{"id":"https://openalex.org/W4404849321","doi":"https://doi.org/10.1109/tpami.2024.3509434","title":"DiffAct++: Diffusion Action Segmentation","display_name":"DiffAct++: Diffusion Action Segmentation","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W4404849321","doi":"https://doi.org/10.1109/tpami.2024.3509434","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030562"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3509434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3509434","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029813674","display_name":"Daochang Liu","orcid":"https://orcid.org/0000-0002-9279-7912"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daochang Liu","raw_affiliation_strings":["School of Physics, Mathematics and Computing, University of Western Australia, Crawley, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9279-7912","affiliations":[{"raw_affiliation_string":"School of Physics, Mathematics and Computing, University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101617264","display_name":"Qiyue Li","orcid":"https://orcid.org/0000-0003-0872-6677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Li","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0872-6677","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076438262","display_name":"Anh-Dung Dinh","orcid":"https://orcid.org/0009-0005-0473-9747"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anh-Dung Dinh","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101606698","display_name":"Tingting Jiang","orcid":"https://orcid.org/0000-0002-5372-0656"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Jiang","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5372-0656","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, National Biomedical Imaging Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215307","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0002-8216-1128"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8216-1128","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4756-0609","affiliations":[{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0936,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79515005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"47","issue":"3","first_page":"1644","last_page":"1659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.644717812538147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6149112582206726},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5722585320472717},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47963055968284607},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4638512134552002},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46249818801879883},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44089943170547485},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41053587198257446},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09372654557228088}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644717812538147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149112582206726},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5722585320472717},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47963055968284607},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4638512134552002},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46249818801879883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44089943170547485},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41053587198257446},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09372654557228088},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3509434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3509434","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030562","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030562","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:pure.atira.dk:publications/fdb93191-d70c-4264-a1ae-8d1d8a444c95","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/fdb93191-d70c-4264-a1ae-8d1d8a444c95","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, D, Li, Q, Dinh, A D, Jiang, T, Shah, M & Xu, C 2025, 'DiffAct++ : Diffusion Action Segmentation', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 3, pp. 1644-1659. https://doi.org/10.1109/TPAMI.2024.3509434","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7332358815","display_name":null,"funder_award_id":"FT230100549","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8682186884","display_name":null,"funder_award_id":"DP210101859","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":124,"referenced_works":["https://openalex.org/W2007964100","https://openalex.org/W2031688197","https://openalex.org/W2099614498","https://openalex.org/W2109698606","https://openalex.org/W2337252826","https://openalex.org/W2461621749","https://openalex.org/W2491875666","https://openalex.org/W2550143307","https://openalex.org/W2618009704","https://openalex.org/W2799262584","https://openalex.org/W2921678202","https://openalex.org/W2962916463","https://openalex.org/W2963524571","https://openalex.org/W2963853051","https://openalex.org/W2970662571","https://openalex.org/W2984100309","https://openalex.org/W3010531964","https://openalex.org/W3015880580","https://openalex.org/W3034373833","https://openalex.org/W3034802267","https://openalex.org/W3083550439","https://openalex.org/W3096383329","https://openalex.org/W3097033071","https://openalex.org/W3108772932","https://openalex.org/W3110