{"id":"https://openalex.org/W7165808788","doi":"https://doi.org/10.1109/tip.2026.3705206","title":"An Episode Memory-Guided Dual-Stage Framework for Long-Form Video Temporal Grounding","display_name":"An Episode Memory-Guided Dual-Stage Framework for Long-Form Video Temporal Grounding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165808788","doi":"https://doi.org/10.1109/tip.2026.3705206","pmid":"https://pubmed.ncbi.nlm.nih.gov/42340901"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3705206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3705206","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5011105024","display_name":"Tianshan Liu","orcid":"https://orcid.org/0000-0003-3831-8893"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshan Liu","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-8893","affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019678322","display_name":"Kin\u2010Man Lam","orcid":"https://orcid.org/0000-0002-0422-8454"},"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":"Kin-Man Lam","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0422-8454","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8304647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6830","last_page":"6845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.2766999900341034,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.2766999900341034,"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":0.23759999871253967,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16670000553131104,"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/image-processing","display_name":"Image processing","score":0.3441999852657318},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3190999925136566},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3165000081062317},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.29679998755455017},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2897000014781952},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.289000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6603999733924866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254000067710876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6209999918937683},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3705206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3705206","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42340901","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42340901","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1362912382","display_name":null,"funder_award_id":"62532003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G264948653","display_name":null,"funder_award_id":"62402243","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3087610523","display_name":null,"funder_award_id":"U23A20387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6514833853","display_name":null,"funder_award_id":"BE2023016-4","funder_id":"https://openalex.org/F4320327780","funder_display_name":"Key Research and Development Program of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"temporal":[1,53,87],"grounding":[2,88],"(VTG)":[3],"aims":[4],"to":[5,13,51],"localize":[6],"video":[7,63,169,178],"moments":[8],"that":[9,186],"are":[10,60],"semantically":[11],"related":[12],"a":[14,97,150],"given":[15],"natural":[16],"language":[17,151],"query.":[18],"In":[19],"spite":[20],"of":[21,62,99,142,149,166],"recent":[22],"progress":[23],"in":[24,30,75,89,134],"short-form":[25],"videos,":[26],"research":[27],"on":[28,129,139,174],"VTG":[29],"long-form":[31,90,177],"videos":[32],"(e.g.,":[33],"hours":[34],"long)":[35],"remains":[36],"highly":[37],"demanded":[38],"yet":[39],"underexplored.":[40],"Existing":[41],"methods":[42],"predominantly":[43],"adopt":[44],"sliding":[45],"window-based":[46],"or":[47,59],"multi-scale":[48],"anchor-based":[49],"strategies":[50],"generate":[52],"proposals,":[54],"which":[55,103],"require":[56],"time-consuming":[57],"post-processing":[58],"independent":[61],"content,":[64],"thereby":[65],"limiting":[66],"their":[67],"performance":[68,204],"and":[69,123,146,183,197],"efficiency.":[70],"To":[71],"address":[72],"this":[73,76],"dilemma,":[74],"paper,":[77],"we":[78],"propose":[79],"an":[80],"episode":[81,101],"memory-prompted":[82],"(EMP)":[83],"two-stage":[84],"framework":[85,190],"for":[86,160],"videos.":[91],"Specifically,":[92],"the":[93,110,127,135,140,147,153,163,167,187],"first":[94],"stage":[95],"generates":[96],"set":[98],"dynamic":[100],"memories,":[102],"explicitly":[104],"summarize":[105],"various":[106],"activities":[107],"occurring":[108],"throughout":[109],"lengthy":[111],"video.":[112],"An":[113],"unsupervised":[114],"memory":[115,155],"learning":[116],"paradigm":[117],"is":[118],"formulated":[119],"by":[120],"imposing":[121],"discriminability":[122],"diversity":[124],"constraints,":[125],"eliminating":[126],"reliance":[128],"additional":[130],"activity-instance":[131],"annotations.":[132],"Then,":[133],"second":[136],"stage,":[137],"based":[138],"supplement":[141],"frame-level":[143],"detailed":[144],"content":[145],"guidance":[148],"query,":[152],"augmented":[154],"prompts":[156],"function":[157],"as":[158],"anchors":[159],"efficiently":[161],"regressing":[162],"refined":[164],"boundaries":[165],"target":[168],"moment.":[170],"Extensive":[171],"experimental":[172],"results":[173],"two":[175],"public":[176],"data":[179],"sets,":[180],"i.e.,":[181],"MAD":[182],"Ego4d,":[184],"validate":[185],"proposed":[188],"EMP":[189],"saves":[191],"more":[192],"than":[193],"8.5%":[194],"trainable":[195],"parameters":[196],"13.9%":[198],"FLOPs,":[199],"while":[200],"still":[201],"achieving":[202],"comparable":[203],"with":[205],"existing":[206],"methods.":[207]},"counts_by_year":[],"updated_date":"2026-06-30T06:16:30.551410","created_date":"2026-06-25T00:00:00"}