{"id":"https://openalex.org/W4403791754","doi":"https://doi.org/10.1145/3664647.3680731","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","display_name":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791754","doi":"https://doi.org/10.1145/3664647.3680731"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.19178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100831936","display_name":"Yang Du","orcid":"https://orcid.org/0009-0007-8636-7258"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Du","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003721747","display_name":"Yuqi Liu","orcid":"https://orcid.org/0000-0002-2119-0881"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100831936"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19752917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5260","last_page":"5269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9983999729156494,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7950476408004761},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7608681917190552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583049535751343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333394765853882},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41756531596183777},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06036245822906494}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7950476408004761},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7608681917190552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583049535751343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333394765853882},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41756531596183777},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06036245822906494},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.19178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19178","pdf_url":"https://arxiv.org/pdf/2412.19178","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.19178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19178","pdf_url":"https://arxiv.org/pdf/2412.19178","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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2078238240","https://openalex.org/W2425121537","https://openalex.org/W2625366777","https://openalex.org/W2798592524","https://openalex.org/W2883429621","https://openalex.org/W2952132648","https://openalex.org/W2963017553","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W2989322838","https://openalex.org/W2990138404","https://openalex.org/W3118473641","https://openalex.org/W3126721948","https://openalex.org/W3168640669","https://openalex.org/W3172655693","https://openalex.org/W3204588463","https://openalex.org/W3216270236","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312560592","https://openalex.org/W4313071966","https://openalex.org/W4313186260","https://openalex.org/W4382457871","https://openalex.org/W4384649091","https://openalex.org/W4385572645","https://openalex.org/W4385895960","https://openalex.org/W4386075757","https://openalex.org/W4386076010","https://openalex.org/W4386501573","https://openalex.org/W4386942867","https://openalex.org/W4387967898","https://openalex.org/W4387968067","https://openalex.org/W4387968121","https://openalex.org/W4387968399","https://openalex.org/W4387968456","https://openalex.org/W4387968500","https://openalex.org/W4387968586","https://openalex.org/W4387968589","https://openalex.org/W4387969154","https://openalex.org/W4387969779","https://openalex.org/W4388187937","https://openalex.org/W4388189856","https://openalex.org/W4388191759","https://openalex.org/W4390871765","https://openalex.org/W4390872366","https://openalex.org/W4404724811"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Cross-modal":[0],"(e.g.":[1],"image-text,":[2],"video-text)":[3],"retrieval":[4,11,21,73,150,201],"is":[5],"an":[6],"important":[7],"task":[8],"in":[9,38,45,164],"information":[10],"and":[12,86,104,109,155,167,185,202],"multimodal":[13,203],"vision-language":[14],"understanding":[15,18,204],"field.":[16],"Temporal":[17],"makes":[19],"video-text":[20,34,60,72,172,189,200],"more":[22,121],"challenging":[23],"than":[24],"image-text":[25,50],"retrieval.":[26,190],"However,":[27],"we":[28,66,147],"find":[29],"that":[30,180],"the":[31,102,160],"widely":[32],"used":[33],"benchmarks":[35],"have":[36],"shortcomings":[37],"comprehensively":[39],"assessing":[40],"abilities":[41],"of":[42,79,106,132,162,171],"models,":[43],"especially":[44],"temporal":[46],"understanding,":[47],"causing":[48],"large-scale":[49],"pre-trained":[51,61],"models":[52,173],"can":[53],"already":[54],"achieve":[55],"comparable":[56],"zero-shot":[57],"performance":[58],"with":[59,83,135],"models.":[62],"In":[63],"this":[64],"paper,":[65],"introduce":[67],"RTime,":[68,146],"a":[69,169],"novel":[70],"temporal-emphasized":[71],"dataset.":[74],"We":[75,96,115,157,191],"first":[76],"obtain":[77],"videos":[78,90,134],"actions":[80],"or":[81],"events":[82],"significant":[84],"temporality,":[85],"then":[87,97],"reverse":[88],"these":[89],"to":[91,100,119,188,197],"create":[92],"harder":[93],"negative":[94],"samples.":[95],"recruit":[98],"annotators":[99],"judge":[101],"significance":[103],"reversibility":[105],"candidate":[107],"videos,":[108],"write":[110],"captions":[111,122,137],"for":[112],"qualified":[113],"videos.":[114],"further":[116,158,198],"adopt":[117],"GPT-4":[118],"extend":[120],"based":[123],"on":[124,145,174],"human-written":[125],"captions.":[126],"Our":[127],"RTime":[128,181,194],"dataset":[129,195],"currently":[130],"consists":[131],"21k":[133],"10":[136],"per":[138],"video,":[139],"totalling":[140],"about":[141],"122":[142],"hours.":[143],"Based":[144],"propose":[148],"three":[149],"benchmark":[151,168],"tasks:":[152],"RTime-Origin,":[153],"RTime-Hard,":[154],"RTime-Binary.":[156],"enhance":[159],"use":[161],"harder-negatives":[163],"model":[165],"training,":[166],"variety":[170],"RTime.":[175],"Extensive":[176],"experiment":[177],"analysis":[178],"proves":[179],"indeed":[182],"poses":[183],"new":[184],"higher":[186],"challenges":[187],"release":[192],"our":[193],"https://github.com/qyr0403/Reversed-in-Time":[196],"advance":[199],"research.":[205]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}