{"id":"https://openalex.org/W3119324419","doi":"https://doi.org/10.1109/tmm.2021.3050058","title":"SAM: Modeling Scene, Object and Action With Semantics Attention Modules for Video Recognition","display_name":"SAM: Modeling Scene, Object and Action With Semantics Attention Modules for Video Recognition","publication_year":2021,"publication_date":"2021-01-09","ids":{"openalex":"https://openalex.org/W3119324419","doi":"https://doi.org/10.1109/tmm.2021.3050058","mag":"3119324419"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3050058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3050058","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5060677081","display_name":"Xing Zhang","orcid":"https://orcid.org/0000-0002-1721-035X"},"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":"Xing Zhang","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1721-035X","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/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":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8689-5807","affiliations":[{"raw_affiliation_string":"School of Computer Science, 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":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"School of Computer Science, 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":0.6595,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69215826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"24","issue":null,"first_page":"313","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9872999787330627,"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":0.8781133890151978},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7487393021583557},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6623504161834717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.637282133102417},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.566860020160675},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.54412442445755},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5135079026222229},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5076712369918823},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.47590479254722595},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4656546711921692},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44624796509742737},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.42887192964553833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4003518521785736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3956248164176941},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34071844816207886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1813124716281891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8781133890151978},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7487393021583557},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6623504161834717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.637282133102417},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.566860020160675},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.54412442445755},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5135079026222229},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5076712369918823},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.47590479254722595},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4656546711921692},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44624796509742737},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.42887192964553833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4003518521785736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3956248164176941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34071844816207886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1813124716281891},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3050058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3050058","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1777628566","https://openalex.org/W1927052826","https://openalex.org/W1954433395","https://openalex.org/W1989085630","https://openalex.org/W2024051019","https://openalex.org/W2068611653","https://openalex.org/W2101443479","https://openalex.org/W2105101328","https://openalex.org/W2139395976","https://openalex.org/W2156303437","https://openalex.org/W2161565164","https://openalex.org/W2161969291","https://openalex.org/W2164507085","https://openalex.org/W2194775991","https://openalex.org/W2216674905","https://openalex.org/W2342662179","https://openalex.org/W2470774766","https://openalex.org/W2473032611","https://openalex.org/W2507009361","https://openalex.org/W2524365899","https://openalex.org/W2608988379","https://openalex.org/W2619947201","https://openalex.org/W2620629206","https://openalex.org/W2706729717","https://openalex.org/W2732026016","https://openalex.org/W2739107216","https://openalex.org/W2752386593","https://openalex.org/W2770446450","https://openalex.org/W2777300582","https://openalex.org/W2788647998","https://openalex.org/W2802501778","https://openalex.org/W2806331055","https://openalex.org/W2809273606","https://openalex.org/W2891544687","https://openalex.org/W2894608918","https://openalex.org/W2897426518","https://openalex.org/W2902469875","https://openalex.org/W2904017099","https://openalex.org/W2906314281","https://openalex.org/W2913302158","https://openalex.org/W2920882913","https://openalex.org/W2950212751","https://openalex.org/W2950568498","https://openalex.org/W2951019013","https://openalex.org/W2962711930","https://openalex.org/W2962899219","https://openalex.org/W2963082988","https://openalex.org/W2963091558","https://openalex.org/W2963176022","https://openalex.org/W2963274633","https://openalex.org/W2963405520","https://openalex.org/W2963722382","https://openalex.org/W2963820951","https://openalex.org/W2964214371","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2992457155","https://openalex.org/W3010010212","https://openalex.org/W3034572008","https://openalex.org/W3034658206","https://openalex.org/W3034972874","https://openalex.org/W3035180180","https://openalex.org/W3035730922","https://openalex.org/W3037046522","https://openalex.org/W3100183449","https://openalex.org/W3103366418","https://openalex.org/W3138121279","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6656675045","https://openalex.org/W6682864246","https://openalex.org/W6720429201","https://openalex.org/W6724944384","https://openalex.org/W6739520758","https://openalex.org/W6739901393","https://openalex.org/W6743837088","https://openalex.org/W6748181105","https://openalex.org/W6751936687","https://openalex.org/W6754630476","https://openalex.org/W6757163628","https://openalex.org/W6773475121","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4311555960","https://openalex.org/W4390871823"],"abstract_inverted_index":{"Video":[0],"recognition":[1,25],"aims":[2],"at":[3],"understanding":[4],"semantic":[5],"contents":[6],"that":[7,39,82],"normally":[8],"involve":[9],"the":[10,50,64,84,93,98,101,114],"interactions":[11],"of":[12,52,66,86,89],"humans":[13],"and":[14,32,148],"related":[15],"objects":[16],"under":[17],"certain":[18],"scenes.":[19],"A":[20],"common":[21],"practice":[22],"to":[23,28],"improve":[24],"accuracy":[26],"is":[27,110],"combine":[29],"object,":[30],"scene":[31],"action":[33],"features":[34,54,90],"for":[35,121,134],"classification":[36],"directly,":[37],"assuming":[38],"they":[40],"are":[41,126,140],"explicitly":[42],"complementary.":[43],"In":[44],"this":[45,74],"paper,":[46],"we":[47,76],"break":[48],"down":[49],"fusion":[51],"three":[53],"into":[55],"two":[56,143],"pairwise":[57],"feature":[58,96,103,116],"relation":[59],"modeling":[60],"processes,":[61],"which":[62],"mitigates":[63],"difficulty":[65],"correlation":[67],"learning":[68],"in":[69,128],"high":[70],"dimensional":[71],"features.":[72],"Towards":[73],"goal,":[75],"introduce":[77],"a":[78,87,118,129],"Semantics":[79,130],"Attention":[80,131],"Module":[81],"captures":[83],"relations":[85],"pair":[88],"by":[91],"refining":[92],"relatively":[94],"\u201cweak\u201d":[95],"with":[97,113],"guidance":[99],"from":[100],"\u201cstrong\u201d":[102,115],"using":[104,117],"attention":[105],"mechanisms.":[106],"The":[107],"refined":[108],"representation":[109],"further":[111],"combined":[112],"residual":[119],"design":[120],"downstream":[122],"tasks.":[123],"Two":[124],"SAMs":[125],"applied":[127],"Network":[132],"(SAN)":[133],"improving":[135],"video":[136,145],"recognition.":[137],"Extensive":[138],"experiments":[139],"conducted":[141],"on":[142],"large-scale":[144],"benchmarks,":[146],"FCVID":[147],"ActivityNet":[149],"v1.3\u2014the":[150],"proposed":[151],"approach":[152],"achieves":[153],"better":[154],"results":[155],"while":[156],"requiring":[157],"much":[158],"less":[159],"computational":[160],"effort":[161],"than":[162],"alternative":[163],"methods.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}