{"id":"https://openalex.org/W4403791330","doi":"https://doi.org/10.1145/3664647.3681591","title":"Cross-modal Observation Hypothesis Inference","display_name":"Cross-modal Observation Hypothesis Inference","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791330","doi":"https://doi.org/10.1145/3664647.3681591"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681591","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":"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/A5101737334","display_name":"Mengze Li","orcid":"https://orcid.org/0000-0002-3482-234X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengze Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102542017","display_name":"Kairong Han","orcid":"https://orcid.org/0000-0003-0003-2312"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kairong Han","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109604425","display_name":"Jiahe Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahe Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760433","display_name":"Yueying Li","orcid":"https://orcid.org/0000-0003-4126-0522"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueying Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841798","display_name":"Tao Wu","orcid":"https://orcid.org/0000-0002-2567-4349"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011439390","display_name":"Jiaxu Miao","orcid":"https://orcid.org/0000-0002-4238-8475"},"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":"Jiaxu Miao","raw_affiliation_strings":["Sun Yat-Sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757087","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-0030-8289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["School of Software Technology, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Ningbo, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009749449","display_name":"Jingyuan Chen","orcid":"https://orcid.org/0000-0003-0415-6937"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101737334"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18481824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"475"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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":0.9986000061035156,"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":0.6812875270843506},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6254539489746094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6221638917922974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38847416639328003}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6812875270843506},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6254539489746094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6221638917922974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38847416639328003},{"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:10.1145/3664647.3681591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681591","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2123442489","https://openalex.org/W2593831809","https://openalex.org/W2618799552","https://openalex.org/W2751936342","https://openalex.org/W2951323451","https://openalex.org/W2963195425","https://openalex.org/W3034188691","https://openalex.org/W3166712493","https://openalex.org/W3204090293","https://openalex.org/W4206657241","https://openalex.org/W4221150420","https://openalex.org/W4221166385","https://openalex.org/W4280583915","https://openalex.org/W4281487830","https://openalex.org/W4281641249","https://openalex.org/W4284698808","https://openalex.org/W4285092328","https://openalex.org/W4285606530","https://openalex.org/W4297947337","https://openalex.org/W4304080724","https://openalex.org/W4312331087","https://openalex.org/W4312380001","https://openalex.org/W4312660844","https://openalex.org/W4312761939","https://openalex.org/W4313270780","https://openalex.org/W4385570480","https://openalex.org/W4386059972","https://openalex.org/W4386066075","https://openalex.org/W4386071468","https://openalex.org/W4386076413","https://openalex.org/W4387968456","https://openalex.org/W4389520777","https://openalex.org/W4402776467"],"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":{"Hypothesis":[0],"inference,":[1],"a":[2,69,73,116,149],"sophisticated":[3],"cognitive":[4],"process":[5],"that":[6,121],"allows":[7],"humans":[8],"to":[9,18,21,79],"construct":[10],"plausible":[11],"explanations":[12],"for":[13,137],"incomplete":[14],"observations,":[15],"is":[16],"paramount":[17],"our":[19,194],"ability":[20],"make":[22],"sense":[23],"of":[24,32,41,72,111,193],"the":[25,30,39,51,61,81,86,93,98,103,109,143,173,187,191,199],"world":[26],"around":[27],"us.":[28],"Despite":[29],"universality":[31],"this":[33,57,112],"skill,":[34],"it":[35],"remains":[36],"under-explored":[37],"within":[38],"context":[40],"multi-modal":[42],"AI,":[43],"which":[44,153],"necessitates":[45],"analyzing":[46],"observation,":[47],"recalling":[48],"information":[49],"in":[50,181],"mind,":[52],"and":[53,91,102,129,170],"generating":[54],"explanations.":[55],"In":[56],"work,":[58],"we":[59,114,147],"propose":[60,115],"<u>C</u>ross-modal":[62],"<u>O</u>bservation":[63],"hypothes<u>I</u>s":[64],"i<u>N</u>ference":[65],"task":[66],"(COIN).":[67],"Given":[68],"textual":[70,161],"description":[71],"partially":[74],"observed":[75,104],"event,":[76],"COIN":[77],"strives":[78],"recall":[80],"most":[82],"probable":[83],"event":[84,101],"from":[85],"visual":[87,99],"mind":[88,100],"(video":[89],"pool),":[90],"infer":[92],"subsequent":[94],"action":[95,174],"flow":[96,175],"connecting":[97],"textural":[105],"event.":[106],"To":[107],"advance":[108],"development":[110],"field,":[113],"large-scale":[117],"text-video":[118],"dataset,":[119,146],"Tex-COIN,":[120],"contains":[122],"39,796":[123],"meticulously":[124],"annotated":[125],"hypothesis":[126],"inference":[127,179],"examples":[128],"auxiliary":[130],"commonsense":[131],"knowledge":[132],"(appearance,":[133],"clothing,":[134],"action,":[135],"etc.)":[136],"key":[138],"video":[139],"characters.":[140],"Based":[141],"on":[142,186],"proposed":[144],"Tex-COIN":[145,188],"design":[148],"strong":[150],"baseline,":[151],"COINNet,":[152],"features":[154],"two":[155],"perspectives:":[156],"1)":[157],"aligning":[158],"temporally":[159],"displaced":[160],"observations":[162],"with":[163,176],"target":[164],"videos":[165],"via":[166],"transformer-based":[167],"multi-task":[168],"learning,":[169],"2)":[171],"inferring":[172],"non-parametric":[177],"graph-based":[178],"grounded":[180],"graph":[182],"theory.":[183],"Extensive":[184],"experiments":[185],"dataset":[189],"validate":[190],"effectiveness":[192],"COINNet":[195],"by":[196],"significantly":[197],"outperforming":[198],"state-of-the-arts.":[200]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}