{"id":"https://openalex.org/W4414981035","doi":"https://doi.org/10.1109/iccv51701.2025.02207","title":"VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-Based Group Relative Policy Optimization","display_name":"VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-Based Group Relative Policy Optimization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414981035","doi":"https://doi.org/10.1109/iccv51701.2025.02207"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.06040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinye Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinye Cao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054502150","display_name":"Hongcan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcan Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012492263","display_name":"Jiawen Qian","orcid":"https://orcid.org/0000-0003-3788-4121"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Qian","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020360628","display_name":"Guoshun Nan","orcid":"https://orcid.org/0000-0002-1987-2736"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoshun Nan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406973","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-3262-653X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112118691","display_name":"Yuqi Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Pan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008238848","display_name":"Tianhao Hou","orcid":"https://orcid.org/0000-0003-0223-7039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Hou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428967","display_name":"Xiaojuan Wang","orcid":"https://orcid.org/0000-0002-1433-2853"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojuan Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113410962","display_name":"Yutong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Gao","raw_affiliation_strings":["Minzu University of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Minzu University of China,China","institution_ids":["https://openalex.org/I145897649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23773","last_page":"23783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.6818000078201294,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.6818000078201294,"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/key","display_name":"Key (lock)","score":0.7235000133514404},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.6243000030517578},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4323999881744385},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40560001134872437},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.391400009393692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453999757766724},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7235000133514404},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.6243000030517578},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5795000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5210999846458435},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4323999881744385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40560001134872437},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.06040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06040","pdf_url":"https://arxiv.org/pdf/2510.06040","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.06040","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06040","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.06040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06040","pdf_url":"https://arxiv.org/pdf/2510.06040","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G202601664","display_name":null,"funder_award_id":"62471064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414981035.pdf","grobid_xml":"https://content.openalex.org/works/W4414981035.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"hour-long":[1],"videos":[2,72,117],"with":[3,21],"multi-modal":[4],"large":[5],"language":[6],"models":[7],"(MM-LLMs)":[8],"enriches":[9],"the":[10,50,64,128,151,154,169,176,180,202,211,218],"landscape":[11],"of":[12,36,52,66,153],"human-centered":[13],"AI":[14],"applications.":[15],"However,":[16],"for":[17,162],"end-to-end":[18],"video":[19,25,40,53],"understanding":[20,54,190],"LLMs,":[22],"uniformly":[23],"sampling":[24],"frames":[26,121],"results":[27],"in":[28,70,145,187],"LLMs":[29],"being":[30,173],"overwhelmed":[31],"by":[32,175],"a":[33,78,107,139,207],"vast":[34],"amount":[35],"irrelevant":[37],"information":[38,69,167],"as":[39],"length":[41],"increases.":[42],"Existing":[43],"hierarchical":[44,84,108],"key":[45,89,134],"frame":[46],"extraction":[47],"methods":[48],"improve":[49],"accuracy":[51,222],"but":[55],"still":[56],"face":[57],"two":[58],"critical":[59],"challenges.":[60],"1)":[61],"How":[62,76],"can":[63,77],"interference":[65],"extensive":[67],"redundant":[68],"long":[71,104,116],"be":[73],"mitigated?":[74],"2)":[75],"model":[79,203],"dynamically":[80,216],"adapt":[81],"to":[82,118,120,204],"complex":[83],"structures":[85],"while":[86,122,172],"accurately":[87],"identifying":[88],"frames?":[90],"To":[91,131],"address":[92],"these":[93],"issues,":[94],"we":[95,136],"propose":[96],"VideoMiner,":[97],"which":[98],"iteratively":[99],"segments,":[100],"captions,":[101],"and":[102,192,223],"clusters":[103],"videos,":[105],"forming":[106],"tree":[109,163,213],"structure.":[110],"The":[111,156,226],"proposed":[112,157,198],"VideoMiner":[113],"progresses":[114],"from":[115],"events":[119],"preserving":[123],"temporal":[124],"coherence,":[125],"effectively":[126],"addressing":[127],"first":[129],"challenge.":[130,182],"precisely":[132],"locate":[133],"frames,":[135],"introduce":[137],"T-GRPO,":[138],"tree-based":[140],"group":[141],"relative":[142],"policy":[143],"optimization":[144],"reinforcement":[146],"learning":[147],"method":[148],"that":[149],"guides":[150],"exploration":[152],"VideoMiner.":[155],"T-GRPO":[158,199],"is":[159,228],"specifically":[160],"designed":[161,212],"structures,":[164],"integrating":[165],"spatiotemporal":[166],"at":[168,231],"event":[170],"level":[171],"guided":[174],"question,":[177],"thus":[178],"solving":[179],"second":[181],"We":[183],"achieve":[184],"superior":[185],"performance":[186],"all":[188],"long-video":[189],"tasks":[191],"uncover":[193],"several":[194],"interesting":[195],"insights.":[196],"Our":[197],"surprisingly":[200],"incentivizes":[201],"spontaneously":[205],"generate":[206],"reasoning":[208],"chain.":[209],"Additionally,":[210],"growth":[214],"auxin":[215],"adjusts":[217],"expansion":[219],"depth,":[220],"obtaining":[221],"efficiency":[224],"gains.":[225],"code":[227],"publicly":[229],"available":[230],"https://github.com/caoxinye/VideoMiner.":[232]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}