{"id":"https://openalex.org/W4403791359","doi":"https://doi.org/10.1145/3664647.3681514","title":"Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding","display_name":"Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791359","doi":"https://doi.org/10.1145/3664647.3681514"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681514","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681514","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082575036","display_name":"Jongbhin Woo","orcid":"https://orcid.org/0009-0005-4941-6837"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jongbhin Woo","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-4941-6837","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014059162","display_name":"Hyeonggon Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonggon Ryu","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-5638-1832","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Jang","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-0500-6025","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041611438","display_name":"Jae Won Cho","orcid":"https://orcid.org/0000-0001-9979-8929"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae Won Cho","raw_affiliation_strings":["Sejong University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-9979-8929","affiliations":[{"raw_affiliation_string":"Sejong University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["KAIST, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082575036"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53599854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8199","last_page":"8208"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987000226974487,"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":0.9977999925613403,"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/sentence","display_name":"Sentence","score":0.6811678409576416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.655524492263794},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.43992194533348083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41195985674858093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34710800647735596},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3201216459274292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13180533051490784},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0958506166934967}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6811678409576416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.655524492263794},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.43992194533348083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41195985674858093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34710800647735596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3201216459274292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13180533051490784},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0958506166934967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681514","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3664647.3681514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681514","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1522734439","https://openalex.org/W1958932515","https://openalex.org/W2111078031","https://openalex.org/W2143800062","https://openalex.org/W2250539671","https://openalex.org/W2889185481","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2897628926","https://openalex.org/W2962766617","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963393391","https://openalex.org/W2964089981","https://openalex.org/W2968356596","https://openalex.org/W2981750465","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3104862079","https://openalex.org/W3120889656","https://openalex.org/W3174490084","https://openalex.org/W3174873881","https://openalex.org/W3203711169","https://openalex.org/W3206019042","https://openalex.org/W3209586588","https://openalex.org/W4214893857","https://openalex.org/W4283376507","https://openalex.org/W4283819318","https://openalex.org/W4312544061","https://openalex.org/W4313011746","https://openalex.org/W4382240078","https://openalex.org/W4386065611","https://openalex.org/W4386083094","https://openalex.org/W4390872419","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4390873641","https://openalex.org/W4392910572","https://openalex.org/W4393148542","https://openalex.org/W4402753830"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"Temporal":[1],"Grounding":[2],"(VTG)":[3],"aims":[4],"to":[5,23,95,140],"identify":[6],"visual":[7,25,62,82,119],"frames":[8,26,63],"in":[9,19,129],"a":[10,38,44,81,106],"video":[11],"clip":[12],"that":[13,86,123,133],"match":[14],"text":[15,28,135],"queries.":[16],"Recent":[17],"studies":[18],"VTG":[20,130],"employ":[21],"cross-attention":[22],"correlate":[24],"and":[27,60,102,116],"queries":[29],"as":[30],"individual":[31,57,113],"token":[32],"sequences.":[33],"However,":[34],"these":[35],"approaches":[36,128],"overlook":[37],"crucial":[39],"aspect":[40],"of":[41,47,112],"the":[42,48,69,97,110,138,143,148],"problem:":[43],"holistic":[45,88,134],"understanding":[46,136],"query":[49,101],"sentence.":[50],"A":[51],"model":[52,139],"may":[53],"capture":[54],"correlations":[55],"between":[56,100],"word":[58,114],"tokens":[59,115],"arbitrary":[61],"while":[64],"possibly":[65],"missing":[66],"out":[67],"on":[68,142],"global":[70],"meaning.":[71],"To":[72],"address":[73],"this,":[74],"we":[75,108],"introduce":[76],"two":[77],"primary":[78],"contributions:":[79],"(1)":[80],"frame-level":[83],"gate":[84],"mechanism":[85],"incorporates":[87],"textual":[89],"information,":[90],"(2)":[91],"cross-modal":[92],"alignment":[93],"loss":[94],"learn":[96],"fine-grained":[98],"correlation":[99],"relevant":[103],"frames.":[104,120],"As":[105],"result,":[107],"regularize":[109],"effect":[111],"suppress":[117],"irrelevant":[118],"We":[121],"demonstrate":[122],"our":[124],"method":[125],"outperforms":[126],"state-of-the-art":[127],"benchmarks,":[131],"indicating":[132],"guides":[137],"focus":[141],"semantically":[144],"important":[145],"parts":[146],"within":[147],"video.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}