{"id":"https://openalex.org/W4415708377","doi":"https://doi.org/10.1109/icme59968.2025.11209249","title":"Instruction-aware Memory Network for Video Recognition","display_name":"Instruction-aware Memory Network for Video Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708377","doi":"https://doi.org/10.1109/icme59968.2025.11209249"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209249","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":"https://openalex.org/A5101994349","display_name":"Haijiang Li","orcid":"https://orcid.org/0000-0001-9924-7174"},"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":"Haijiang Li","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":"https://openalex.org/A5100377600","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0001-7146-8290"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["City University of HongKong,College of Computing,China"],"affiliations":[{"raw_affiliation_string":"City University of HongKong,College of Computing,China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108016643","display_name":"Zhixuan Chen","orcid":"https://orcid.org/0000-0001-8767-7177"},"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/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/A5101579470","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0001-9427-8609"},"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/A5100695457","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0003-2436-942X"},"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":0.31073217,"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":0.9883999824523926,"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":0.9883999824523926,"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":0.0020000000949949026,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0013000000035390258,"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/context","display_name":"Context (archaeology)","score":0.5730000138282776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.48170000314712524},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.423799991607666},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4099000096321106},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.3765999972820282},{"id":"https://openalex.org/keywords/visual-memory","display_name":"Visual memory","score":0.3352999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389000296592712},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4156000018119812},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.27900001406669617},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.2736000120639801},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209249","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":27,"referenced_works":["https://openalex.org/W2981851019","https://openalex.org/W3096383329","https://openalex.org/W3109729331","https://openalex.org/W3161082133","https://openalex.org/W3175859344","https://openalex.org/W3177141386","https://openalex.org/W3177399480","https://openalex.org/W4205277845","https://openalex.org/W4244502008","https://openalex.org/W4285108184","https://openalex.org/W4312772544","https://openalex.org/W4313038481","https://openalex.org/W4377235190","https://openalex.org/W4383899959","https://openalex.org/W4389519587","https://openalex.org/W4390017901","https://openalex.org/W4391547535","https://openalex.org/W4393178509","https://openalex.org/W4400071543","https://openalex.org/W4400579078","https://openalex.org/W4401990337","https://openalex.org/W4402671548","https://openalex.org/W4402780269","https://openalex.org/W4402916752","https://openalex.org/W4403725941","https://openalex.org/W4403878713","https://openalex.org/W4404739549"],"related_works":[],"abstract_inverted_index":{"The":[0,130],"rapid":[1],"development":[2],"of":[3],"multimodal":[4],"large":[5],"language":[6],"models":[7,135],"(MLLMs)":[8],"has":[9],"highlighted":[10],"their":[11],"potential":[12],"in":[13,19,24,38,85,110],"video":[14,21,36,63,111,128],"understanding.":[15,64],"However,":[16],"challenges":[17],"remain":[18],"long":[20],"tasks,":[22],"particularly":[23],"integrating":[25,66],"visual":[26,67],"features":[27,76,82],"with":[28,77],"prompt":[29],"texts.":[30],"Existing":[31],"methods":[32],"naively":[33],"store":[34],"processed":[35],"frames":[37],"a":[39,86,123],"long-term":[40,62,92,127],"memory":[41,57,88,100],"bank,":[42,89],"but":[43],"neglect":[44],"simple":[45],"yet":[46],"effective":[47],"cross-modal":[48,75],"integration.":[49],"To":[50],"address":[51],"this,":[52],"we":[53],"introduce":[54],"the":[55,104,117],"instruction-aware":[56],"construction":[58],"(IaMC)":[59],"model":[60,72],"for":[61,126],"By":[65],"and":[68,113,121,133],"textual":[69],"information,":[70],"our":[71],"can":[73],"obtain":[74],"robust":[78],"understanding":[79,112],"capabilities.":[80],"These":[81],"are":[83],"stored":[84],"text-visual":[87],"enabling":[90],"efficient":[91],"aggregation":[93],"without":[94],"surpassing":[95],"LLM":[96],"context":[97],"or":[98],"GPU":[99],"limits.":[101],"Experiments":[102],"on":[103],"LVU":[105],"dataset":[106],"demonstrate":[107],"state-of-the-art":[108],"performance":[109],"question":[114],"answering,":[115],"showcasing":[116],"IaMC":[118],"model\u2019s":[119],"effectiveness":[120],"setting":[122],"new":[124],"benchmark":[125],"analysis.":[129],"source":[131],"code":[132],"trained":[134],"will":[136],"be":[137],"released":[138],"publicly.":[139]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}