{"id":"https://openalex.org/W4413146582","doi":"https://doi.org/10.1109/cvpr52734.2025.02243","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","display_name":"Cross-modal Causal Relation Alignment for Video Question Grounding","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146582","doi":"https://doi.org/10.1109/cvpr52734.2025.02243"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5041160382","display_name":"Weixing Chen","orcid":"https://orcid.org/0009-0000-7284-5078"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weixing Chen","raw_affiliation_strings":["Sun Yat-sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051943832","display_name":"Y. Liu","orcid":"https://orcid.org/0000-0003-3615-2332"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Sun Yat-sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837461","display_name":"Binglin Chen","orcid":"https://orcid.org/0000-0003-2666-0595"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binglin Chen","raw_affiliation_strings":["Sun Yat-sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049269851","display_name":"Jie Su","orcid":"https://orcid.org/0000-0003-1071-9556"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangdon Su","raw_affiliation_strings":["Sun Yat-sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003424646","display_name":"Yongsen Zheng","orcid":"https://orcid.org/0000-0003-2692-6429"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yongsen Zheng","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041160382"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":6.5952,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96938564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24087","last_page":"24096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7514723539352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843723654747009},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6837272644042969},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.534444272518158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3632839322090149},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15277037024497986},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1305215060710907},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07378044724464417}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7514723539352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843723654747009},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6837272644042969},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.534444272518158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3632839322090149},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15277037024497986},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1305215060710907},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07378044724464417},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2606982687","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2964220823","https://openalex.org/W3036148046","https://openalex.org/W3037109418","https://openalex.org/W3175961224","https://openalex.org/W3215892227","https://openalex.org/W4283801188","https://openalex.org/W4289639375","https://openalex.org/W4304098887","https://openalex.org/W4308455108","https://openalex.org/W4312232840","https://openalex.org/W4312246181","https://openalex.org/W4312974690","https://openalex.org/W4327852044","https://openalex.org/W4379929708","https://openalex.org/W4385696173","https://openalex.org/W4386075754","https://openalex.org/W4386076176","https://openalex.org/W4386076225","https://openalex.org/W4387546363","https://openalex.org/W4388189274","https://openalex.org/W4390873373","https://openalex.org/W4402727520","https://openalex.org/W4402753952","https://openalex.org/W4403878506","https://openalex.org/W4404781975"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4234874385","https://openalex.org/W2021787609","https://openalex.org/W2390279801","https://openalex.org/W1537063595","https://openalex.org/W2323648130","https://openalex.org/W2097328689","https://openalex.org/W4391913857"],"abstract_inverted_index":{"Video":[0],"question":[1,185],"grounding":[2],"(VideoQG)":[3],"requires":[4],"models":[5,49],"to":[6,17,32,35,79],"answer":[7],"the":[8,13,19,37,44,85,108,127,172],"questions":[9],"and":[10,54,83,90,142,160,182],"simultaneously":[11],"infer":[12],"relevant":[14],"video":[15,91,140],"segments":[16,141],"support":[18],"answers.":[20],"However,":[21],"existing":[22],"VideoQG":[23,71,132,169],"methods":[24],"usually":[25],"suffer":[26],"from":[27],"spurious":[28,81],"cross-modal":[29,112],"correlations,":[30],"leading":[31],"a":[33,69],"failure":[34],"identify":[36],"dominant":[38],"visual":[39],"scenes":[40],"that":[41],"align":[42],"with":[43],"intended":[45],"question.":[46],"Moreover,":[47],"vision-language":[48],"exhibit":[50],"unfaithful":[51],"generalization":[52],"performance":[53,128],"lack":[55],"robustness":[56],"on":[57,167],"challenging":[58],"downstream":[59],"tasks":[60],"such":[61],"as":[62],"VideoQG.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"novel":[70],"framework":[72],"named":[73],"Cross-modal":[74],"Causal":[75,147],"Relation":[76],"Alignment":[77,124],"(CRA),":[78],"eliminate":[80],"correlations":[82],"improve":[84],"causal":[86],"consistency":[87],"between":[88,138],"question-answering":[89],"temporal":[92],"grounding.":[93],"Our":[94],"CRA":[95,176],"involves":[96,155],"three":[97],"essential":[98],"components:":[99],"i)":[100],"Gaussian":[101,120],"Smoothing":[102],"Grounding":[103],"(GSG)":[104],"module":[105,150],"for":[106,151,158,163],"estimating":[107],"time":[109],"interval":[110],"via":[111],"attention,":[113],"which":[114,154],"is":[115],"de-noised":[116],"by":[117,133],"an":[118],"adaptive":[119],"filter,":[121],"ii)":[122],"Cross-Modal":[123],"(CMA)":[125],"enhances":[126],"of":[129,174],"weakly":[130],"supervised":[131],"leveraging":[134],"bidirectional":[135],"contrastive":[136],"learning":[137],"estimated":[139],"QA":[143],"features,":[144],"iii)":[145],"Explicit":[146],"Intervention":[148],"(ECI)":[149],"multimodal":[152],"deconfounding,":[153],"front-door":[156],"intervention":[157,162],"vision":[159],"backdoor":[161],"language.":[164],"Extensive":[165],"experiments":[166],"two":[168],"datasets":[170],"demonstrate":[171],"superiority":[173],"our":[175],"in":[177],"discovering":[178],"visually":[179],"grounded":[180],"content":[181],"achieving":[183],"robust":[184],"reasoning.":[186],"Codes":[187],"are":[188],"available":[189],"at":[190],"https://github.com/WissingChen/CRA-GQA.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}