{"id":"https://openalex.org/W4304080420","doi":"https://doi.org/10.1145/3503161.3546971","title":"Video Grounding and Its Generalization","display_name":"Video Grounding and Its Generalization","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080420","doi":"https://doi.org/10.1145/3503161.3546971"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3546971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3546971","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100327844","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8639-3818"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009016908","display_name":"Xiaohan Lan","orcid":"https://orcid.org/0000-0001-5382-6699"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Lan","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7377","last_page":"7379"},"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":0.9976999759674072,"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":0.9807000160217285,"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/ground","display_name":"Ground","score":0.831652045249939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8261051177978516},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.7699726223945618},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.689620852470398},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6811959743499756},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6176563501358032},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.6142114400863647},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5587465167045593},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5562858581542969},{"id":"https://openalex.org/keywords/common-ground","display_name":"Common ground","score":0.4565948247909546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41523969173431396},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40933746099472046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4047551155090332},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39859914779663086},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16524183750152588},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.11955147981643677},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07935541868209839},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07055532932281494}],"concepts":[{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.831652045249939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261051177978516},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7699726223945618},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.689620852470398},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6811959743499756},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6176563501358032},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6142114400863647},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5587465167045593},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5562858581542969},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.4565948247909546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41523969173431396},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40933746099472046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4047551155090332},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39859914779663086},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16524183750152588},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.11955147981643677},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07935541868209839},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07055532932281494},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3546971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3546971","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7084459132","display_name":null,"funder_award_id":"No. 62250008, No. 62102222","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2949789546","https://openalex.org/W2963393391","https://openalex.org/W2970898753","https://openalex.org/W2973131617","https://openalex.org/W2981721414","https://openalex.org/W3004413500","https://openalex.org/W3093200502","https://openalex.org/W3093274101","https://openalex.org/W3160140554","https://openalex.org/W3216763528","https://openalex.org/W6754478056","https://openalex.org/W6762518954","https://openalex.org/W6801330939"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W4379524643","https://openalex.org/W2011027677","https://openalex.org/W2367807705","https://openalex.org/W4285233590"],"abstract_inverted_index":{"Video":[0],"grounding":[1,74],"aims":[2],"to":[3,76,113],"ground":[4],"a":[5,9,25,51,72],"sentence":[6],"query":[7],"in":[8,44],"video":[10,91],"by":[11,33],"determining":[12],"the":[13,19,34,55,64,84,102,105],"start":[14],"and":[15,27,37,57,69,110,119],"end":[16],"timestamps":[17],"of":[18,59,66,86,104,107],"semantically":[20],"matched":[21],"segment.":[22],"It":[23],"is":[24,100,111],"fundamental":[26],"essential":[28],"vision-and-language":[29],"problem":[30],"widely":[31],"investigated":[32],"research":[35],"community,":[36],"it":[38,82],"also":[39],"has":[40],"potential":[41],"values":[42],"applied":[43],"industrial":[45],"domains.":[46],"This":[47,98],"tutorial":[48],"will":[49],"give":[50],"detailed":[52],"introduction":[53],"about":[54],"development":[56],"evolution":[58],"this":[60],"task,":[61],"point":[62],"out":[63],"limitations":[65],"existing":[67],"benchmarks,":[68],"extend":[70],"such":[71],"text-based":[73],"task":[75],"more":[77],"general":[78],"scenarios,":[79],"especially":[80],"how":[81],"guides":[83],"learning":[85],"other":[87],"video-language":[88],"tasks":[89],"like":[90],"question":[92],"answering":[93],"based":[94],"on":[95],"event":[96],"grounding.":[97],"topic":[99],"at":[101],"core":[103],"scope":[106],"ACM":[108],"Multimedia,":[109],"attractive":[112],"MM":[114],"audience":[115],"from":[116],"both":[117],"academia":[118],"industry.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
