{"id":"https://openalex.org/W4415707986","doi":"https://doi.org/10.1109/icme59968.2025.11210126","title":"Quality-Guided Dynamic Memory for LLMs-based Long-Term Video Understanding","display_name":"Quality-Guided Dynamic Memory for LLMs-based Long-Term Video Understanding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707986","doi":"https://doi.org/10.1109/icme59968.2025.11210126"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210126","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/A5101160189","display_name":"Bimei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]},{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bimei Wang","raw_affiliation_strings":["Jinan University,College of Cyber Security,China"],"affiliations":[{"raw_affiliation_string":"Jinan University,College of Cyber Security,China","institution_ids":["https://openalex.org/I34949971","https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingmei Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I3133134087","display_name":"Lanzhou Jiaotong University","ror":"https://ror.org/03144pv92","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133134087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingmei Jiao","raw_affiliation_strings":["Lanzhou Jiaotong University,School of Electronic Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"Lanzhou Jiaotong University,School of Electronic Information Engineering,China","institution_ids":["https://openalex.org/I3133134087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058458910","display_name":"Jisheng Dang","orcid":"https://orcid.org/0000-0002-5378-6225"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jisheng Dang","raw_affiliation_strings":["Lanzhou University,School of Information Science & Engineering,China"],"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science & Engineering,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qingrun Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingrun Jiang","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102531975","display_name":"Jiyuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyuan Lin","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113411138","display_name":"Zeshun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixuan Chen","raw_affiliation_strings":["Sun Yat-sen University,School of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348968","display_name":"Teng Wang","orcid":"https://orcid.org/0009-0008-9212-3134"},"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":"Teng Wang","raw_affiliation_strings":["The University of Hong Kong,Faculty of Engineering,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Faculty of Engineering,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089763731","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-6403-3408"},"institutions":[{"id":"https://openalex.org/I3133134087","display_name":"Lanzhou Jiaotong University","ror":"https://ror.org/03144pv92","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133134087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Lanzhou Jiaotong University,School of Electronic Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"Lanzhou Jiaotong University,School of Electronic Information Engineering,China","institution_ids":["https://openalex.org/I3133134087"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101160189"],"corresponding_institution_ids":["https://openalex.org/I159948400","https://openalex.org/I34949971"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30239663,"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":0.7901999950408936,"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":0.7901999950408936,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09650000184774399,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.03220000118017197,"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/inference","display_name":"Inference","score":0.5960999727249146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5084999799728394},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.3601999878883362},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568000197410583},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5336999893188477},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41449999809265137},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3443000018596649},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2985957978","wikidata":"https://www.wikidata.org/wiki/Q492","display_name":"Human memory","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210126","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":24,"referenced_works":["https://openalex.org/W2955874753","https://openalex.org/W2981851019","https://openalex.org/W3096383329","https://openalex.org/W3109729331","https://openalex.org/W3155080005","https://openalex.org/W3161082133","https://openalex.org/W3175859344","https://openalex.org/W4205277845","https://openalex.org/W4244502008","https://openalex.org/W4285108184","https://openalex.org/W4312690503","https://openalex.org/W4313038481","https://openalex.org/W4383899959","https://openalex.org/W4389519587","https://openalex.org/W4390017901","https://openalex.org/W4391129224","https://openalex.org/W4391547535","https://openalex.org/W4392796587","https://openalex.org/W4400579078","https://openalex.org/W4401880109","https://openalex.org/W4401990337","https://openalex.org/W4402671548","https://openalex.org/W4402780269","https://openalex.org/W4404544862"],"related_works":[],"abstract_inverted_index":{"Using":[0],"the":[1,25,108,112,121,125],"impressive":[2],"learning":[3],"representation":[4],"capacity":[5],"of":[6,29,115],"large":[7],"language":[8],"models":[9],"(LLMs),":[10],"LLM-based":[11],"video":[12,57,134],"understanding":[13,58,135],"methods":[14,23],"have":[15],"made":[16],"significant":[17],"strides":[18],"recently.":[19],"However,":[20],"most":[21,126],"existing":[22],"overlook":[24],"crucial":[26],"importance":[27],"discrepancy":[28],"frames,":[30,36],"which":[31,76,102],"often":[32],"include":[33],"massive":[34],"low-quality":[35],"leading":[37],"to":[38,80,84],"limited":[39],"performance":[40],"and":[41,118,153],"inferior":[42],"inference":[43],"efficiency,":[44],"particularly":[45],"for":[46],"long-term":[47,133],"videos.":[48],"To":[49],"this":[50,52],"end,":[51],"paper":[53],"proposes":[54],"a":[55,70,93],"new":[56],"method":[59],"called":[60],"quality-":[61],"guided":[62],"dynamic":[63],"memory":[64,71,97,109],"network":[65],"(QDM-Net).":[66],"First,":[67],"we":[68,91],"design":[69],"quality":[72,96],"evolution":[73],"module":[74],"(MQEM),":[75],"dynamically":[77],"assigns":[78],"weights":[79],"each":[81],"frame":[82],"according":[83],"contextual":[85],"relationships":[86],"between":[87],"adjacent":[88],"frames.":[89],"Second,":[90],"devise":[92],"high-":[94],"level":[95],"bank":[98],"updating":[99],"mechanism":[100],"(HQMBU),":[101],"selectively":[103],"maintains":[104],"high-quality":[105],"frames":[106,117],"in":[107,148],"bank,":[110],"avoiding":[111],"negative":[113],"influences":[114],"redundant":[116],"ensuring":[119],"that":[120,138],"model":[122,154],"focuses":[123],"on":[124,132],"informative":[127],"visual":[128],"cues.":[129],"Extensive":[130],"experiments":[131],"benchmarks":[136],"demonstrate":[137],"our":[139],"QDM-Net":[140],"consistently":[141],"outperforms":[142],"state-of-the-art":[143],"methods,":[144],"showcasing":[145],"its":[146],"potential":[147],"real-world":[149],"applications.":[150],"Our":[151],"code":[152],"will":[155],"be":[156],"publicly":[157],"available.":[158]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-30T00:00:00"}