{"id":"https://openalex.org/W4388185892","doi":"https://doi.org/10.1145/3581783.3613822","title":"Deconfounded Multimodal Learning for Spatio-temporal Video Grounding","display_name":"Deconfounded Multimodal Learning for Spatio-temporal Video Grounding","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388185892","doi":"https://doi.org/10.1145/3581783.3613822"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5058918328","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0002-6601-2958"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6601-2958","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083597502","display_name":"Zhanchang Ma","orcid":"https://orcid.org/0009-0006-7705-3639"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanchang Ma","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-7705-3639","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078164599","display_name":"Da Cao","orcid":"https://orcid.org/0000-0002-2611-2559"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Cao","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2611-2559","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034405338","display_name":"Yuquan Le","orcid":"https://orcid.org/0000-0001-6283-9037"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuquan Le","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-6283-9037","affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5573-6195","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6737,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71980091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7521","last_page":"7529"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/unobservable","display_name":"Unobservable","score":0.7769627571105957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766750693321228},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6188006401062012},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5671583414077759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485098361968994},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5428943037986755},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.38862618803977966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10638204216957092},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.10613301396369934}],"concepts":[{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.7769627571105957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766750693321228},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6188006401062012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5671583414077759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485098361968994},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5428943037986755},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.38862618803977966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10638204216957092},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.10613301396369934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G178670498","display_name":null,"funder_award_id":"202206130103","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7252533263","display_name":null,"funder_award_id":"61802121","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W287934474","https://openalex.org/W2194775991","https://openalex.org/W2951323451","https://openalex.org/W2960655175","https://openalex.org/W2962766617","https://openalex.org/W2963017553","https://openalex.org/W2963521717","https://openalex.org/W2963735856","https://openalex.org/W2963843782","https://openalex.org/W2964089981","https://openalex.org/W2964284374","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3035590142","https://openalex.org/W3092803144","https://openalex.org/W3093034080","https://openalex.org/W3093154363","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3152619510","https://openalex.org/W3159619744","https://openalex.org/W3166712493","https://openalex.org/W3171353004","https://openalex.org/W3174490084","https://openalex.org/W3177772862","https://openalex.org/W3204090293","https://openalex.org/W3205945847","https://openalex.org/W3207731638","https://openalex.org/W4221166385","https://openalex.org/W4226392681","https://openalex.org/W4231098138","https://openalex.org/W4304080724","https://openalex.org/W4304086137","https://openalex.org/W4304098003","https://openalex.org/W4312974690","https://openalex.org/W6600424091"],"related_works":["https://openalex.org/W2614563012","https://openalex.org/W4293337373","https://openalex.org/W2562263695","https://openalex.org/W2135187896","https://openalex.org/W2147201983","https://openalex.org/W2015518264","https://openalex.org/W2795035211","https://openalex.org/W2160108762","https://openalex.org/W1718066205","https://openalex.org/W2017034551"],"abstract_inverted_index":{"The":[0,144],"task":[1],"of":[2,126,181],"spatio-temporal":[3,34,41,160],"video":[4,15,35],"grounding":[5,36],"involves":[6],"identifying":[7],"the":[8,19,45,58,107,117,124,165,177],"spatial":[9],"and":[10,56,92,110,128,154,179],"temporal":[11],"regions":[12],"in":[13,24],"a":[14,25,48,74,81,90,135,140],"that":[16],"correspond":[17],"to":[18,43,60,63,85,122,150],"objects":[20],"or":[21,65],"actions":[22],"described":[23],"given":[26],"textual":[27],"description.":[28],"However,":[29],"current":[30],"models":[31],"used":[32],"for":[33],"often":[37,129],"rely":[38],"heavily":[39],"on":[40,106,170],"priors":[42],"make":[44],"predictions.":[46],"As":[47],"result,":[49],"they":[50],"may":[51],"suffer":[52],"from":[53],"spurious":[54],"correlations":[55],"lack":[57],"ability":[59],"generalize":[61],"well":[62,175],"new":[64],"diverse":[66,127],"scenarios.":[67],"To":[68],"overcome":[69],"this":[70,99],"limitation,":[71],"we":[72,101,132],"introduce":[73],"deconfounded":[75,152],"multimodal":[76,108],"learning":[77,153],"framework,":[78,100],"which":[79],"utilizes":[80],"structural":[82],"causal":[83,104,141],"model":[84],"treat":[86],"dataset":[87,156],"biases":[88],"as":[89],"confounder":[91],"subsequently":[93],"remove":[94],"their":[95],"confounding":[96,166],"effect.":[97],"Through":[98],"can":[102],"perform":[103],"intervention":[105],"input":[109],"derive":[111],"an":[112],"unbiased":[113,159],"estimation":[114],"formula":[115],"through":[116],"do-calculus":[118],"technique.":[119],"In":[120],"order":[121],"tackle":[123],"challenge":[125],"unobservable":[130],"confounders,":[131],"further":[133],"propose":[134],"novel":[136],"retrieval-based":[137],"approach":[138],"with":[139],"mask":[142],"mechanism.":[143],"proposed":[145,183],"method":[146],"leverages":[147],"analogical":[148],"reasoning":[149],"facilitate":[151],"mitigate":[155],"biases,":[157],"enabling":[158],"prediction":[161],"without":[162],"explicitly":[163],"modeling":[164],"factors.":[167],"Extensive":[168],"experiments":[169],"two":[171],"challenging":[172],"benchmarks":[173],"have":[174],"verified":[176],"effectiveness":[178],"rationality":[180],"our":[182],"solution.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}