{"id":"https://openalex.org/W7149024810","doi":"https://doi.org/10.48550/arxiv.2604.01859","title":"Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation","display_name":"Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7149024810","doi":"https://doi.org/10.48550/arxiv.2604.01859"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01859","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107404759","display_name":"Hinako Mitsuoka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitsuoka, Hinako","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132837688","display_name":"Kazuhiro Hotta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hotta, Kazuhiro","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":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":0.9754999876022339,"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":0.9754999876022339,"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":0.004999999888241291,"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":0.002400000113993883,"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/segmentation","display_name":"Segmentation","score":0.8384000062942505},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6015999913215637},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5267999768257141},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5044000148773193},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4691999852657318}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8384000062942505},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5928000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531499981880188},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.44589999318122864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2921000123023987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2754000127315521},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01859","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,"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":"doi:10.48550/arxiv.2604.01859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01859","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2],"Temporal":[3],"Action":[4],"Segmentation":[5],"(TAS)":[6],"has":[7],"increasingly":[8],"relied":[9],"on":[10],"complex":[11],"architectures,":[12],"which":[13],"can":[14,86,134],"hinder":[15],"practical":[16],"deployment.":[17],"We":[18],"present":[19],"a":[20,48,57,62,98],"lightweight":[21],"dual-loss":[22],"training":[23],"framework":[24,82],"that":[25,51,67,131],"improves":[26,109],"fine-grained":[27],"segmentation":[28,133],"quality":[29],"with":[30],"only":[31],"one":[32],"additional":[33],"output":[34],"channel":[35],"and":[36,61,78,85,112,118],"two":[37],"auxiliary":[38],"loss":[39,50,66,100,139],"terms,":[40],"requiring":[41],"minimal":[42],"architectural":[43],"modification.":[44],"Our":[45],"approach":[46],"combines":[47],"boundary-regression":[49],"promotes":[52],"accurate":[53],"temporal":[54],"localization":[55],"via":[56],"single-channel":[58],"boundary":[59,113],"prediction":[60],"CDF-based":[63],"segment-level":[64,110],"regularization":[65],"encourages":[68],"coherent":[69],"within-segment":[70],"structure":[71],"by":[72],"matching":[73],"cumulative":[74],"distributions":[75],"over":[76],"predicted":[77],"ground-truth":[79],"segments.":[80],"The":[81],"is":[83],"architecture-agnostic":[84],"be":[87,135],"integrated":[88],"into":[89],"existing":[90],"TAS":[91],"models":[92],"(e.g.,":[93],"MS-TCN,":[94],"C2F-TCN,":[95],"FACT)":[96],"as":[97],"training-time":[99],"function.":[101],"Across":[102],"three":[103,122],"benchmark":[104],"datasets,":[105],"the":[106],"proposed":[107],"method":[108],"consistency":[111],"quality,":[114],"yielding":[115],"higher":[116],"F1":[117],"Edit":[119],"scores":[120],"across":[121],"different":[123],"models.":[124],"Frame-wise":[125],"accuracy":[126],"remains":[127],"largely":[128],"unchanged,":[129],"highlighting":[130],"precise":[132],"achieved":[136],"through":[137],"simple":[138],"design":[140],"rather":[141],"than":[142],"heavier":[143],"architectures":[144],"or":[145],"inference-time":[146],"refinements.":[147]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-04T00:00:00"}