{"id":"https://openalex.org/W4413157636","doi":"https://doi.org/10.1109/cvpr52734.2025.00318","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","display_name":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413157636","doi":"https://doi.org/10.1109/cvpr52734.2025.00318"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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":"Junho Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junho Kim","raw_affiliation_strings":["KAIST,Integrated Vision and Language Lab,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Integrated Vision and Language Lab,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737613","display_name":"Hyunjun Kim","orcid":"https://orcid.org/0000-0001-9257-4471"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjun Kim","raw_affiliation_strings":["KAIST,Integrated Vision and Language Lab,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Integrated Vision and Language Lab,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043134790","display_name":"Hosu Lee","orcid":"https://orcid.org/0000-0002-8702-5993"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hosu Lee","raw_affiliation_strings":["KAIST,Integrated Vision and Language Lab,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Integrated Vision and Language Lab,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["KAIST,Integrated Vision and Language Lab,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Integrated Vision and Language Lab,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.4158,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82262713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3352","last_page":"3362"},"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":0.9909999966621399,"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":0.9909999966621399,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9761000275611877,"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":0.968500018119812,"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/computer-science","display_name":"Computer science","score":0.7729430198669434},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5851592421531677},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3358214497566223},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.26596295833587646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7729430198669434},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5851592421531677},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3358214497566223},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26596295833587646}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2886641317","https://openalex.org/W2964220823","https://openalex.org/W2990503944","https://openalex.org/W3129831491","https://openalex.org/W3172806051","https://openalex.org/W3175961224","https://openalex.org/W3204588463","https://openalex.org/W4226289673","https://openalex.org/W4389519587","https://openalex.org/W4390873312","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402713111","https://openalex.org/W4402727142","https://openalex.org/W4402727764","https://openalex.org/W4402727885","https://openalex.org/W4402753903","https://openalex.org/W4402753980","https://openalex.org/W4402754220","https://openalex.org/W4402780269","https://openalex.org/W4402952458","https://openalex.org/W4402955558","https://openalex.org/W4403002096","https://openalex.org/W4404002404","https://openalex.org/W4404784276"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,19,37,171,191],"Large":[3],"Multi-Modal":[4],"Models,":[5],"applying":[6],"them":[7],"to":[8,17,30,75,92,115,118,140,173,199],"long":[9,106],"and":[10,22,34,122,137,143,165],"untrimmed":[11],"video":[12,46,53,81,146,169],"content":[13,82],"remains":[14],"challenging":[15],"due":[16],"limitations":[18,156],"context":[20],"length":[21],"substantial":[23],"memory":[24],"overhead.":[25],"These":[26],"constraints":[27],"often":[28],"lead":[29],"significant":[31,197],"information":[32],"loss":[33],"reduced":[35],"relevance":[36,179],"the":[38,42,77,98,112,155,177,181],"model":[39],"responses.":[40,183],"With":[41],"exponential":[43],"growth":[44],"of":[45,79,104,157,167,180],"data":[47],"across":[48,203],"web":[49],"platforms,":[50],"understanding":[51],"long-form":[52,194],"is":[54],"crucial":[55],"for":[56,162],"advancing":[57],"generalized":[58],"intelligence.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"introduce":[64],"SALOVA:":[65],"Segment-Augmented":[66],"LOng":[67],"Video":[68],"Assistant,":[69],"a":[70,101],"novel":[71],"video-LLM":[72],"framework":[73,153],"designed":[74],"enhance":[76],"comprehension":[78],"lengthy":[80],"through":[83],"targeted":[84],"retrieval":[85,166],"process.":[86],"We":[87,96,128],"address":[88],"two":[89],"main":[90],"challenges":[91],"achieve":[93],"it:":[94],"(i)":[95],"present":[97],"SceneWalk":[99],"dataset,":[100],"high-quality":[102],"collection":[103],"87.8K":[105],"videos,":[107,195],"each":[108],"densely":[109],"captioned":[110],"at":[111],"segment":[113],"level":[114],"enable":[116],"models":[117],"capture":[119],"scene":[120],"continuity":[121],"maintain":[123,200],"rich":[124],"descriptive":[125],"context.":[126],"(ii)":[127],"develop":[129],"robust":[130],"architectural":[131],"designs":[132],"integrating":[133],"dynamic":[134],"routing":[135],"mechanism":[136],"spatiotemporal":[138],"projector":[139],"efficiently":[141],"retrieve":[142],"process":[144],"relevant":[145,168],"segments":[147,170],"based":[148],"on":[149],"user":[150],"queries.":[151],"Our":[152],"mitigates":[154],"current":[158],"video-LMMs":[159],"by":[160],"allowing":[161],"precise":[163],"identification":[164],"response":[172],"queries,":[174],"thereby":[175],"improving":[176],"contextual":[178,201],"generated":[182],"Through":[184],"extensive":[185],"experiments,":[186],"SALOVA":[187],"demonstrates":[188],"enhanced":[189],"capability":[190,198],"processing":[192],"complex":[193],"showing":[196],"integrity":[202],"extended":[204],"sequences.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}