],"costs":[15],"and":[16,45,86,131,145,205],"accuracy.":[18],"However,":[19],"current":[20],"methods":[21],"only":[22],"consider":[23],"features":[24,53,61,125,152],"from":[25,32,54],"visual":[26,55,60,144],"inputs,":[27],"neglecting":[28],"helpful":[29],"semantic":[30,129],"information":[31],"the":[33,59,76,109,141,149,156,171,190],"text":[34],"side.":[35],"To":[36],"address":[37],"this":[38],"issue,":[39],"we":[40,94],"propose":[41],"a":[42,80,87,102,127,133,195],"Text":[43,82],"Refinement":[44,83],"Alignment":[46,90],"(TRA)":[47],"framework":[48,177,191],"that":[49,189],"effectively":[50],"utilizes":[51],"textual":[52],"descriptions":[56,97,111],"to":[57,139,179],"complement":[58],"as":[62],"they":[63],"are":[64,153],"semantically":[65],"rich.":[66],"This":[67],"is":[68],"achieved":[69],"by":[70,112],"designing":[71],"two":[72],"new":[73],"modules":[74],"original":[77],"framework:":[79],"Point-based":[81,88],"module":[84,91],"(PTR)":[85],"Multimodal":[89],"(PMA).":[92],"Specifically,":[93],"first":[95],"generate":[96],"video":[99],"frames":[100],"using":[101],"pre-trained":[103,119],"multimodal":[104,135],"model.":[105],"Next,":[106],"PTR":[107],"refines":[108],"initial":[110],"leveraging":[113],"point":[114],"annotations":[115],"together":[116],"with":[117],"multiple":[118],"models.":[120],"PMA":[121],"then":[122],"projects":[123],"all":[124],"into":[126,155],"unified":[128],"space":[130],"leverages":[132],"point-level":[134],"feature":[136],"contrastive":[137],"learning":[138],"reduce":[140],"gap":[142],"linguistic":[146],"modalities.":[147],"Last,":[148],"enhanced":[150],"multi-modal":[151],"fed":[154],"detector":[158],"precise":[160],"localization.":[161],"Extensive":[162],"experimental":[163],"results":[164],"on":[165,194],"five":[166],"widely":[167],"used":[168],"benchmarks":[169],"demonstrate":[170],"favorable":[172],"performance":[173],"of":[174],"our":[175,184],"proposed":[176],"compared":[178],"several":[180],"state-of-the-art":[181],"methods.":[182],"Moreover,":[183],"computational":[185],"overhead":[186],"analysis":[187],"shows":[188],"can":[192],"run":[193],"single":[196],"24":[197],"GB":[198],"RTX":[199],"3090":[200],"GPU,":[201],"indicating":[202],"practicality":[204],"scalability.":[206]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-02-04T00:00:00"}