{"id":"https://openalex.org/W4402125038","doi":"https://doi.org/10.1109/tmm.2024.3453062","title":"Rethinking Video Sentence Grounding From a Tracking Perspective With Memory Network and Masked Attention","display_name":"Rethinking Video Sentence Grounding From a Tracking Perspective With Memory Network and Masked Attention","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402125038","doi":"https://doi.org/10.1109/tmm.2024.3453062"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3453062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3453062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5056981085","display_name":"Zeyu Xiong","orcid":"https://orcid.org/0000-0002-8330-5912"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyu Xiong","raw_affiliation_strings":["Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078220957","display_name":"Daizong Liu","orcid":"https://orcid.org/0000-0001-8179-4508"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083888610","display_name":"Xiang Fang","orcid":"https://orcid.org/0000-0003-3231-5771"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiang Fang","raw_affiliation_strings":["Energy Research Institute @ NTU, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Energy Research Institute @ NTU, Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065871371","display_name":"Xiaoye Qu","orcid":"https://orcid.org/0000-0002-4907-3978"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":["Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008417257","display_name":"Jianfeng Dong","orcid":"https://orcid.org/0000-0001-5244-3274"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Dong","raw_affiliation_strings":["College of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101901855","display_name":"Jiahao Zhu","orcid":"https://orcid.org/0000-0001-7925-3614"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Zhu","raw_affiliation_strings":["Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533842","display_name":"Keke Tang","orcid":"https://orcid.org/0000-0003-0377-1022"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Tang","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5056981085"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":1.3748,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81906505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"11204","last_page":"11218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9538999795913696,"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":0.9538999795913696,"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":0.9394000172615051,"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":0.8557316064834595},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6191306114196777},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5230896472930908},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.46984854340553284},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4153573215007782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3827766478061676},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3233751058578491},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09035775065422058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557316064834595},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6191306114196777},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5230896472930908},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.46984854340553284},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4153573215007782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3827766478061676},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3233751058578491},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09035775065422058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3453062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3453062","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1861492603","https://openalex.org/W1924343884","https://openalex.org/W1926243429","https://openalex.org/W1942126453","https://openalex.org/W1964846093","https://openalex.org/W1995903777","https://openalex.org/W2076269884","https://openalex.org/W2100857488","https://openalex.org/W2221502561","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2470394683","https://openalex.org/W2517710169","https://openalex.org/W2565639579","https://openalex.org/W2742165450","https://openalex.org/W2800230615","https://openalex.org/W2890502146","https://openalex.org/W2904291752","https://openalex.org/W2914134937","https://openalex.org/W2948958195","https://openalex.org/W2963017553","https://openalex.org/W2963393391","https://openalex.org/W2963524571","https://openalex.org/W2963534981","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970401629","https://openalex.org/W2970938561","https://openalex.org/W2995633532","https://openalex.org