{"id":"https://openalex.org/W4389815697","doi":"https://doi.org/10.1109/tip.2023.3341297","title":"Semantic-Disentangled Transformer With Noun-Verb Embedding for Compositional Action Recognition","display_name":"Semantic-Disentangled Transformer With Noun-Verb Embedding for Compositional Action Recognition","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4389815697","doi":"https://doi.org/10.1109/tip.2023.3341297","pmid":"https://pubmed.ncbi.nlm.nih.gov/38100340"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3341297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3341297","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","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/A5029702480","display_name":"Peng Huang","orcid":"https://orcid.org/0009-0003-4102-6506"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-4102-6506","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716371","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0002-0694-9458"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":["Department of Computer Science and Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040437528","display_name":"Xiangbo Shu","orcid":"https://orcid.org/0000-0003-4902-4663"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangbo Shu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4902-4663","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101280341","display_name":"Zhewei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhewei Tu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016663057","display_name":"Guangzhao Dai","orcid":"https://orcid.org/0000-0003-4111-9334"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhao Dai","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4111-9334","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":1.3827,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83923981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"297","last_page":"309"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157355546951294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6418282985687256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46203330159187317},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45469963550567627},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42772117257118225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.423710435628891},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3997317850589752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3241482973098755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3234850764274597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157355546951294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6418282985687256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46203330159187317},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45469963550567627},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42772117257118225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.423710435628891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3997317850589752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3241482973098755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3234850764274597},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3341297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3341297","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Image Processing","raw_type":"journal-article"},{"id":"pmid:38100340","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38100340","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5512729199","display_name":null,"funder_award_id":"62222207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5950360714","display_name":null,"funder_award_id":"BK20211520","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6329772822","display_name":null,"funder_award_id":"61925204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7042539249","display_name":null,"funder_award_id":"2018AAA0102002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W1944615693","https://openalex.org/W2117539524","https://openalex.org/W2126579184","https://openalex.org/W2128730107","https://openalex.org/W2337252826","https://openalex.org/W2342662179","https://openalex.org/W2507009361","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2716916105","https://openalex.org/W2736334449","https://openalex.org/W2736809457","https://openalex.org/W2739179646","https://openalex.org/W2770804203","https://openalex.org/W2806331055","https://openalex.org/W2896457183","https://openalex.org/W2896659472","https://openalex.org/W2962934715","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963315828","https://openalex.org/W2963524571","https://openalex.org/W2965373594","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2998360624","https://openalex.org/W3021013305","https://openalex.org/W3034257141","https://openalex.org/W3034572008","https://openalex.org/W3034679267","https://openalex.org/W