{"id":"https://openalex.org/W4407691335","doi":"https://doi.org/10.1109/iceic64972.2025.10879687","title":"Making Mamba Vision Temporal: Leveraging TSM for Efficient Video Understanding","display_name":"Making Mamba Vision Temporal: Leveraging TSM for Efficient Video Understanding","publication_year":2025,"publication_date":"2025-01-19","ids":{"openalex":"https://openalex.org/W4407691335","doi":"https://doi.org/10.1109/iceic64972.2025.10879687"},"language":"en","primary_location":{"id":"doi:10.1109/iceic64972.2025.10879687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-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":null,"display_name":"Seung Woo Kwak","orcid":null},"institutions":[{"id":"https://openalex.org/I896994792","display_name":"Sungkonghoe University","ror":"https://ror.org/04rg3qa61","country_code":"KR","type":"education","lineage":["https://openalex.org/I896994792"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seung Woo Kwak","raw_affiliation_strings":["Sungkonghoe University,Division of Future Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Sungkonghoe University,Division of Future Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I896994792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021748549","display_name":"Sungjun Hong","orcid":"https://orcid.org/0000-0002-0859-8006"},"institutions":[{"id":"https://openalex.org/I896994792","display_name":"Sungkonghoe University","ror":"https://ror.org/04rg3qa61","country_code":"KR","type":"education","lineage":["https://openalex.org/I896994792"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjun Hong","raw_affiliation_strings":["Sungkonghoe University,Division of Future Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Sungkonghoe University,Division of Future Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I896994792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101822470","display_name":"Sangyun Lee","orcid":"https://orcid.org/0000-0003-4842-5668"},"institutions":[{"id":"https://openalex.org/I896994792","display_name":"Sungkonghoe University","ror":"https://ror.org/04rg3qa61","country_code":"KR","type":"education","lineage":["https://openalex.org/I896994792"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangyun Lee","raw_affiliation_strings":["Sungkonghoe University,Division of Future Convergence,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Sungkonghoe University,Division of Future Convergence,Seoul,South Korea","institution_ids":["https://openalex.org/I896994792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I896994792"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01829089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8274000287055969,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8274000287055969,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.8205999732017517,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.7412999868392944,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238789796829224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4217906594276428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729875087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238789796829224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4217906594276428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729875087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic64972.2025.10879687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2963315828","https://openalex.org/W2990152177","https://openalex.org/W3092499653","https://openalex.org/W3126721948","https://openalex.org/W4205427072","https://openalex.org/W4214516465","https://openalex.org/W4379382445","https://openalex.org/W4383220250","https://openalex.org/W4385656317","https://openalex.org/W4389670852","https://openalex.org/W4390874610","https://openalex.org/W6869952813"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Transformer":[0],"and":[1,25],"Mamba-based":[2],"models":[3],"have":[4],"shown":[5],"promising":[6],"results":[7,96],"in":[8,60,117],"field":[9],"of":[10,22,91],"video":[11,125],"understanding.":[12],"However,":[13],"their":[14],"excessive":[15],"complexity":[16],"often":[17],"leads":[18],"to":[19,56,71,79,113],"the":[20,42,46,72,86,98],"problem":[21],"computational":[23],"overhead":[24],"memory":[26],"explosion.":[27],"To":[28],"address":[29],"this":[30,65],"issue,":[31],"we":[32,67,102],"propose":[33],"a":[34],"novel":[35],"model":[36],"called":[37],"Mamba":[38,74,92],"VisionTSM,":[39],"which":[40],"integrates":[41],"MambaVision":[43],"architecture":[44],"with":[45],"Temporal":[47],"Shift":[48],"Module":[49],"(TSM).":[50],"TSM":[51],"has":[52],"been":[53],"effectively":[54],"used":[55],"enable":[57],"temporal":[58,82],"modeling":[59],"2D":[61],"CNN":[62],"models.":[63],"In":[64],"work,":[66],"extend":[68],"its":[69,121],"application":[70],"hybrid":[73],"Vision":[75],"model,":[76],"allowing":[77],"it":[78],"efficiently":[80],"process":[81],"information":[83],"while":[84],"retaining":[85],"long-range":[87],"spatial":[88],"dependency":[89],"capabilities":[90],"Vision.":[93],"Through":[94],"experimental":[95],"on":[97],"Something-Something":[99],"V2":[100],"dataset,":[101],"demonstrate":[103],"that":[104],"our":[105],"approach":[106],"achieves":[107],"comparable":[108],"or":[109],"superior":[110],"performance":[111],"compared":[112],"existing":[114],"Transformer-based":[115],"approaches":[116],"action":[118],"recognition,":[119],"highlighting":[120],"potential":[122],"for":[123],"broader":[124],"understanding":[126],"tasks.":[127]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}