{"id":"https://openalex.org/W4402979203","doi":"https://doi.org/10.1109/icme57554.2024.10687697","title":"Memory-Augmented Transformer for Efficient End-to-End Video Grounding","display_name":"Memory-Augmented Transformer for Efficient End-to-End Video Grounding","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979203","doi":"https://doi.org/10.1109/icme57554.2024.10687697"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082630864","display_name":"Yuanwu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanwu Xu","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076410530","display_name":"Mohan Chen","orcid":"https://orcid.org/0000-0002-8071-5633"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Chen","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103186940","display_name":"Z. Tao","orcid":"https://orcid.org/0000-0003-0878-8229"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Shanghai University of Finance and Economics,School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics,School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048961502","display_name":"Shang Gao","orcid":"https://orcid.org/0000-0002-2176-6553"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shang Gao","raw_affiliation_strings":["Deakin University,School of Information Technology"],"affiliations":[{"raw_affiliation_string":"Deakin University,School of Information Technology","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082630864"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16022855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9987999796867371,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9987999796867371,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9980999827384949,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9980000257492065,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6989350318908691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464530229568481},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6266111731529236},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.6102043986320496},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3665403723716736},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2122529149055481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19799372553825378},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12281674146652222}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6989350318908691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464530229568481},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6266111731529236},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6102043986320496},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3665403723716736},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2122529149055481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19799372553825378},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12281674146652222}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme57554.2024.10687697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/27411297","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27411297","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2111078031","https://openalex.org/W2948958195","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2982770724","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3168640669","https://openalex.org/W3173621652","https://openalex.org/W3199096350","https://openalex.org/W3199858703","https://openalex.org/W3211772574","https://openalex.org/W4313011746","https://openalex.org/W4386076698","https://openalex.org/W6770251742"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2021787609","https://openalex.org/W2390279801","https://openalex.org/W2348662814","https://openalex.org/W7239252","https://openalex.org/W2016892069","https://openalex.org/W2012183883","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Video":[0],"grounding":[1,35],"aims":[2],"to":[3,9,18,24,37],"localize":[4],"a":[5,10,69,88],"specific":[6],"segment":[7],"corresponding":[8],"text":[11],"query":[12],"in":[13,87],"an":[14],"untrimmed":[15],"video.":[16],"Due":[17],"the":[19,26,29,48,57,60],"tremendous":[20],"computational":[21],"cost":[22],"required":[23],"process":[25],"video":[27,34,39,43,49,76,93],"frames,":[28],"de":[30],"facto":[31],"paradigm":[32],"of":[33,47,59],"is":[36,77,143],"extract":[38],"features":[40,94],"using":[41],"pretrained":[42],"encoders.":[44],"The":[45],"parameters":[46],"encoders":[50],"are":[51],"fixed":[52],"during":[53],"training,":[54],"which":[55],"limits":[56],"performance":[58,131],"localization":[61],"model.":[62,73],"To":[63],"solve":[64],"this":[65],"problem,":[66],"we":[67],"propose":[68],"Memory-Augmented":[70],"Transformer":[71],"(MAT)":[72],"Specifically,":[74],"each":[75],"split":[78],"into":[79,95],"non-overlapping":[80],"clips,":[81],"and":[82],"our":[83,104,126],"MAT":[84,105,127],"processes":[85],"videos":[86],"clip-by-clip":[89],"manner":[90],"while":[91,132],"caching":[92],"FIFO":[96],"cached":[97],"memory":[98],"queues.":[99],"By":[100],"enabling":[101],"early":[102],"return,":[103],"outperforms":[106],"previous":[107],"methods":[108],"with":[109],"only":[110],"less":[111],"than":[112,137],"60%":[113],"frames":[114],"seen.":[115],"Extensive":[116],"experimental":[117],"results":[118],"on":[119],"three":[120],"public":[121],"benchmark":[122],"datasets":[123],"demonstrate":[124],"that":[125],"can":[128],"achieve":[129],"competitive":[130],"being":[133],"much":[134],"more":[135],"efficient":[136],"currently":[138],"prevailing":[139],"two-stage":[140],"methods.":[141],"Code":[142],"available":[144],"at":[145],"https://github.com/xuyw1997/MAT.":[146]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}