{"id":"https://openalex.org/W4416078078","doi":"https://doi.org/10.1109/tai.2025.3630621","title":"Inter and Intra-snippet Multi-head Attention With Position Offset for Action Localization and Recognition","display_name":"Inter and Intra-snippet Multi-head Attention With Position Offset for Action Localization and Recognition","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078078","doi":"https://doi.org/10.1109/tai.2025.3630621"},"language":null,"primary_location":{"id":"doi:10.1109/tai.2025.3630621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3630621","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5102791920","display_name":"Himanshu Singh","orcid":"https://orcid.org/0000-0003-4085-0168"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Himanshu Singh","raw_affiliation_strings":["Indian Institute of Technology Jammu, Jammu, India","Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India"],"raw_orcid":"https://orcid.org/0000-0003-4085-0168","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]},{"raw_affiliation_string":"Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030252907","display_name":"Khanjan Choudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Khanjan Choudhury","raw_affiliation_strings":["Indian Institute of Technology Jammu, Jammu, India","Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India"],"raw_orcid":"https://orcid.org/0009-0009-4430-7323","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]},{"raw_affiliation_string":"Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026675739","display_name":"Badri Narayan Subudhi","orcid":"https://orcid.org/0000-0002-4378-0065"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Badri Narayan Subudhi","raw_affiliation_strings":["Indian Institute of Technology Jammu, Jammu, India","Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India"],"raw_orcid":"https://orcid.org/0000-0002-4378-0065","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]},{"raw_affiliation_string":"Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102827377","display_name":"Vinit Jakhetiya","orcid":"https://orcid.org/0000-0002-2593-397X"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinit Jakhetiya","raw_affiliation_strings":["Indian Institute of Technology Jammu, Jammu, India","Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India"],"raw_orcid":"https://orcid.org/0000-0002-8325-4908","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jammu, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]},{"raw_affiliation_string":"Indian Institute of Technology Jammu, NH44, Nagrota, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005180011","display_name":"T. Veerakumar","orcid":"https://orcid.org/0000-0001-9084-1847"},"institutions":[{"id":"https://openalex.org/I4210109276","display_name":"National Institute of Technology Goa","ror":"https://ror.org/01vmfpj79","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210109276"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"T. Veerakumar","raw_affiliation_strings":["National Institute of Technology Goa, Goa, India","National Institute of Technology Goa, Farmagudi, Ponda, Goa, India"],"raw_orcid":"https://orcid.org/0000-0001-9084-1847","affiliations":[{"raw_affiliation_string":"National Institute of Technology Goa, Goa, India","institution_ids":["https://openalex.org/I4210109276"]},{"raw_affiliation_string":"National Institute of Technology Goa, Farmagudi, Ponda, Goa, India","institution_ids":["https://openalex.org/I4210109276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102791920"],"corresponding_institution_ids":["https://openalex.org/I4210127441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31264046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"5","first_page":"3018","last_page":"3030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9822999835014343,"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":0.9822999835014343,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.0013000000035390258,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.0012000000569969416,"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/offset","display_name":"Offset (computer