{"id":"https://openalex.org/W7207865643","doi":"https://doi.org/10.48550/arxiv.2609.01654","title":"MELON: A Large-Scale Dataset for Multi-Event Text-to-Long-Video Retrieval","display_name":"MELON: A Large-Scale Dataset for Multi-Event Text-to-Long-Video Retrieval","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7207865643","doi":"https://doi.org/10.48550/arxiv.2609.01654"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.01654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01654","pdf_url":"https://arxiv.org/pdf/2609.01654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.01654","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045230148","display_name":"Chan Hur","orcid":"https://orcid.org/0000-0003-3980-4607","observed_orcids":["https://orcid.org/0000-0003-3980-4607"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hur, Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149515754","display_name":"SeungWoo Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, SeungWoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122372602","display_name":"Jeong-hun Hong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Jeong-hun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103538207","display_name":"Won Jun Oh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oh, Won Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010610758","display_name":"Hyeyoung Park","orcid":"https://orcid.org/0000-0003-0716-4385","observed_orcids":["https://orcid.org/0000-0003-0716-4385"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Hyeyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130411205","display_name":"KyungTae Lim","orcid":"https://orcid.org/0000-0002-5818-1161","observed_orcids":["https://orcid.org/0000-0002-5818-1161"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, KyungTae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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":0.006899999920278788,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/text-video-retrieval","display_name":"video-text retrieval","score":0.8389999866485596},{"id":"https://openalex.org/keywords/long-form-video","display_name":"long-form video","score":0.6790000200271606},{"id":"https://openalex.org/keywords/event-annotation","display_name":"event annotation","score":0.6200000047683716},{"id":"https://openalex.org/keywords/vision-language-alignment","display_name":"vision-language alignment","score":0.6850000023841858},{"id":"https://openalex.org/keywords/untrimmed-video","display_name":"untrimmed video","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051000237464905},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708000123500824},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.27709999680519104}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.01654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01654","pdf_url":"https://arxiv.org/pdf/2609.01654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2609.01654","doi":"https://doi.org/10.48550/arxiv.2609.01654","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.01654","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.01654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01654","pdf_url":"https://arxiv.org/pdf/2609.01654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390872455","https://openalex.org/W4404820248","https://openalex.org/W4416135629","https://openalex.org/W7220950221","https://openalex.org/W7223018162","https://openalex.org/W4416214650","https://openalex.org/W4399911523","https://openalex.org/W4416117170","https://openalex.org/W4413147612","https://openalex.org/W7221802056"],"abstract_inverted_index":{"Existing":[0],"text-video":[1,64],"retrieval":[2,27,65,121,138],"datasets":[3],"primarily":[4],"consist":[5],"of":[6,92],"short-form":[7],"clips":[8],"containing":[9],"a":[10,39,103,132,145],"single":[11,40],"dominant":[12],"event.":[13],"While":[14],"suitable":[15],"for":[16,135,150],"measuring":[17],"basic":[18],"vision-language":[19],"alignment,":[20],"they":[21],"are":[22],"limited":[23],"in":[24,95,120,153],"capturing":[25],"real-world":[26],"scenarios,":[28],"where":[29],"long-form":[30,67,141],"videos":[31,68],"naturally":[32],"contain":[33],"multiple":[34,76],"semantically":[35],"distinct":[36],"events":[37],"and":[38,90,114,127,143],"text":[41],"query":[42],"may":[43],"correspond":[44],"to":[45,62,66,110,139],"several":[46],"non-contiguous":[47],"temporal":[48],"segments.":[49],"To":[50],"bridge":[51],"this":[52],"gap,":[53],"we":[54,101],"introduce":[55],"MELON,":[56],"the":[57,124,154],"first":[58],"large-scale":[59],"dataset":[60,126],"designed":[61],"extend":[63],"featuring":[69],"complex,":[70],"multi-event":[71,93,104],"structures.":[72],"MELON":[73,125],"explicitly":[74],"annotates":[75],"event":[77],"intervals":[78],"per":[79],"video":[80],"along":[81],"with":[82],"their":[83],"corresponding":[84],"textual":[85],"descriptions,":[86],"enabling":[87],"both":[88],"training":[89],"evaluation":[91,148],"understanding":[94],"long,":[96],"untrimmed":[97],"videos.":[98],"In":[99],"addition,":[100],"propose":[102],"aware":[105],"loss":[106,130],"that":[107],"encourages":[108],"models":[109],"differentiate":[111],"between":[112],"full-event":[113],"partial-event":[115],"matches,":[116],"yielding":[117],"substantial":[118],"improvements":[119],"accuracy.":[122],"Together,":[123],"our":[128],"proposed":[129],"establish":[131],"robust":[133],"foundation":[134],"expanding":[136],"text-to-video":[137],"complex":[140],"scenarios":[142],"provide":[144],"more":[146],"realistic":[147],"setting":[149],"future":[151],"research":[152],"field.":[155]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-04T00:00:00"}