{"id":"https://openalex.org/W4402981196","doi":"https://doi.org/10.1109/icme57554.2024.10687387","title":"Temporal Feature Aggregation for Efficient 2D Video Grounding","display_name":"Temporal Feature Aggregation for Efficient 2D Video Grounding","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981196","doi":"https://doi.org/10.1109/icme57554.2024.10687387"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687387","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687387","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/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":true,"raw_author_name":"Mohan Chen","raw_affiliation_strings":["Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068603970","display_name":"Yiren Zhang","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":false,"raw_author_name":"Yiren Zhang","raw_affiliation_strings":["Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112987380","display_name":"Jueqi Wei","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":false,"raw_author_name":"Jueqi Wei","raw_affiliation_strings":["Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114236957","display_name":"Yuejie Zhang","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":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science","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,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center of Intelligent Visual Computing,School of Computer Science","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375722","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7561-0143"},"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,Shanghai Key Laboratory of Financial Information Technology,School of Information Management and Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics,Shanghai Key Laboratory of Financial Information Technology,School of Information Management and Engineering","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":7,"corresponding_author_ids":["https://openalex.org/A5076410530"],"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":0.16110758,"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":0.996399998664856,"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":0.996399998664856,"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":0.9954000115394592,"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":0.9954000115394592,"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":0.6892087459564209},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5688296556472778},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.49565017223358154},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3647543787956238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35740697383880615},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09274664521217346},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0744016170501709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892087459564209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5688296556472778},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.49565017223358154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3647543787956238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35740697383880615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09274664521217346},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0744016170501709},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme57554.2024.10687387","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687387","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/27406701","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/27406701","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":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2904824998","https://openalex.org/W2948958195","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970401629","https://openalex.org/W2997429269","https://openalex.org/W2998712570","https://openalex.org/W3034743747","https://openalex.org/W3035640828","https://openalex.org/W3174364033","https://openalex.org/W3176201273","https://openalex.org/W3199096350","https://openalex.org/W3199858703","https://openalex.org/W4293519329","https://openalex.org/W4386065871","https://openalex.org/W6755207826","https://openalex.org/W6761268011","https://openalex.org/W6761423549","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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],"grounding":[1,71,138],"aims":[2],"to":[3,51,92,108],"locate":[4],"the":[5,25,52,118],"target":[6],"video":[7,12,26,41,70,103,137],"moment":[8],"in":[9],"an":[10],"untrimmed":[11],"based":[13],"on":[14,126],"a":[15,34,67,85],"text":[16],"query.":[17],"Most":[18],"existing":[19],"methods":[20,36,139,147],"employ":[21],"3D":[22,146],"CNNs":[23],"as":[24],"feature":[27,42,88],"extractor,":[28],"incurring":[29],"substantial":[30],"computational":[31,80,110],"costs.":[32,81,151],"Only":[33],"few":[35],"use":[37],"2D":[38,59,69,136],"backbones":[39],"for":[40,121],"extraction,":[43],"and":[44,105,140],"they":[45],"suffer":[46],"from":[47],"diminished":[48],"accuracy":[49,77],"due":[50],"inherent":[53],"lack":[54],"of":[55,101],"temporal":[56,87,95],"information":[57],"within":[58],"features.":[60],"To":[61],"address":[62],"this":[63],"problem,":[64],"we":[65,113],"propose":[66],"novel":[68],"method":[72,133],"called":[73],"TFA":[74],"that":[75,131],"improves":[76],"while":[78],"minimizing":[79],"Our":[82],"approach":[83],"involves":[84],"query-guided":[86],"aggregation":[89],"module":[90],"designed":[91],"explicitly":[93],"capture":[94],"information.":[96],"We":[97],"disentangle":[98],"time":[99],"intervals":[100],"input":[102],"frames":[104],"prediction":[106],"spans":[107],"reduce":[109],"overhead.":[111],"Additionally,":[112],"introduce":[114],"deformable":[115],"attention":[116],"into":[117],"multi-modal":[119],"encoder":[120],"further":[122],"enhancement.":[123],"Extensive":[124],"experiments":[125],"two":[127],"public":[128],"datasets":[129],"demonstrate":[130],"our":[132],"outperforms":[134],"previous":[135],"achieves":[141],"competitive":[142],"results":[143],"with":[144],"most":[145],"at":[148],"significantly":[149],"reduced":[150]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}