science)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.42170000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.692300021648407},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.42170000076293945},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3125},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3630621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3630621","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2096108608","https://openalex.org/W2096300942","https://openalex.org/W2105880637","https://openalex.org/W2127878586","https://openalex.org/W2604113307","https://openalex.org/W2755876276","https://openalex.org/W2884293275","https://openalex.org/W2895240652","https://openalex.org/W2903955835","https://openalex.org/W2948229620","https://openalex.org/W2952435096","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963287896","https://openalex.org/W2963524571","https://openalex.org/W2964216549","https://openalex.org/W2983918066","https://openalex.org/W2984478308","https://openalex.org/W2984619425","https://openalex.org/W2986407524","https://openalex.org/W2998702159","https://openalex.org/W3035251589","https://openalex.org/W3035585099","https://openalex.org/W3109715102","https://openalex.org/W3109986575","https://openalex.org/W3128626728","https://openalex.org/W3162617744","https://openalex.org/W3173212682","https://openalex.org/W3173459793","https://openalex.org/W3173698268","https://openalex.org/W3174421047","https://openalex.org/W3174511093","https://openalex.org/W3178036208","https://openalex.org/W3202076256","https://openalex.org/W3203848195","https://openalex.org/W3207927851","https://openalex.org/W3214808272","https://openalex.org/W4205415396","https://openalex.org/W4283810887","https://openalex.org/W4312508181","https://openalex.org/W4312960790","https://openalex.org/W4313024697","https://openalex.org/W4313185587","https://openalex.org/W4319992862","https://openalex.org/W4385245566","https://openalex.org/W4386076085","https://openalex.org/W4388430274","https://openalex.org/W4393206831","https://openalex.org/W4400726480","https://openalex.org/W4400770637","https://openalex.org/W4402753877","https://openalex.org/W4403002315","https://openalex.org/W4404893007","https://openalex.org/W4413146733"],"related_works":[],"abstract_inverted_index":{"Numerous":[0],"studies":[1],"have":[2],"focused":[3],"on":[4,35,171,185,193,205,211],"action":[5,40,69,99,106,130],"localization":[6,41,107,133],"and":[7,67,79,92,112,174,187,207],"recognition;":[8],"however,":[9],"their":[10],"performance":[11,148],"suffers":[12],"when":[13],"applied":[14],"to":[15,20,38,86,115],"weakly":[16],"supervised":[17],"scenarios,":[18],"leading":[19],"poor":[21],"or":[22],"rapidly":[23],"declining":[24],"results.":[25],"This":[26],"article":[27],"introduces":[28],"an":[29,105,180,188],"efficient":[30],"deep":[31],"learning":[32],"architecture":[33],"based":[34],"multi-head":[36,81],"attention":[37],"enhance":[39,116],"in":[42,61],"untrimmed":[43],"videos.":[44],"Our":[45,177],"proposed":[46,143,151,218],"algorithm":[47,178],"comprises":[48],"three":[49],"stages.":[50],"Initially,":[51],"a":[52],"short-snippet":[53],"enhancement":[54],"(SSE)":[55],"sampling":[56],"module":[57],"captures":[58],"intrinsic":[59],"details":[60],"video":[62,95],"frames,":[63],"adeptly":[64],"balancing":[65],"short-term":[66],"long-term":[68],"contributions":[70],"for":[71],"improved":[72],"localization.":[73],"The":[74,101],"second":[75],"stage":[76,103],"employs":[77],"inter-snippet":[78],"intra-snippet":[80],"attention,":[82],"incorporating":[83],"positional":[84],"offset,":[85],"capture":[87],"spatio-temporal":[88],"dependencies":[89],"among":[90],"videos":[91],"within":[93],"individual":[94],"snippets,":[96],"precisely":[97],"identifying":[98],"boundaries.":[100],"third":[102],"integrates":[104],"network":[108],"with":[109,200],"uncertainty-guided":[110],"pseudo-instance-level":[111],"video-level":[113],"losses":[114],"performance,":[117],"mitigating":[118],"the":[119,139,147,150,159,168,172,214,217],"impact":[120],"of":[121,141,149,162,183,191,216],"noisy":[122],"labels.":[123],"A":[124],"multi-step":[125],"updating":[126],"process":[127],"progressively":[128],"refines":[129],"proposals,":[131],"augmenting":[132],"precision.":[134],"<p":[135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">To":[137],"demonstrate":[138],"effectiveness":[140],"our":[142,198],"scheme,":[144],"we":[145,196],"evaluate":[146],"scheme":[152],"using":[153],"mean":[154],"average":[155],"precision":[156],"(mAP)":[157],"over":[158,164],"different":[160],"thresholds":[161],"Intersection":[163],"Union":[165],"(IoU)":[166],"as":[167],"evaluation":[169],"measure":[170],"\u201cTHUMOS14\u201d":[173,186,206],"\u201cActivityNet-v1.3\u201d":[175],"datasets.":[176],"achieves":[179],"mAP":[181,189],"value":[182,190],"45.20%":[184],"25.24%":[192],"\u201cActivityNet-v1.3.":[194],"Furthermore,":[195],"compare":[197],"technique":[199],"twenty-four":[201],"state-of-the-art":[202],"(SOTA)":[203],"techniques":[204,210],"eleven":[208],"SOTA":[209],"\u201cActivityNet-v1.3\u201d,":[212],"confirming":[213],"superiority":[215],"scheme.":[219]},"counts_by_year":[],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-11-10T00:00:00"}