{"id":"https://openalex.org/W4387968455","doi":"https://doi.org/10.1145/3581783.3612131","title":"Fine-grained Key-Value Memory Enhanced Predictor for Video Representation Learning","display_name":"Fine-grained Key-Value Memory Enhanced Predictor for Video Representation Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968455","doi":"https://doi.org/10.1145/3581783.3612131"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100428843","display_name":"Xiaojie Li","orcid":"https://orcid.org/0000-0001-6449-2727"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Li","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen) & Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6449-2727","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen) & Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"]}]},{"author_position":"middle","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":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0247-5221","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006586772","display_name":"Shaowei He","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":"Shaowei He","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-7214-0921","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101900560","display_name":"Shuo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Kang","raw_affiliation_strings":["Sensetime Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-8167-8099","affiliations":[{"raw_affiliation_string":"Sensetime Research, Hangzhou, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397991","display_name":"Yue Yu","orcid":"https://orcid.org/0000-0002-9865-2212"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9865-2212","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"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":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3895-5510","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2264","last_page":"2274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8620165586471558},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6668695211410522},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6579536199569702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565960168838501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5636969804763794},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5402022004127502},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5347862243652344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4934731721878052},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4500362277030945},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4431377053260803},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.4220700263977051},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.10290354490280151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620165586471558},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6668695211410522},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6579536199569702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565960168838501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5636969804763794},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5402022004127502},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5347862243652344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4934731721878052},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4500362277030945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4431377053260803},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.4220700263977051},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.10290354490280151},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612131","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1789959723","display_name":null,"funder_award_id":"62006140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7395080110","display_name":null,"funder_award_id":"ZR2020QF106","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2099749431","https://openalex.org/W2117865218","https://openalex.org/W2121058967","https://openalex.org/W2126579184","https://openalex.org/W2136995369","https://openalex.org/W2559655401","https://openalex.org/W2578257192","https://openalex.org/W2737008123","https://openalex.org/W2766452532","https://openalex.org/W2909577373","https://openalex.org/W2948242301","https://openalex.org/W2952071070","https://openalex.org/W2962934715","https://openalex.org/W2963155035","https://openalex.org/W2963616706","https://openalex.org/W2963814513","https://openalex.org/W2964216549","https://openalex.org/W2990503944","https://openalex.org/W2997907976","https://openalex.org/W3010874390","https://openalex.org/W3035060554","https://openalex.org/W3035240825","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3045150439","https://openalex.org/W3094454579","https://openalex.org/W3100063120","https://openalex.org/W3110190397","https://openalex.org/W3110306138","https://openalex.org/W3115964123","https://openalex.org/W3117097536","https://openalex.org/W3123599388","https://openalex.org/W3145385912","https://openalex.org/W3159481202","https://openalex.org/W3169761664","https://openalex.org/W3170837227","https://openalex.org/W3171007011","https://openalex.org/W3176780013","https://openalex.org/W3203774379","https://openalex.org/W3203789665","https://openalex.org/W3205193540","https://openalex.org/W3208431284","https://openalex.org/W3210733870","https://openalex.org/W4206118545","https://openalex.org/W4225985153","https://openalex.org/W4285428931","https://openalex.org/W4286951705","https://openalex.org/W4301409532","https://openalex.org/W4304092645","https://openalex.org/W4312469841","https://openalex.org/W4312472954","https://openalex.org/W4313007634","https://openalex.org/W4364353722","https://openalex.org/W6600018615","https://openalex.org/W6600403135"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W1950940422","https://openalex.org/W4283822356","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,158,171],"methods":[2],"have":[3],"shown":[4],"significant":[5],"promise":[6],"in":[7,23,134,157],"acquiring":[8],"robust":[9],"spatiotemporal":[10],"representations":[11,161],"from":[12],"unlabeled":[13],"videos.":[14],"In":[15],"this":[16],"work,":[17],"we":[18,59,98,124],"address":[19],"three":[20],"critical":[21],"limitations":[22],"existing":[24,168],"self-supervised":[25,170],"video":[26,160],"representation":[27,132],"learning:":[28],"1)":[29],"insufficient":[30],"utilization":[31],"of":[32,40,48,87,109,115],"contextual":[33,88],"information":[34,112],"and":[35,45,76,85,93,151],"lifelong":[36],"memory,":[37],"2)":[38],"lack":[39],"fine-grained":[41,107],"visual":[42,101,127],"concept":[43,102],"alignment,":[44],"3)":[46],"neglect":[47],"the":[49,74,82,116,130,135],"feature":[50],"distribution":[51],"gap":[52],"between":[53],"encoders.":[54,78],"To":[55],"overcome":[56],"these":[57],"limitations,":[58],"propose":[60],"a":[61,100],"novel":[62],"memory-enhanced":[63],"predictor":[64],"that":[65,105],"leverages":[66],"key-value":[67],"memory":[68,136],"networks":[69],"with":[70,162],"separate":[71],"memories":[72],"for":[73,148],"online":[75],"target":[77],"This":[79],"design":[80],"enables":[81],"effective":[83],"storage":[84],"retrieval":[86,152],"knowledge,":[89],"facilitating":[90],"informed":[91],"predictions":[92],"enhancing":[94],"overall":[95],"performance.":[96],"Additionally,":[97],"introduce":[99],"alignment":[103,108],"module":[104],"ensures":[106],"shared":[110],"semantic":[111,131],"across":[113],"segments":[114],"same":[117],"video.":[118],"By":[119],"employing":[120],"coupled":[121],"dictionary":[122],"learning,":[123],"effectively":[125],"decouple":[126],"concepts,":[128],"enriching":[129],"stored":[133],"networks.":[137],"Our":[138],"proposed":[139],"approach":[140],"is":[141,174],"extensively":[142],"evaluated":[143],"on":[144],"widely":[145],"recognized":[146],"benchmarks":[147],"action":[149],"recognition":[150],"tasks,":[153],"demonstrating":[154],"its":[155],"superiority":[156],"generalized":[159],"significantly":[163],"improved":[164],"performance":[165],"compared":[166],"to":[167],"state-of-the-art":[169],"methods.":[172],"Code":[173],"released":[175],"at":[176],"https://github.com/xiaojieli0903/FGKVMemPred_video.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}