{"id":"https://openalex.org/W4414604029","doi":"https://doi.org/10.1109/tpami.2025.3615586","title":"A Survey on Video Temporal Grounding With Multimodal Large Language Model","display_name":"A Survey on Video Temporal Grounding With Multimodal Large Language Model","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4414604029","doi":"https://doi.org/10.1109/tpami.2025.3615586","pmid":"https://pubmed.ncbi.nlm.nih.gov/41021939"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3615586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3615586","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100654190","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Liu","orcid":"https://orcid.org/0009-0007-3685-5747"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ye Liu","orcid":"https://orcid.org/0000-0001-9597-0525"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ye Liu","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085804436","display_name":"Liqiang Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016399094","display_name":"Zhouchen Lin","orcid":"https://orcid.org/0000-0003-1493-7569"},"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":"Zhouchen Lin","raw_affiliation_strings":["State Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China","School of Intelligence Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":"https://orcid.org/0000-0002-6720-234X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chang Wen Chen","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100654190"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90842059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"48","issue":"2","first_page":"1521","last_page":"1541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9613999724388123,"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":0.9613999724388123,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5576000213623047},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.47609999775886536},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4350999891757965},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41019999980926514},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295999765396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6198999881744385},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41019999980926514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3615586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3615586","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41021939","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41021939","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G11609016","display_name":null,"funder_award_id":"62276004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3968320906","display_name":null,"funder_award_id":"62376140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4777104730","display_name":null,"funder_award_id":"L257007","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5954055007","display_name":null,"funder_award_id":"62376069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873523568","display_name":null,"funder_award_id":"2024A1515012027","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W1958932515","https://openalex.org/W2111078031","https://openalex.org/W2337252826","https://openalex.org/W2798354744","https://openalex.org/W2896457183","https://openalex.org/W2897628926","https://openalex.org/W2919974746","https://openalex.org/W2952132648","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963351113","https://openalex.org/W2963393391","https://openalex.org/W2963735856","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970641574","https://openalex.org/W2984008963","https://openalex.org/W2997429269","https://openalex.org/W2998495542","https://openalex.org/W3034815696","https://openalex.org/W3093206850","https://openalex.org/W3094502228","https://openalex.org/W3096935578","https://openalex.org/W3097607319","https://openalex.org/W3107593835","https://openalex.org/W3108328693","https://openalex.org/W3124671614","https://openalex.org/W3130619535","https://openalex.org/W3174364033","https://openalex.org/W3175082063","https://openalex.org/W3175961224","https://openalex.org/W3180476551","https://openalex.org/W3200924860","https://openalex.org/W3204588463","https://openalex.org/W3205786327","https://openalex.org/W3216765867","https://openalex.org/W4214663214","https://openalex.org/W4220863439","https://openalex.org/W4234728002","https://openalex.org/W4292092982","https://openalex.org/W4298364821","https://openalex.org/W4312544061","https://openalex.org/W4312864639","https://openalex.org/W4327852044","https://openalex.org/W4385572712","https://openalex.org/W4386057769","https://openalex.org/W4386065689","https://openalex.org/W4386076522","https://openalex.org/W4386083094","https://openalex.org/W4388854793","https://openalex.org/W4389519587","https://openalex.org/W4389722225","https://openalex.org/W4390190760","https://openalex.org/W4390873056","https://openalex.org/W4390873341","https://openalex.org/W4391941517","https://openalex.org/W4392162962","https://openalex.org/W4392172801","https://openalex.org/W4393147998","https://openalex.org/W4396681775","https://openalex.org/W4402582789","https://openalex.org/W4402671548","https://openalex.org/W4402671847","https://openalex.org/W4402727272","https://openalex.org/W4402727520","https://openalex.org/W4402727764","https://openalex.org/W4402754238","https://openalex.org/W4402777385","https://openalex.org/W4402917053","https://openalex.org/W4402969017","https://openalex.org/W4403002096","https://openalex.org/W4403791441","https://openalex.org/W4403791786","https://openalex.org/W4403792095","https://openalex.org/W4403878506","https://openalex.org/W4403888320","https://openalex.org/W4404782290","https://openalex.org/W4404784276","https://openalex.org/W4405022193","https://openalex.org/W4408352828","https://openalex.org/W4409346443","https://openalex.org/W4409349177","https://openalex.org/W4409366186","https://openalex.org/W4409369885","https://openalex.org/W4411472307","https://openalex.org/W4411630225","https://openalex.org/W4412376987","https://openalex.org/W4412888584","https://openalex.org/W4413145109","https://openalex.org/W4413145251","https://openalex.org/W4413145325","https://openalex.org/W4413145412","https://openalex.org/W4413146199","https://openalex.org/W4413147815","https://openalex.org/W4414281281","https://openalex.org/W4415797872","https://openalex.org/W4415798265","https://openalex.org/W4416035957","https://openalex.org/W7108068597"],"related_works":[],"abstract_inverted_index":{"The":[0],"recent":[1],"advancement":[2],"in":[3,50],"video":[4,12,111],"temporal":[5,104],"grounding":[6],"(VTG)":[7],"has":[8],"significantly":[9],"enhanced":[10],"fine-grained":[11],"understanding,":[13,64],"primarily":[14],"driven":[15],"by":[16],"multimodal":[17,24],"large":[18],"language":[19],"models":[20],"(MLLMs).":[21],"With":[22],"superior":[23],"comprehension":[25],"and":[26,55,106,109,127,136],"reasoning":[27,105],"abilities,":[28],"VTG":[29],"approaches":[30],"based":[31],"on":[32,61,82],"MLLMs":[33],"(VTG-MLLMs)":[34],"are":[35],"gradually":[36],"surpassing":[37],"traditional":[38],"fine-tuned":[39],"methods.":[40],"They":[41],"not":[42],"only":[43],"achieve":[44],"competitive":[45],"performance":[46],"but":[47],"also":[48],"excel":[49],"generalization":[51],"across":[52],"zero-shot,":[53],"multi-task,":[54],"multi-domain":[56],"settings.":[57],"Despite":[58],"extensive":[59],"surveys":[60],"general":[62],"video-language":[63],"comprehensive":[65],"reviews":[66],"specifically":[67],"addressing":[68],"VTG-MLLMs":[69,83],"remain":[70],"scarce.":[71],"To":[72],"fill":[73],"this":[74,76],"gap,":[75],"survey":[77],"systematically":[78],"examines":[79],"current":[80],"research":[81,139],"through":[84],"a":[85],"three-dimensional":[86],"taxonomy:":[87],"1)":[88],"the":[89],"functional":[90],"roles":[91],"of":[92],"MLLMs,":[93],"highlighting":[94],"their":[95],"architectural":[96],"significance;":[97],"2)":[98],"training":[99],"paradigms,":[100],"analyzing":[101],"strategies":[102],"for":[103],"task":[107],"adaptation;":[108],"3)":[110],"feature":[112],"processing":[113],"techniques,":[114],"which":[115],"determine":[116],"spatiotemporal":[117],"representation":[118],"effectiveness.":[119],"We":[120],"further":[121],"discuss":[122],"benchmark":[123],"datasets,":[124],"evaluation":[125],"protocols,":[126],"summarize":[128],"empirical":[129],"findings.":[130],"Finally,":[131],"we":[132],"identify":[133],"existing":[134],"limitations":[135],"propose":[137],"promising":[138],"directions.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}