{"id":"https://openalex.org/W4392902613","doi":"https://doi.org/10.1109/icassp48485.2024.10447846","title":"Mrtnet: Multi-Resolution Temporal Network for Video Sentence Grounding","display_name":"Mrtnet: Multi-Resolution Temporal Network for Video Sentence Grounding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902613","doi":"https://doi.org/10.1109/icassp48485.2024.10447846"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034729053","display_name":"You Qin","orcid":"https://orcid.org/0009-0009-2880-1022"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"You Qin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039731055","display_name":"Yinwei Wei","orcid":"https://orcid.org/0000-0003-1791-3159"},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yinwei Wei","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100539790","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0001-7892-9088"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["Hong Kong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058575315","display_name":"Roger Zimmermann","orcid":"https://orcid.org/0000-0002-7410-2590"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.406,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8959125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2770","last_page":"2774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9979000091552734,"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":0.996999979019165,"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":0.810404896736145},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6822500228881836},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5912715792655945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47713327407836914},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4724738299846649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.445556640625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3329554796218872},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32320404052734375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810404896736145},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6822500228881836},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5912715792655945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47713327407836914},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4724738299846649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.445556640625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3329554796218872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32320404052734375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1927052826","https://openalex.org/W2250539671","https://openalex.org/W2765137706","https://openalex.org/W2890502146","https://openalex.org/W2961348656","https://openalex.org/W2964089981","https://openalex.org/W3034743747","https://openalex.org/W3035640828","https://openalex.org/W3153098222","https://openalex.org/W3174364033","https://openalex.org/W4200631219","https://openalex.org/W4221160126","https://openalex.org/W4224993577","https://openalex.org/W4312535423","https://openalex.org/W4312941859","https://openalex.org/W4386065419","https://openalex.org/W4386075849","https://openalex.org/W4386231783","https://openalex.org/W4390874032","https://openalex.org/W4396568588","https://openalex.org/W6843502183","https://openalex.org/W6847146670"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2375873920","https://openalex.org/W2384362569","https://openalex.org/W2146114872","https://openalex.org/W2142795561","https://openalex.org/W2392060890","https://openalex.org/W2012531322","https://openalex.org/W2360644719","https://openalex.org/W2385471969"],"abstract_inverted_index":{"Video":[0],"sentence":[1],"grounding":[2,31],"locates":[3],"a":[4,8,12,29,37,40,45,51,91],"specific":[5],"moment":[6],"in":[7],"video":[9],"based":[10],"on":[11,18,103],"text":[13,74],"query.":[14],"Existing":[15],"methods":[16],"focus":[17],"single":[19],"temporal":[20,24],"resolution,":[21],"ignoring":[22],"multi-scale":[23],"consistency.":[25],"We":[26,88],"introduce":[27],"MRTNet,":[28],"multi-resolution":[30],"network":[32,59],"with":[33],"four":[34],"key":[35],"components:":[36],"feature":[38,96],"encoder,":[39],"Multi-Resolution":[41],"Temporal":[42],"(MRT)":[43],"module,":[44,49],"Query-aware":[46],"Attention":[47],"(QAM)":[48],"and":[50,60,65,73,78],"predictor.":[52],"The":[53,68],"MRT":[54,77],"module":[55,70],"uses":[56],"an":[57],"encoder-decoder":[58],"Transformers":[61],"to":[62],"predict":[63],"start":[64],"end":[66],"times.":[67],"QAM":[69,79],"fuses":[71],"visual":[72],"features.":[75],"Both":[76],"modules":[80],"are":[81],"easily":[82],"integrated":[83],"into":[84],"existing":[85],"VSG":[86],"models.":[87],"also":[89],"employ":[90],"loss":[92],"function":[93],"for":[94],"cross-modal":[95],"supervision":[97],"at":[98],"multiple":[99],"scales.":[100],"Extensive":[101],"experiments":[102],"two":[104],"prevalent":[105],"datasets":[106],"have":[107],"shown":[108],"the":[109],"effectiveness":[110],"of":[111],"MRTNet.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
