{"id":"https://openalex.org/W7160906003","doi":"https://doi.org/10.48550/arxiv.2605.10149","title":"Improving Temporal Action Segmentation via Constraint-Aware Decoding","display_name":"Improving Temporal Action Segmentation via Constraint-Aware Decoding","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160906003","doi":"https://doi.org/10.48550/arxiv.2605.10149"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10149","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10149","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":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.2605.10149","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068711711","display_name":"Yeo Keat Ee","orcid":"https://orcid.org/0000-0001-6935-3101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ee, Yeo Keat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135950172","display_name":"Debaditya Roy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roy, Debaditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135921194","display_name":"Chen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135920349","display_name":"Hao Richard Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090467618","display_name":"Basura Fernando","orcid":"https://orcid.org/0000-0002-6920-9916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernando, Basura","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":0.9433000087738037,"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":0.9433000087738037,"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":0.030500000342726707,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00430000014603138,"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/segmentation","display_name":"Segmentation","score":0.7132999897003174},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6309000253677368},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6226999759674072},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5659000277519226},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5561000108718872},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5116999745368958},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4715000092983246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4108999967575073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347999811172485},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7132999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6366000175476074},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6226999759674072},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5116999745368958},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4715000092983246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10149","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10149","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10149","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10149","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":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":{"Temporal":[0],"action":[1,9,22,74],"segmentation":[2,40],"(TAS)":[3],"divides":[4],"untrimmed":[5],"videos":[6],"into":[7,92],"labeled":[8],"segments.":[10],"While":[11],"fully":[12,111],"supervised":[13],"methods":[14],"have":[15],"advanced":[16],"the":[17],"field,":[18],"challenges":[19],"such":[20,70],"as":[21,71],"variability,":[23],"ambiguous":[24],"boundaries,":[25],"and":[26,77,112],"high":[27,123],"annotation":[28],"costs":[29],"remain,":[30],"especially":[31],"in":[32],"new":[33],"or":[34,103],"low-resource":[35],"domains.":[36],"Grammar-based":[37],"approaches":[38],"improve":[39],"with":[41],"structural":[42,68,118],"priors":[43,69],"but":[44],"rely":[45],"on":[46],"complex":[47],"parsing":[48],"limiting":[49],"scalability.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"a":[56,93],"lightweight,":[57],"constraint-based":[58],"refinement":[59,100],"framework":[60],"that":[61,80],"enhances":[62],"TAS":[63,114],"predictions":[64],"by":[65,116],"integrating":[66],"statistical":[67],"transition":[72],"confidence,":[73],"boundary":[75],"sets,":[76],"per-class":[78],"duration,":[79],"can":[81],"be":[82],"directly":[83],"extracted":[84],"from":[85],"annotated":[86],"data.":[87],"These":[88],"constraints":[89],"are":[90],"integrated":[91],"modified":[94],"Viterbi":[95],"decoding":[96],"algorithm,":[97],"allowing":[98],"inference-time":[99],"without":[101],"retraining":[102],"added":[104],"model":[105],"complexity.":[106],"Our":[107],"approach":[108],"improves":[109],"both":[110],"semi-supervised":[113],"models":[115],"correcting":[117],"prediction":[119],"errors":[120],"while":[121],"maintaining":[122],"efficiency.":[124],"Code":[125],"is":[126],"available":[127],"at":[128],"https://github.com/LUNAProject22/CAD":[129]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}