{"id":"https://openalex.org/W4415708017","doi":"https://doi.org/10.1109/icme59968.2025.11209793","title":"Localizing Step-by-Step: Multimodal Long Video Temporal Grounding with LLM","display_name":"Localizing Step-by-Step: Multimodal Long Video Temporal Grounding with LLM","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708017","doi":"https://doi.org/10.1109/icme59968.2025.11209793"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5004625583","display_name":"Houlun Chen","orcid":"https://orcid.org/0009-0006-7749-7328"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Houlun Chen","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607896","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-0950-5542"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420423","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-2035-6851"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044432126","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0001-7472-7921"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Feng","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101644468","display_name":"Zihan Song","orcid":"https://orcid.org/0009-0009-1485-0536"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Song","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405579","display_name":"Jia Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004625583"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30956419,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829999804496765,"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":0.9829999804496765,"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":0.0026000000070780516,"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/T10028","display_name":"Topic Modeling","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/timestamp","display_name":"Timestamp","score":0.6886000037193298},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5454000234603882},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5374000072479248},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49799999594688416},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4690999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6886000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630299985408783},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4690999984741211},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W3175859344","https://openalex.org/W3216765867","https://openalex.org/W4386075572","https://openalex.org/W4387968116","https://openalex.org/W4389519587","https://openalex.org/W4390873341","https://openalex.org/W4392162962","https://openalex.org/W4402671548","https://openalex.org/W4402727272","https://openalex.org/W4402754238","https://openalex.org/W4404446900","https://openalex.org/W4409368374","https://openalex.org/W4409369885"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Temporal":[1],"Grounding":[2],"(VTG)":[3],"localizes":[4],"moments":[5],"in":[6,24,177],"untrimmed":[7],"videos":[8],"using":[9],"natural":[10],"language":[11],"queries.":[12],"Most":[13],"VTG":[14,68,152],"datasets":[15],"focus":[16],"on":[17],"short":[18],"videos,":[19],"and":[20,74,91,117,133,157,174],"existing":[21],"approaches":[22,43],"excel":[23],"short-term":[25],"cross-modal":[26],"matching":[27],"but":[28],"struggle":[29],"with":[30,71,120,154,181],"long":[31,67,151],"VTG,":[32],"where":[33],"long-range":[34],"temporal":[35,99],"reasoning":[36,141,170],"is":[37],"required":[38],"for":[39,82,172],"complex":[40],"events.":[41],"Existing":[42],"typically":[44],"output":[45],"timestamp":[46],"predictions":[47,173],"without":[48],"intermediate":[49],"steps,":[50],"limiting":[51],"effective":[52],"reasoning,":[53,100],"whereas":[54],"humans":[55],"solve":[56],"this":[57],"step":[58],"by":[59],"step.":[60],"To":[61,97],"address":[62],"this,":[63],"we":[64,86,101,146],"propose":[65],"a":[66,110,149],"framework,":[69],"StepVTG,":[70],"multimodal":[72,155],"visual":[73,92],"speech":[75],"inputs,":[76,156],"leveraging":[77],"Large":[78],"Language":[79],"Models":[80],"(LLMs)":[81],"step-by-step":[83],"reasoning.":[84],"Specifically,":[85],"transform":[87],"task":[88],"descriptions,":[89],"speech,":[90],"inputs":[93],"into":[94],"text":[95],"prompts.":[96],"enhance":[98],"introduce":[102],"the":[103],"Boundary-Perceptive":[104],"Prompting":[105],"strategy,":[106],"which":[107],"includes:":[108],"i)":[109],"multiscale":[111],"denoising":[112],"Chain-of-Thought":[113],"(CoT)":[114],"combining":[115],"global":[116],"local":[118],"semantics":[119],"noise":[121],"filtering,":[122],"ii)":[123],"validity":[124],"principles":[125],"to":[126,139],"ensure":[127],"LLMs":[128],"generate":[129],"reasonable,":[130],"parsable":[131],"predictions,":[132],"iii)":[134],"one-shot":[135],"In-Context":[136],"Learning":[137],"(ICL)":[138],"improve":[140],"via":[142],"imitation.":[143],"For":[144],"evaluation,":[145],"establish":[147],"MM-LVTG,":[148],"new":[150],"benchmark":[153],"demonstrate":[158],"through":[159],"extensive":[160],"experiments":[161],"that":[162],"StepVTG":[163],"achieves":[164],"state-of-the-art":[165],"performance.":[166],"It":[167],"offers":[168],"explainable":[169],"steps":[171],"reveals":[175],"potential":[176],"facilitating":[178],"video":[179],"understanding":[180],"off-the-shelf":[182],"LLMs.":[183]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}