{"id":"https://openalex.org/W4387968116","doi":"https://doi.org/10.1145/3581783.3612504","title":"Curriculum-Listener: Consistency- and Complementarity-Aware Audio-Enhanced Temporal Sentence Grounding","display_name":"Curriculum-Listener: Consistency- and Complementarity-Aware Audio-Enhanced Temporal Sentence Grounding","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968116","doi":"https://doi.org/10.1145/3581783.3612504"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612504","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612504","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612504","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 31st 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://dl.acm.org/doi/pdf/10.1145/3581783.3612504","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004625583","display_name":"Houlun Chen","orcid":"https://orcid.org/0009-0006-7749-7328"},"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":true,"raw_author_name":"Houlun Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"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"],"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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"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":"Hong Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028258340","display_name":"Xuguang Duan","orcid":"https://orcid.org/0000-0001-9108-9618"},"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":"Xuguang Duan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039477812","display_name":"Jia Jia","orcid":"https://orcid.org/0009-0005-8449-278X"},"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":"Jia Jia","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, 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"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004625583"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.1584,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88732917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3117","last_page":"3128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8022534251213074},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.6868054866790771},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5895972847938538},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5091411471366882},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.494773805141449},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4585343301296234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4549115002155304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4158177971839905},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34679877758026123},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08853334188461304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022534251213074},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.6868054866790771},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5895972847938538},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5091411471366882},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.494773805141449},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4585343301296234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4549115002155304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4158177971839905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34679877758026123},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08853334188461304},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612504","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612504","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612504","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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612504","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612504","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612504","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 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1557924762","display_name":null,"funder_award_id":"TITAN X","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"},{"id":"https://openalex.org/G1570076315","display_name":null,"funder_award_id":"BNR2023RC01003,BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3720940119","display_name":null,"funder_award_id":"2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7661645822","display_name":null,"funder_award_id":"62250008,62222209,62102222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968116.pdf","grobid_xml":"https://content.openalex.org/works/W4387968116.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2250539671","https://openalex.org/W2296073425","https://openalex.org/W2593116425","https://openalex.org/W2620239873","https://openalex.org/W2747329762","https://openalex.org/W2798354744","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963393391","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970401629","https://openalex.org/W2972758308","https://openalex.org/W2997429269","https://openalex.org/W2997762001","https://openalex.org/W2999905431","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3035333188","https://openalex.org/W3035339529","https://openalex.org/W3035640828","https://openalex.org/W3092739351","https://openalex.org/W3094550259","https://openalex.org/W3096935578","https://openalex.org/W3142849873","https://openalex.org/W3160264863","https://openalex.org/W3173161217","https://openalex.org/W3174364033","https://openalex.org/W3176201273","https://openalex.org/W3176763654","https://openalex.org/W3178457761","https://openalex.org/W3180476551","https://openalex.org/W3200924860","https://openalex.org/W3209586588","https://openalex.org/W3211772574","https://openalex.org/W3212687458","https://openalex.org/W3214448253","https://openalex.org/W4221148502","https://openalex.org/W4281487830","https://openalex.org/W4284685693","https://openalex.org/W4298364821","https://openalex.org/W4304083155","https://openalex.org/W4312544061","https://openalex.org/W4312639100","https://openalex.org/W4312653797","https://openalex.org/W4312689520","https://openalex.org/W4312941859","https://openalex.org/W4320008746","https://openalex.org/W4327668311","https://openalex.org/W6601250092","https://openalex.org/W6792244340","https://openalex.org/W6798195429"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"Temporal":[0],"Sentence":[1],"Grounding":[2],"aims":[3],"to":[4,52,88,108,120],"retrieve":[5],"a":[6,10,97,141,154,160],"video":[7],"moment":[8],"given":[9],"natural":[11],"language":[12],"query.":[13],"Most":[14],"existing":[15],"literature":[16],"merely":[17],"focuses":[18],"on":[19],"visual":[20],"information":[21,69],"in":[22,73,159],"videos":[23],"without":[24],"considering":[25,38,126],"the":[26,74,166],"naturally":[27],"accompanied":[28],"audio":[29,39,58],"which":[30],"may":[31],"contain":[32],"rich":[33],"semantics.":[34],"The":[35],"few":[36],"works":[37],"simply":[40],"regard":[41],"it":[42],"as":[43,153],"an":[44],"additional":[45],"modality,":[46],"overlooking":[47],"that:":[48],"i)":[49,94],"it's":[50],"non-trivial":[51],"explore":[53],"consistency":[54,91,128],"and":[55,59,71,92,105,129],"complementarity":[56,130],"between":[57],"visual;":[60],"ii)":[61,113],"such":[62,90],"exploration":[63],"requires":[64],"handling":[65],"different":[66],"levels":[67],"of":[68,101,156,169],"densities":[70],"noises":[72],"two":[75],"modalities.":[76],"To":[77],"tackle":[78],"these":[79],"challenges,":[80],"we":[81,95,114,139,148],"propose":[82,140],"Adaptive":[83],"Dual-branch":[84],"Promoted":[85],"Network":[86],"(ADPN)":[87],"exploit":[89],"complementarity:":[93],"introduce":[96],"dual-branch":[98],"pipeline":[99],"capable":[100],"jointly":[102],"training":[103],"visual-only":[104],"audio-visual":[106,132],"branches":[107],"simultaneously":[109],"eliminate":[110],"inter-modal":[111],"interference;":[112],"design":[115],"Text-Guided":[116],"Clues":[117],"Miner":[118],"(TGCM)":[119],"discover":[121],"crucial":[122],"locating":[123],"clues":[124],"via":[125],"both":[127],"during":[131],"interaction":[133],"guided":[134],"by":[135],"text":[136],"semantics;":[137],"iii)":[138],"novel":[142],"curriculum-based":[143],"denoising":[144],"optimization":[145],"strategy,":[146],"where":[147],"adaptively":[149],"evaluate":[150],"sample":[151],"difficulty":[152],"measure":[155],"noise":[157],"intensity":[158],"self-aware":[161],"fashion.":[162],"Extensive":[163],"experiments":[164],"show":[165],"state-of-the-art":[167],"performance":[168],"our":[170],"method.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}