{"id":"https://openalex.org/W7166823400","doi":"https://doi.org/10.1016/j.imavis.2026.106093","title":"Explicitly modeling trajectories and correlations for video analysis","display_name":"Explicitly modeling trajectories and correlations for video analysis","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7166823400","doi":"https://doi.org/10.1016/j.imavis.2026.106093"},"language":"en","primary_location":{"id":"doi:10.1016/j.imavis.2026.106093","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106093","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.imavis.2026.106093","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139722878","display_name":"Hui Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105769246","display_name":"Albert Ali Salah","orcid":"https://orcid.org/0000-0001-6342-428X"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Albert Ali Salah","raw_affiliation_strings":["Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087762753","display_name":"Ronald Poppe","orcid":"https://orcid.org/0000-0002-0843-7878"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ronald Poppe","raw_affiliation_strings":["Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0843-7878","affiliations":[{"raw_affiliation_string":"Utrecht University, Department of Information and Computing Sciences, Princetonplein 5, Utrecht, 3584 CC, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087762753"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":{"value":2270,"currency":"USD","value_usd":2270},"apc_paid":{"value":2270,"currency":"USD","value_usd":2270},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86575672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"173","issue":null,"first_page":"106093","last_page":"106093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8044000267982483,"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":0.8044000267982483,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.13449999690055847,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.012500000186264515,"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/trajectory","display_name":"Trajectory","score":0.6417999863624573},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6079999804496765},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.521399974822998},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5052000284194946},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.4884999990463257},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.477400004863739},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.43309998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.652999997138977},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.43309998512268066},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.imavis.2026.106093","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106093","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.imavis.2026.106093","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106093","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6117797493934631,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2188882108","https://openalex.org/W2342662179","https://openalex.org/W2473032611","https://openalex.org/W2548527721","https://openalex.org/W2625366777","https://openalex.org/W2752782242","https://openalex.org/W2799020610","https://openalex.org/W2883780447","https://openalex.org/W2908497602","https://openalex.org/W2941870244","https://openalex.org/W2948139159","https://openalex.org/W2962858109","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963563276","https://openalex.org/W2963775820","https://openalex.org/W2964094092","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3045196480","https://openalex.org/W3092042812","https://openalex.org/W3092363664","https://openalex.org/W3106633148","https://openalex.org/W3173290664","https://openalex.org/W3175528717","https://openalex.org/W3203359574","https://openalex.org/W3216270236","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4312263092","https://openalex.org/W4312312750","https://openalex.org/W4312439137","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4312769131","https://openalex.org/W4312910375","https://openalex.org/W4312960790","https://openalex.org/W4313007769","https://openalex.org/W4379382445","https://openalex.org/W4386057769","https://openalex.org/W4386071548","https://openalex.org/W4386076398","https://openalex.org/W4386076625","https://openalex.org/W4386076650","https://openalex.org/W4390874610","https://openalex.org/W4402753666","https://openalex.org/W4410875568","https://openalex.org/W7133229819"],"related_works":[],"abstract_inverted_index":{"Video":[0],"analysis":[1],"tasks":[2],"such":[3,36,156],"as":[4,37,157],"action":[5,203],"recognition":[6,10,204],"and":[7,16,20,52,112,160,173,187,199,201,206,226],"sign":[8,194],"language":[9,195],"require":[11],"that":[12,133,180],"both":[13,56],"the":[14,104,115],"appearance":[15,30,154],"dynamics":[17],"of":[18,22,27,32,77,117,121],"objects":[19],"people":[21],"interest":[23],"are":[24],"captured.":[25],"Extraction":[26],"distinctive":[28,118],"local":[29,119],"changes":[31,155],"regions":[33,122,146],"under":[34,123],"motion,":[35],"finger":[38],"movement":[39,111],"while":[40,163],"gesturing,":[41],"is":[42,128],"often":[43],"essential":[44],"to":[45,61,68,90,147,150],"make":[46],"correct":[47],"classifications.":[48],"Without":[49],"disentangling":[50],"gross":[51,110],"fine":[53],"spatio-temporal":[54,183],"patterns,":[55],"will":[57],"be":[58],"confounded,":[59],"leading":[60],"reduced":[62],"accuracy.":[63],"We":[64,165,190],"introduce":[65],"two":[66,202],"innovations":[67,168],"tackle":[69],"this":[70],"issue.":[71],"First,":[72],"we":[73,100],"explicitly":[74],"model":[75],"motion":[76,94],"image":[78],"patches":[79],"by":[80],"temporally":[81],"aligning":[82],"visual":[83],"tokens":[84,143],"using":[85],"optical":[86],"flow.":[87],"In":[88],"addition":[89],"obtaining":[91],"a":[92,97,129,170,177,221],"coarse":[93],"representation,":[95],"for":[96],"query":[98,149],"token,":[99],"apply":[101],"self-attention":[102],"along":[103],"trajectory.":[105],"This":[106],"essentially":[107],"cancels":[108],"out":[109,135],"makes":[113],"possible":[114],"extraction":[116],"patterns":[120],"motion.":[124],"Our":[125],"second":[126],"innovation":[127],"dynamic":[130,141],"attention":[131],"mechanism":[132],"filters":[134],"irrelevant":[136],"frame":[137],"regions.":[138,189],"It":[139],"assigns":[140],"key\u2013value":[142],"from":[144,185],"correlated":[145,188],"each":[148],"focus":[151],"on":[152,192],"coordinated":[153],"joint":[158],"hand":[159],"mouth":[161],"movements":[162],"gesturing.":[164],"combine":[166],"these":[167],"in":[169,213,224],"novel":[171],"Trajectory":[172],"Correlation":[174],"(TC)":[175],"block,":[176],"hybrid":[178],"network":[179],"effectively":[181],"models":[182],"information":[184],"trajectories":[186],"experiment":[191],"four":[193],"(PHOENIX14,":[196],"PHOENIX14-T,":[197],"CSL,":[198],"CSL-Daily)":[200],"(Kinetics-400":[205],"Something-Something":[207],"V2)":[208],"datasets.":[209],"Using":[210],"TC":[211],"blocks":[212],"different":[214],"backbones":[215],"consistently":[216],"achieves":[217],"improved":[218],"performance":[219],"with":[220],"modest":[222],"increase":[223],"parameters,":[225],"30%":[227],"additional":[228],"computational":[229],"cost.":[230]},"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-07-02T00:00:00"}