{"id":"https://openalex.org/W4405468100","doi":"https://doi.org/10.1109/iccv51701.2025.01876","title":"VCA: Video Curious Agent for Long Video Understanding","display_name":"VCA: Video Curious Agent for Long Video Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405468100","doi":"https://doi.org/10.1109/iccv51701.2025.01876"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01876","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.10471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115505074","display_name":"Zeyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zeyuan Yang","raw_affiliation_strings":["University of Massachusetts,Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505075","display_name":"Delin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Delin Chen","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505076","display_name":"Xueyang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueyang Yu","raw_affiliation_strings":["University of Massachusetts,Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505077","display_name":"Maohao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maohao Shen","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115505078","display_name":"Chuang Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["University of Massachusetts,Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115505074"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00127264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20168","last_page":"20179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9699000120162964,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9699000120162964,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9564999938011169,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9402999877929688,"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":0.5064786672592163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5064786672592163}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01876","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:2412.10471","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10471","pdf_url":"https://arxiv.org/pdf/2412.10471","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.10471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.10471","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":"pmh:oai:arXiv.org:2412.10471","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10471","pdf_url":"https://arxiv.org/pdf/2412.10471","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"Long":[0],"video":[1,45,59,69,83,121],"understanding":[2,66],"poses":[3],"unique":[4],"challenges":[5],"due":[6],"to":[7,81,102,108],"their":[8],"temporal":[9],"complexity":[10],"and":[11,61,85,128],"low":[12],"information":[13,113],"density.":[14],"Recent":[15],"works":[16],"address":[17],"this":[18,39],"task":[19],"by":[20],"sampling":[21,74],"numerous":[22],"frames":[23],"or":[24,94],"incorporating":[25],"auxiliary":[26],"tools":[27],"using":[28],"LLMs,":[29],"both":[30],"of":[31,67,72],"which":[32],"result":[33],"in":[34],"high":[35],"computational":[36],"costs.":[37],"In":[38],"work,":[40],"we":[41],"introduce":[42],"a":[43,64,78],"curiosity-driven":[44],"agent":[46],"with":[47],"self-exploration":[48],"capability,":[49],"dubbed":[50],"as":[51],"VCA.":[52],"Built":[53],"upon":[54],"VLMs,":[55],"VCA":[56,76,96],"autonomously":[57],"navigates":[58],"segments":[60,84],"efficiently":[62],"builds":[63],"comprehensive":[65],"complex":[68],"sequences.":[70],"Instead":[71],"directly":[73],"frames,":[75],"employs":[77],"tree-search":[79],"structure":[80],"explore":[82],"collect":[86],"frames.":[87],"Rather":[88],"than":[89],"relying":[90],"on":[91,118],"external":[92],"feedback":[93],"reward,":[95],"leverages":[97],"VLM's":[98],"self-generated":[99],"intrinsic":[100],"reward":[101],"guide":[103],"its":[104],"exploration,":[105],"enabling":[106],"it":[107],"capture":[109],"the":[110],"most":[111],"crucial":[112],"for":[114],"reasoning.":[115],"Experimental":[116],"results":[117],"multiple":[119],"long":[120],"benchmarks":[122],"demonstrate":[123],"our":[124],"approach's":[125],"superior":[126],"effectiveness":[127],"efficiency.":[129]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}