257065","https://openalex.org/W3119038403","https://openalex.org/W3127601431","https://openalex.org/W3157403981","https://openalex.org/W3166363426","https://openalex.org/W3196971551","https://openalex.org/W3204193736","https://openalex.org/W3210314917","https://openalex.org/W3217030260","https://openalex.org/W4221159371","https://openalex.org/W4225147643","https://openalex.org/W4225271941","https://openalex.org/W4226000809","https://openalex.org/W4226213470","https://openalex.org/W4226270831","https://openalex.org/W4282958700","https://openalex.org/W4283009758","https://openalex.org/W4285513169","https://openalex.org/W4293327156","https://openalex.org/W4300717114","https://openalex.org/W4306250499","https://openalex.org/W4308023490","https://openalex.org/W4308234150","https://openalex.org/W4311356630","https://openalex.org/W4312050966","https://openalex.org/W4312069729","https://openalex.org/W4312322722","https://openalex.org/W4312388283","https://openalex.org/W4312626235","https://openalex.org/W4312933868","https://openalex.org/W4312982010","https://openalex.org/W4313055276","https://openalex.org/W4313071313","https://openalex.org/W4313187295","https://openalex.org/W4322716591","https://openalex.org/W4360884927","https://openalex.org/W4361856374","https://openalex.org/W4362679141","https://openalex.org/W4372263459","https://openalex.org/W4375869475","https://openalex.org/W4376610929","https://openalex.org/W4377371450","https://openalex.org/W4379927854","https://openalex.org/W4380303514","https://openalex.org/W4382464395","https://openalex.org/W4382652433","https://openalex.org/W4386050422","https://openalex.org/W4386065529","https://openalex.org/W4386075813","https://openalex.org/W4386076520","https://openalex.org/W4386076622","https://openalex.org/W4386172434","https://openalex.org/W4386302139","https://openalex.org/W4386302495","https://openalex.org/W4386597243","https://openalex.org/W4387806972","https://openalex.org/W4387917672","https://openalex.org/W4387969575","https://openalex.org/W4390871861","https://openalex.org/W4390871911","https://openalex.org/W4390872069","https://openalex.org/W4390872435","https://openalex.org/W4390872681","https://openalex.org/W4390873541","https://openalex.org/W4390873568","https://openalex.org/W4390873616","https://openalex.org/W4390873751","https://openalex.org/W4390873752","https://openalex.org/W4390874241","https://openalex.org/W4391321196","https://openalex.org/W4404295488","https://openalex.org/W6679045638","https://openalex.org/W6738279089","https://openalex.org/W6755431558","https://openalex.org/W6765775151","https://openalex.org/W6778946027","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6795288823","https://openalex.org/W6801642238","https://openalex.org/W6802442395","https://openalex.org/W6804703708","https://openalex.org/W6805547681","https://openalex.org/W6809884996","https://openalex.org/W6811008979","https://openalex.org/W6838327568","https://openalex.org/W6838844135","https://openalex.org/W6839081181","https://openalex.org/W6839691352","https://openalex.org/W6840815571","https://openalex.org/W6842958722","https://openalex.org/W6846611385","https://openalex.org/W6847925894","https://openalex.org/W6850900418","https://openalex.org/W6851861220","https://openalex.org/W6852463612","https://openalex.org/W6853598158","https://openalex.org/W6855273927","https://openalex.org/W6855980909"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Understanding":[0],"long-form":[1],"videos":[2],"requires":[3],"precise":[4],"temporal":[5],"action":[6,45,152],"segmentation.":[7,153],"While":[8],"existing":[9,142],"studies":[10],"typically":[11],"employ":[12],"multi-stage":[13],"models":[14],"that":[15,32,132],"follow":[16],"an":[17],"iterative":[18,36],"refinement":[19],"process,":[20],"we":[21,79],"present":[22],"a":[23,81,90],"novel":[24],"framework":[25],"based":[26],"on":[27,52,120,139],"the":[28,41,53,56,69,72,76,86,99,106,113,146],"denoising":[29],"diffusion":[30],"model":[31,42],"retains":[33],"this":[34,39],"core":[35],"principle.":[37],"Within":[38],"framework,":[40],"iteratively":[43],"produces":[44],"predictions":[46],"starting":[47],"with":[48,103,141],"random":[49],"noise,":[50],"conditioned":[51],"features":[54],"of":[55,65,148],"input":[57],"video.":[58],"To":[59],"effectively":[60],"capture":[61],"three":[62],"key":[63],"characteristics":[64],"human":[66],"actions,":[67],"namely":[68],"position":[70],"prior,":[71],"boundary":[73],"ambiguity,":[74],"and":[75,127],"relational":[77],"dependency,":[78],"propose":[80],"cohesive":[82],"masking":[83],"strategy":[84],"for":[85,151],"conditioning":[87],"features.":[88],"Moreover,":[89],"consistency":[91],"gradient":[92],"guidance":[93],"technique":[94],"is":[95,138],"proposed,":[96],"which":[97],"maximizes":[98],"similarity":[100],"between":[101],"outputs":[102],"or":[104,137],"without":[105],"masking,":[107],"thereby":[108],"enriching":[109],"conditional":[110],"information":[111],"during":[112],"inference":[114],"process.":[115],"Extensive":[116],"experiments":[117],"are":[118],"performed":[119],"four":[121],"datasets,":[122],"i.e.,":[123],"GTEA,":[124],"50Salads,":[125],"Breakfast,":[126],"Assembly101.":[128],"The":[129],"results":[130],"indicate":[131],"our":[133],"proposed":[134],"method":[135],"outperforms":[136],"par":[140],"state-of-the-art":[143],"techniques,":[144],"underscoring":[145],"potential":[147],"generative":[149],"approaches":[150]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}