3035413240","https://openalex.org/W3107646798","https://openalex.org/W3110854813","https://openalex.org/W3111098292","https://openalex.org/W3123784868","https://openalex.org/W3134272453","https://openalex.org/W3138516171","https://openalex.org/W3152380984","https://openalex.org/W3159212182","https://openalex.org/W3168640669","https://openalex.org/W3204588463","https://openalex.org/W3205691536","https://openalex.org/W3206930349","https://openalex.org/W3210279979","https://openalex.org/W3217102353","https://openalex.org/W3217340782","https://openalex.org/W3217364789","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4225965641","https://openalex.org/W4281752744","https://openalex.org/W4284965682","https://openalex.org/W4285588963","https://openalex.org/W4285606530","https://openalex.org/W4287557725","https://openalex.org/W4304092632","https://openalex.org/W4309157236","https://openalex.org/W4309396261","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4313186260","https://openalex.org/W4386066282","https://openalex.org/W4386076661","https://openalex.org/W6600983433","https://openalex.org/W6682864246","https://openalex.org/W6739901393","https://openalex.org/W6749916090","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6774314701","https://openalex.org/W6778883912","https://openalex.org/W6786833581","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6796494063","https://openalex.org/W6797263693","https://openalex.org/W6804204055","https://openalex.org/W6810265253","https://openalex.org/W6810842295","https://openalex.org/W6811013733","https://openalex.org/W6840478680","https://openalex.org/W6846726380","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416","https://openalex.org/W4313153715"],"abstract_inverted_index":{"Recognizing":[0],"actions":[1],"performed":[2],"on":[3,229,234,247],"unseen":[4],"objects,":[5],"known":[6],"as":[7,74,130],"Compositional":[8],"Action":[9],"Recognition":[10],"(CAR),":[11],"has":[12],"attracted":[13],"increasing":[14],"attention":[15],"in":[16,67,93,116,170,180,200],"recent":[17],"years.":[18],"The":[19],"main":[20],"challenge":[21],"is":[22],"to":[23,48,109,154,185,190,212],"overcome":[24],"the":[25,32,50,63,68,75,82,89,117,164,181,192,205,213],"distribution":[26],"shift":[27],"of":[28,53,114,208,220],"\"action-objects\"":[29],"pairs":[30],"between":[31],"training":[33],"and":[34,140,159,167,196,223,239],"testing":[35],"sets.":[36],"Previous":[37],"works":[38],"for":[39,78],"CAR":[40],"usually":[41,86],"introduce":[42],"extra":[43],"information":[44,179],"(e.g.":[45],"bounding":[46],"box)":[47],"enhance":[49],"dynamic":[51],"cues":[52],"video":[54,83],"features.":[55],"However,":[56],"these":[57],"approaches":[58],"do":[59],"not":[60],"essentially":[61],"eliminate":[62],"inherent":[64],"inductive":[65],"bias":[66],"video,":[69],"which":[70,94,132],"can":[71],"be":[72,98],"regarded":[73],"stumbling":[76],"block":[77],"model":[79],"generalization.":[80],"Because":[81],"features":[84],"are":[85,236],"extracted":[87],"from":[88],"visually":[90],"cluttered":[91],"areas":[92],"many":[95],"objects":[96],"cannot":[97],"removed":[99],"or":[100,249],"masked":[101],"explicitly.":[102],"To":[103],"this":[104,106],"end,":[105],"work":[107],"attempts":[108],"implicitly":[110],"accomplish":[111],"semantic-level":[112],"decoupling":[113],"\"object-action\"":[115],"high-level":[118,171,182],"feature":[119,166,169,195,198],"space.":[120,173],"Specifically,":[121,210],"we":[122,146,176],"propose":[123],"a":[124,187],"novel":[125],"Semantic-Decoupling":[126,141],"Transformer":[127],"framework,":[128],"dubbed":[129],"DeFormer,":[131],"contains":[133],"two":[134],"insightful":[135],"sub-modules:":[136],"Objects-Motion":[137],"Decoupler":[138],"(OMD)":[139],"Constrainer":[142],"(SDC).":[143],"In":[144,174],"OMD,":[145],"initialize":[147],"several":[148],"learnable":[149],"tokens":[150],"incorporating":[151],"annotation":[152],"priors":[153],"learn":[155],"an":[156],"instance-level":[157],"representation":[158],"then":[160],"decouple":[161],"it":[162],"into":[163],"appearance":[165,194],"motion":[168,197],"visual":[172],"SDC,":[175],"use":[177],"textual":[178],"language":[183],"space":[184],"construct":[186],"dual-contrastive":[188],"association":[189],"constrain":[191],"decoupled":[193],"obtained":[199],"OMD.":[201],"Extensive":[202],"experiments":[203],"verify":[204],"generalization":[206],"ability":[207],"DeFormer.":[209],"compared":[211],"baseline":[214],"method,":[215],"DeFormer":[216,242],"achieves":[217],"absolute":[218],"improvements":[219,233],"3%,":[221],"3.3%,":[222],"5.4%":[224],"under":[225],"three":[226],"different":[227],"settings":[228],"STH-ELSE,":[230],"while":[231],"corresponding":[232],"EPIC-KITCHENS-55":[235],"4.7%,":[237],"9.2%,":[238],"4.4%.":[240],"Besides,":[241],"gains":[243],"state-of-the-art":[244],"results":[245],"either":[246],"ground-truth":[248],"detected":[250],"annotations.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}