{"id":"https://openalex.org/W4402352879","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651273","title":"Coarse-to-Fine Recurrently Aligned Transformer with Balance Tokens for Video Moment Retrieval and Highlight Detection","display_name":"Coarse-to-Fine Recurrently Aligned Transformer with Balance Tokens for Video Moment Retrieval and Highlight Detection","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352879","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651273"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651273","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5068003384","display_name":"Yi Pan","orcid":"https://orcid.org/0000-0003-1978-475X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Pan","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107957998","display_name":"Yujia Zhang","orcid":"https://orcid.org/0009-0000-9392-1041"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujia Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068146183","display_name":"Hui\u2010Ming Chang","orcid":"https://orcid.org/0000-0002-5856-3397"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chang","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741126","display_name":"Shiying Sun","orcid":"https://orcid.org/0000-0002-7870-8733"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiying Sun","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078189753","display_name":"Feihu Zhou","orcid":"https://orcid.org/0000-0001-6154-013X"},"institutions":[{"id":"https://openalex.org/I2802939634","display_name":"Chinese PLA General Hospital","ror":"https://ror.org/04gw3ra78","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802939634"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feihu Zhou","raw_affiliation_strings":["Chinese PLA General Hospital,The First Medical Centre,Department of Critical Care Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese PLA General Hospital,The First Medical Centre,Department of Critical Care Medicine","institution_ids":["https://openalex.org/I2802939634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100845614","display_name":"Xiaoguang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13285589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9994000196456909,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9993000030517578,"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/transformer","display_name":"Transformer","score":0.6623706817626953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6311150789260864},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5113462805747986},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4420733153820038},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1197996735572815},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1052892804145813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09079298377037048},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08412706851959229},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07071736454963684},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06833145022392273}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6623706817626953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6311150789260864},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5113462805747986},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4420733153820038},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1197996735572815},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1052892804145813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09079298377037048},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08412706851959229},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07071736454963684},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06833145022392273},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651273","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320337572","display_name":"Engineering Laboratory","ror":"https://ror.org/03v61g875"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1926243429","https://openalex.org/W1958932515","https://openalex.org/W2919974746","https://openalex.org/W2964089981","https://openalex.org/W2968356596","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3096609285","https://openalex.org/W3106645934","https://openalex.org/W3152619510","https://openalex.org/W3153755697","https://openalex.org/W3201832684","https://openalex.org/W3214448253","https://openalex.org/W4226017311","https://openalex.org/W4283819318","https://openalex.org/W4312544061","https://openalex.org/W4312693115","https://openalex.org/W4382700251","https://openalex.org/W4386083094","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4402352082","https://openalex.org/W6791353385","https://openalex.org/W6804424445","https://openalex.org/W6810863107","https://openalex.org/W6811230874","https://openalex.org/W6852495480"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Video":[0],"moment":[1],"retrieval":[2],"(MR)":[3],"and":[4,40,56,63,72,160],"highlight":[5],"detection":[6],"(HD)":[7],"are":[8],"two":[9,108],"user-oriented":[10],"video":[11,55,70],"understanding":[12],"tasks":[13],"aimed":[14],"at":[15],"extracting":[16],"query-dependent":[17],"or":[18],"highlighted":[19],"moments":[20],"to":[21,105,123,133,146],"provide":[22],"valuable":[23],"content":[24],"for":[25,34],"users.":[26],"While":[27],"many":[28],"recent":[29],"works":[30],"have":[31,50,64],"proposed":[32,164],"solutions":[33],"the":[35,54,66,101,107,126,135,148,158],"joint":[36],"task":[37],"of":[38,162],"MR":[39],"HD":[41],"leveraging":[42],"transformer":[43,61,103],"architecture,":[44],"we":[45,79,91,115,138],"argue":[46],"that":[47],"existing":[48],"approaches":[49],"not":[51],"adequately":[52],"aligned":[53],"text":[57,73,140,149],"modalities":[58,109,127],"using":[59],"basic":[60],"encoders,":[62],"overlooked":[65],"misalignment":[67,136],"between":[68],"irrelevant":[69,153],"clips":[71],"queries.":[74],"To":[75],"address":[76],"these":[77],"issues,":[78],"introduce":[80],"COREBA:":[81],"a":[82,93,111,117,129],"Coarse-to-Fine":[83,95],"Recurrently":[84],"Aligned":[85],"Transformer":[86],"with":[87,142,152],"Balance":[88,144],"Tokens.":[89],"Firstly,":[90],"design":[92],"plug-and-play":[94],"Cross-modal":[96],"interaction":[97],"(CFC)":[98],"module,":[99],"replacing":[100],"original":[102],"encoder":[104],"align":[106,125],"in":[110,128],"progressive":[112],"manner.":[113],"Secondly,":[114],"present":[116],"novel":[118],"Recurrent":[119],"Alignment":[120],"Mechanism":[121],"(RAM)":[122],"deeply":[124],"recurrent":[130],"fashion.":[131],"Thirdly,":[132],"mitigate":[134],"problem,":[137],"append":[139],"queries":[141],"learnable":[143],"Tokens":[145],"restrict":[147],"information":[150],"fused":[151],"clips.":[154],"Extensive":[155],"experiments":[156],"validate":[157],"effectiveness":[159],"superiority":[161],"our":[163],"method.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}