/W2997429269","https://openalex.org/W2997762001","https://openalex.org/W2998495542","https://openalex.org/W2998712570","https://openalex.org/W3025323587","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3035511673","https://openalex.org/W3035640828","https://openalex.org/W3047922786","https://openalex.org/W3088744711","https://openalex.org/W3093174808","https://openalex.org/W3119243803","https://openalex.org/W3127165192","https://openalex.org/W3134875898","https://openalex.org/W3162694035","https://openalex.org/W3166712493","https://openalex.org/W3176471072","https://openalex.org/W3178087530","https://openalex.org/W3180476551","https://openalex.org/W3186567887","https://openalex.org/W3200255008","https://openalex.org/W3203870241","https://openalex.org/W3207439579","https://openalex.org/W3211772574","https://openalex.org/W4205605843","https://openalex.org/W4206957911","https://openalex.org/W4221148502","https://openalex.org/W4221167018","https://openalex.org/W4225547367","https://openalex.org/W4226051135","https://openalex.org/W4283824961","https://openalex.org/W4285283873","https://openalex.org/W4312295550","https://openalex.org/W4312341368","https://openalex.org/W4312941859","https://openalex.org/W4313163028","https://openalex.org/W4320008746","https://openalex.org/W4372190174","https://openalex.org/W4385245566","https://openalex.org/W4386075849","https://openalex.org/W4386231783","https://openalex.org/W4388756695","https://openalex.org/W4389520490","https://openalex.org/W4392902613","https://openalex.org/W4393150296","https://openalex.org/W6620707391","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6767457941","https://openalex.org/W6784333009","https://openalex.org/W6798195429"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W1537063595","https://openalex.org/W2379604501","https://openalex.org/W2149537132","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W2373854414","https://openalex.org/W370975646"],"abstract_inverted_index":{"Video":[0,122],"sentence":[1],"grounding":[2],"(VSG)":[3],"is":[4],"the":[5,9,77,80,85,89,103,121,184,188],"task":[6,105],"of":[7,11,79,87,190],"identifying":[8],"segment":[10],"an":[12],"untrimmed":[13],"video":[14],"that":[15],"semantically":[16],"corresponds":[17],"to":[18,40,58,75,112,157],"a":[19,98,134,145,154,161,222],"given":[20],"natural":[21],"language":[22],"query.":[23],"While":[24],"many":[25],"existing":[26],"methods":[27,201],"extract":[28],"frame-grained":[29],"features":[30,54,169],"using":[31,55,153],"pre-trained":[32],"2D":[33],"or":[34],"3D":[35],"convolution":[36],"networks,":[37],"often":[38],"fail":[39],"capture":[41,59],"subtle":[42],"differences":[43],"between":[44,170],"ambiguous":[45],"adjacent":[46],"frames.":[47],"Although":[48],"some":[49],"recent":[50],"approaches":[51],"incorporate":[52],"object-grained":[53],"Faster":[56],"R-CNN":[57],"more":[60,114],"fine-grained":[61,115],"details,":[62],"they":[63],"are":[64],"still":[65],"primarily":[66],"based":[67],"on":[68,202],"feature":[69],"enhancement":[70],"and":[71,110,128,142,172,197,210,214],"lack":[72],"spatio-temporal":[73,116],"modeling":[74,88],"explore":[76],"semantics":[78],"core":[81,90],"persons/objects.":[82],"To":[83,186],"solve":[84],"problem":[86],"target's":[91],"behavior,":[92],"in":[93,179],"this":[94],"paper,":[95],"we":[96,119,193],"propose":[97],"new":[99],"perspective":[100],"for":[101,138,148],"addressing":[102],"VSG":[104],"by":[106],"tracking":[107,150],"pivotal":[108],"objects":[109],"activities":[111],"learn":[113],"features.":[117],"Specifically,":[118],"introduce":[120],"Sentence":[123],"Tracker":[124],"with":[125,199,221],"Memory":[126],"Network":[127],"Masked":[129],"Attention":[130],"(VSTMM),":[131],"which":[132,165],"comprises":[133],"cross-modal":[135],"targets":[136,152],"generator":[137],"producing":[139],"multi-modal":[140,151],"templates":[141],"search":[143],"space,":[144],"memory-based":[146],"tracker":[147],"dynamically":[149],"memory":[155],"network":[156],"record":[158],"targets'":[159],"behaviors,":[160],"masked":[162],"attention":[163],"localizer":[164],"learns":[166],"local":[167],"shared":[168],"frames":[171],"eliminates":[173],"interference":[174],"from":[175],"long-term":[176],"dependencies,":[177],"resulting":[178],"improved":[180],"accuracy":[181],"when":[182],"localizing":[183],"moment.":[185],"evaluate":[187],"performance":[189,220],"our":[191,216],"VSTMM,":[192],"conducted":[194],"extensive":[195],"experiments":[196],"comparisons":[198],"state-of-the-art":[200],"three":[203],"challenging":[204],"benchmarks,":[205],"including":[206],"Charades-STA,":[207],"ActivityNet":[208],"Captions,":[209],"TACoS.":[211],"Without":[212],"bells":[213],"whistles,":[215],"VSTMM":[217],"achieves":[218],"leading":[219],"considerable":[223],"real-time":[224],"speed.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}