{"id":"https://openalex.org/W4404370873","doi":"https://doi.org/10.1109/tcsvt.2024.3497997","title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","display_name":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404370873","doi":"https://doi.org/10.1109/tcsvt.2024.3497997"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3497997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3497997","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5102932116","display_name":"Yeming Chen","orcid":"https://orcid.org/0009-0005-5515-1943"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yeming Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347374","display_name":"Siyu Zhang","orcid":"https://orcid.org/0000-0002-0001-0204"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102966948","display_name":"Yaoru Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoru Sun","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103205273","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-2124-0869"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041687721","display_name":"Weijian Liang","orcid":"https://orcid.org/0000-0001-5868-8854"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Liang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100324824","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-4622-0119"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102932116"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20847762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"3","first_page":"2768","last_page":"2781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9580000042915344,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9580000042915344,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9556000232696533,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.92330002784729,"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/computer-science","display_name":"Computer science","score":0.7452289462089539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6632707118988037},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5532295107841492},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47613099217414856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3550434410572052},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3528674840927124},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33827775716781616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452289462089539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632707118988037},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5532295107841492},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47613099217414856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3550434410572052},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3528674840927124},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33827775716781616},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3497997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3497997","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2718252163","display_name":null,"funder_award_id":"91748122","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":71,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2741631785","https://openalex.org/W2741961663","https://openalex.org/W2745461083","https://openalex.org/W2808550672","https://openalex.org/W2962964995","https://openalex.org/W2963191264","https://openalex.org/W2963530300","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2981578638","https://openalex.org/W2997591391","https://openalex.org/W2998119008","https://openalex.org/W2998356391","https://openalex.org/W3004349648","https://openalex.org/W3034727271","https://openalex.org/W3035497460","https://openalex.org/W3035524453","https://openalex.org/W3037773948","https://openalex.org/W3090449556","https://openalex.org/W3102040318","https://openalex.org/W3102750118","https://openalex.org/W3136792391","https://openalex.org/W3154781046","https://openalex.org/W3173220247","https://openalex.org/W3184784418","https://openalex.org/W3202778561","https://openalex.org/W3203354307","https://openalex.org/W4231081240","https://openalex.org/W4282968790","https://openalex.org/W4285118104","https://openalex.org/W4285605441","https://openalex.org/W4285606073","https://openalex.org/W4292421571","https://openalex.org/W4313046728","https://openalex.org/W4313131769","https://openalex.org/W4313178921","https://openalex.org/W4319299938","https://openalex.org/W4382998936","https://openalex.org/W4385574358","https://openalex.org/W4386065353","https://openalex.org/W4387917764","https://openalex.org/W6634232107","https://openalex.org/W6727690538","https://openalex.org/W6755207826","https://openalex.org/W6756398402","https://openalex.org/W6766904570","https://openalex.org/W6773829392","https://openalex.org/W6775188310","https://openalex.org/W6779473860","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798350552","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6803432384","https://openalex.org/W6804095316","https://openalex.org/W6811072154","https://openalex.org/W6840657638","https://openalex.org/W6843018836","https://openalex.org/W6843183339","https://openalex.org/W6850626707","https://openalex.org/W6851592950"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2961085424","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4224009465","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742"],"abstract_inverted_index":{"With":[0],"the":[1,37,41,73,76,92,132,138,152,160,164,168,176,182,201,209,220],"success":[2],"of":[3,15,75,95,134,141,154,163,170,178,204],"self-supervised":[4],"learning,":[5],"multimodal":[6,61],"foundation":[7],"models":[8],"have":[9],"rapidly":[10],"adapted":[11],"a":[12,45,65,82,112,117,146],"wide":[13],"range":[14],"downstream":[16,214],"tasks":[17],"driven":[18],"by":[19,30,63],"vision":[20],"and":[21,100,116,126],"language":[22],"(VL)":[23],"pre-training.":[24],"State-of-the-art":[25],"methods":[26],"achieve":[27,223],"impressive":[28],"performance":[29,74,210],"pre-training":[31,189],"on":[32,196,211,230],"large-scale":[33],"datasets.":[34],"However,":[35],"bridging":[36],"semantic":[38,68,108,118,135],"gap":[39],"between":[40],"two":[42],"modalities":[43],"remains":[44],"non-negligible":[46],"challenge":[47],"for":[48,60],"VL":[49,77,215],"tasks.":[50,78,216],"In":[51,110],"this":[52],"work,":[53],"we":[54,80,144],"propose":[55,81],"an":[56],"efficient":[57],"computation":[58],"framework":[59],"alignment":[62],"introducing":[64],"novel":[66],"visual":[67,107,113,179],"module":[69],"to":[70,105,123,130,150,175,184,199],"further":[71],"improve":[72,159],"Specifically,":[79],"flexible":[83],"model,":[84],"namely":[85],"Artificial-Spiking":[86],"Hierarchical":[87],"Networks":[88],"(ASH-Nets),":[89],"which":[90,193],"combines":[91],"complementary":[93],"advantages":[94],"Artificial":[96],"Neural":[97,102],"Network":[98,103],"(ANN)":[99],"Spiking":[101,183],"(SNN)":[104],"enrich":[106],"representations.":[109,180],"particular,":[111],"concrete":[114],"encoder":[115,120],"abstract":[119,205],"are":[121],"constructed":[122],"learn":[124],"continuous":[125],"discrete":[127],"latent":[128],"variables":[129],"enhance":[131,200],"flexibility":[133],"encoding.":[136],"Considering":[137],"spatiotemporal":[139],"properties":[140],"SNN":[142],"modeling,":[143],"introduce":[145],"contrastive":[147],"learning":[148,177],"method":[149,190],"optimize":[151],"inputs":[153],"similar":[155],"samples.":[156],"This":[157],"can":[158],"computational":[161],"efficiency":[162],"hierarchical":[165],"network,":[166],"while":[167],"augmentation":[169],"hard":[171],"samples":[172],"is":[173,191,228],"beneficial":[174],"Furthermore,":[181],"Text":[185],"Uni-Alignment":[186],"Learning":[187],"(STUA)":[188],"proposed,":[192],"only":[194],"relies":[195],"text":[197],"features":[198],"encoding":[202],"ability":[203],"semantics.":[206],"We":[207],"validate":[208],"multiple":[212],"well-established":[213],"Experiments":[217],"show":[218],"that":[219],"proposed":[221],"ASH-Nets":[222],"competitive":[224],"results.":[225],"Our":[226],"code":[227],"available":[229],"GitHub":[231],"(<uri":[232],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[233],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ZSYTJ/ASH-Nets</uri>).":[234]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}