{"id":"https://openalex.org/W7152626797","doi":"https://doi.org/10.48550/arxiv.2604.06783","title":"Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer","display_name":"Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152626797","doi":"https://doi.org/10.48550/arxiv.2604.06783"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06783","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059997187","display_name":"Bohao Xing","orcid":"https://orcid.org/0009-0005-5924-4178"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xing, Bohao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446370","display_name":"Di Li","orcid":"https://orcid.org/0000-0002-9578-5183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052869008","display_name":"Rong Gao","orcid":"https://orcid.org/0000-0001-7935-7173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Rong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133255825","display_name":"Xin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133291925","display_name":"Heikki K\u00e4lvi\u00e4inen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K\u00e4lvi\u00e4inen, Heikki","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059997187"],"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.7139000296592712,"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"}},"topics":[{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.7139000296592712,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.1598999947309494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.016100000590085983,"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/gaze","display_name":"Gaze","score":0.8184000253677368},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5763999819755554},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46630001068115234},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4372999966144562},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3684000074863434},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3366999924182892},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.3327000141143799}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8184000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46630001068115234},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C130187892","wikidata":"https://www.wikidata.org/wiki/Q133327","display_name":"Spacetime","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2696000039577484}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06783","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06783","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":"article"},"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":{"Recently,":[0],"Transformer":[1],"has":[2],"made":[3],"significant":[4],"progress":[5],"in":[6,15,37,95],"various":[7],"vision":[8],"tasks.":[9],"To":[10],"balance":[11],"computation":[12],"and":[13,46,65,73,82,90,111,146],"efficiency":[14],"video":[16,96],"tasks,":[17],"recent":[18],"works":[19],"heavily":[20],"rely":[21],"on":[22,141],"factorized":[23],"or":[24],"window-based":[25],"self-attention.":[26],"However,":[27],"these":[28],"approaches":[29],"split":[30],"spatiotemporal":[31,122],"correlations":[32],"between":[33],"regions":[34],"of":[35,63,88],"interest":[36],"videos,":[38],"limiting":[39],"the":[40,57,61,108,125,129,142],"models'":[41],"ability":[42],"to":[43,56],"capture":[44],"motion":[45],"long-range":[47],"dependencies.":[48],"In":[49],"this":[50,100],"paper,":[51],"we":[52,102],"argue":[53],"that,":[54],"similar":[55],"human":[58],"visual":[59],"system,":[60],"importance":[62],"temporal":[64],"spatial":[66],"information":[67],"varies":[68],"across":[69],"different":[70],"time":[71,79,89],"scales,":[72],"attention":[74],"is":[75],"allocated":[76],"sparsely":[77],"over":[78],"through":[80],"glance":[81],"gaze":[83],"behavior.":[84],"Is":[85],"equal":[86],"consideration":[87],"space":[91],"crucial":[92],"for":[93],"success":[94],"tasks?":[97],"Motivated":[98],"by":[99,132],"understanding,":[101],"propose":[103],"a":[104],"dual-path":[105],"network":[106],"called":[107],"Overall":[109],"Glance":[110,117,130],"Refined":[112],"Gaze":[113,126],"(OG-ReG)":[114],"Transformer.":[115],"The":[116,152],"path":[118,127,131],"extracts":[119],"coarse-grained":[120],"overall":[121],"information,":[123],"while":[124],"supplements":[128],"providing":[133],"local":[134],"details.":[135],"Our":[136],"model":[137],"achieves":[138],"state-of-the-art":[139],"results":[140],"Kinetics-400,":[143],"Something-Something":[144],"v2,":[145],"Diving-48,":[147],"demonstrating":[148],"its":[149],"competitive":[150],"performance.":[151],"code":[153],"will":[154],"be":[155],"available":[156],"at":[157],"https://github.com/linuxsino/OG-ReG.":[158]},"counts_by_year":[],"updated_date":"2026-04-10T06:07:51.998497","created_date":"2026-04-10T00:00:00"}