{"id":"https://openalex.org/W4387968380","doi":"https://doi.org/10.1145/3581783.3612192","title":"On the Importance of Spatial Relations for Few-shot Action Recognition","display_name":"On the Importance of Spatial Relations for Few-shot Action Recognition","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968380","doi":"https://doi.org/10.1145/3581783.3612192"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612192","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/A5116568560","display_name":"Yilun Zhang","orcid":"https://orcid.org/0009-0001-8471-6983"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilun Zhang","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-8471-6983","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072248915","display_name":"Yuqian Fu","orcid":"https://orcid.org/0000-0002-0412-5500"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0412-5500","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078711649","display_name":"Xingjun Ma","orcid":"https://orcid.org/0000-0003-2099-4973"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjun Ma","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2099-4973","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009450745","display_name":"Lizhe Qi","orcid":"https://orcid.org/0000-0002-4348-1559"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhe Qi","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4348-1559","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3148-264X","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8689-5807","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intel. Info. Proc., School of CS, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2243","last_page":"2251"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9908999800682068,"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/T11227","display_name":"Diabetic Foot Ulcer Assessment and Management","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.824018120765686},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.7480680346488953},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6958606243133545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6414263248443604},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6172767877578735},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5105007886886597},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4841350018978119},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4621376097202301},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.46039173007011414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44592347741127014},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4315086305141449},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4191124439239502},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4020211100578308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824018120765686},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.7480680346488953},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6958606243133545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6414263248443604},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6172767877578735},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5105007886886597},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4841350018978119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4621376097202301},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.46039173007011414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44592347741127014},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4315086305141449},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4191124439239502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4020211100578308},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"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/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612192","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":[],"awards":[{"id":"https://openalex.org/G3970387658","display_name":"\u77e5\u8bc6\u9a71\u52a8\u7684\u5c0f\u6837\u672c\u89c6\u89c9\u8bc6\u522b\u7814\u7a76","funder_award_id":"62072116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2126579184","https://openalex.org/W2963524571","https://openalex.org/W2990503944","https://openalex.org/W2994785205","https://openalex.org/W3035374961","https://openalex.org/W3092900959","https://openalex.org/W3118473641","https://openalex.org/W3120637139","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3173271747","https://openalex.org/W4225569978","https://openalex.org/W4288073030","https://openalex.org/W4312259618"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"achieved":[3],"great":[4],"success":[5],"in":[6,88],"video":[7,188],"recognition,":[8,215],"yet":[9,178],"still":[10],"struggles":[11],"to":[12,34,41,101,134,161],"recognize":[13],"novel":[14,43,126],"actions":[15],"when":[16],"faced":[17],"with":[18,46],"only":[19,47],"a":[20,38,42,50,110,125,176],"few":[21,51],"examples.":[22],"To":[23,168],"tackle":[24],"this":[25,76,204,220],"challenge,":[26],"few-shot":[27,113,213],"action":[28,114,214],"recognition":[29,115],"methods":[30,56,164],"have":[31],"been":[32],"proposed":[33],"transfer":[35],"knowledge":[36],"from":[37],"source":[39],"dataset":[40,45],"target":[44],"one":[48],"or":[49],"labeled":[52],"videos.":[53],"However,":[54],"existing":[55],"mainly":[57],"focus":[58],"on":[59,165],"modeling":[60],"the":[61,65,72,81,94,103,136,141,155,171,187,192,195],"temporal":[62,95,122,142,153,162,172],"relations":[63,107,138],"between":[64,84],"query":[66],"and":[67,108,121,139,190],"support":[68],"videos":[69],"while":[70],"ignoring":[71],"spatial":[73,82,106,120,137],"relations.":[74],"In":[75,203],"paper,":[77],"we":[78,174,206],"find":[79],"that":[80,117],"misalignment":[83],"objects":[85],"also":[86,207],"occurs":[87],"videos,":[89],"notably":[90],"more":[91,111],"common":[92],"than":[93],"inconsistency.":[96],"We":[97],"are":[98],"thus":[99],"motivated":[100],"investigate":[102],"importance":[104],"of":[105,157,194],"propose":[109,175],"accurate":[112],"method":[116],"leverages":[118],"both":[119],"information.":[123],"Particularly,":[124],"Spatial":[127],"Alignment":[128],"Cross":[129],"Transformer":[130],"(SA-CT)":[131],"which":[132],"learns":[133],"re-adjust":[135],"incorporates":[140],"information":[143],"is":[144,159],"contributed.":[145],"Experiments":[146],"reveal":[147],"that,":[148],"even":[149],"without":[150],"using":[151],"any":[152],"information,":[154,173],"performance":[156,193],"SA-CT":[158,197],"comparable":[160],"based":[163],"3/4":[166],"benchmarks.":[167],"further":[169],"incorporate":[170],"simple":[177],"effective":[179],"Temporal":[180,184],"Mixer":[181,185],"module.":[182],"The":[183],"enhances":[186],"representation":[189],"improves":[191],"full":[196],"model,":[198],"achieving":[199],"very":[200],"competitive":[201],"results.":[202],"work,":[205],"exploit":[208],"large-scale":[209],"pretrained":[210],"models":[211],"for":[212,219],"providing":[216],"useful":[217],"insights":[218],"research":[221],"direction.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}