{"id":"https://openalex.org/W4402351775","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649969","title":"Novel Design Ideas that Improve Video-Understanding Networks with Transformers","display_name":"Novel Design Ideas that Improve Video-Understanding Networks with Transformers","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351775","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649969"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10649969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5111319804","display_name":"Yaxin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092939","display_name":"Institute for Integrative and Experimental Genomics","ror":"https://ror.org/00fy7kr67","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210092939"]},{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yaxin Hu","raw_affiliation_strings":["University of Luebeck,Institute of Neuro- and Bioinformatic,Luebeck,Germany"],"affiliations":[{"raw_affiliation_string":"University of Luebeck,Institute of Neuro- and Bioinformatic,Luebeck,Germany","institution_ids":["https://openalex.org/I9341345","https://openalex.org/I4210092939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021756032","display_name":"Erhardt Barth","orcid":"https://orcid.org/0000-0001-8556-2472"},"institutions":[{"id":"https://openalex.org/I4210092939","display_name":"Institute for Integrative and Experimental Genomics","ror":"https://ror.org/00fy7kr67","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210092939"]},{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erhardt Barth","raw_affiliation_strings":["University of Luebeck,Institute of Neuro- and Bioinformatic,Luebeck,Germany"],"affiliations":[{"raw_affiliation_string":"University of Luebeck,Institute of Neuro- and Bioinformatic,Luebeck,Germany","institution_ids":["https://openalex.org/I9341345","https://openalex.org/I4210092939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111319804"],"corresponding_institution_ids":["https://openalex.org/I4210092939","https://openalex.org/I9341345"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53136559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987000226974487,"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":0.9966999888420105,"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":0.6655124425888062},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5833055973052979},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.20992246270179749},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20370721817016602},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0892874002456665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655124425888062},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5833055973052979},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.20992246270179749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20370721817016602},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0892874002456665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10649969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1536957109","https://openalex.org/W1578285471","https://openalex.org/W1586939924","https://openalex.org/W1595717062","https://openalex.org/W2012664231","https://openalex.org/W2020163092","https://openalex.org/W2103518000","https://openalex.org/W2105101328","https://openalex.org/W2156303437","https://openalex.org/W2507009361","https://openalex.org/W2768282280","https://openalex.org/W2962934715","https://openalex.org/W2963155035","https://openalex.org/W2963246338","https://openalex.org/W2963263347","https://openalex.org/W2963524571","https://openalex.org/W3034572008","https://openalex.org/W3094502228","https://openalex.org/W3113370935","https://openalex.org/W3126721948","https://openalex.org/W3210279979","https://openalex.org/W4205256528","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4221142360","https://openalex.org/W4221167396","https://openalex.org/W4246193833","https://openalex.org/W4309396261","https://openalex.org/W4310921506","https://openalex.org/W4312560592","https://openalex.org/W4312658081","https://openalex.org/W4386076398","https://openalex.org/W4386790714","https://openalex.org/W4394597798","https://openalex.org/W6600983433","https://openalex.org/W6682864246","https://openalex.org/W6726497184","https://openalex.org/W6746052068","https://openalex.org/W6784333009","https://openalex.org/W6787254463","https://openalex.org/W6810265253","https://openalex.org/W6846726380","https://openalex.org/W6846867676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"With":[0],"the":[1,66,69,74,89,97,100,112],"development":[2],"of":[3,62,68,99,127],"deep":[4],"learning,":[5],"video":[6,55],"understanding":[7],"has":[8],"become":[9],"a":[10,63,103,115],"promising":[11],"and":[12,36,47,65,87,130],"challenging":[13],"research":[14],"field.":[15],"In":[16,78],"recent":[17],"years,":[18],"different":[19],"transformer":[20],"architectures":[21],"have":[22,48],"shown":[23],"state-of-the-art":[24],"performance":[25,134],"on":[26],"most":[27],"benchmarks.":[28],"Although":[29],"transformers":[30,56],"can":[31],"process":[32],"longer":[33],"temporal":[34],"sequences":[35],"therefor":[37],"perform":[38],"better":[39,95],"than":[40],"convolution":[41],"networks,":[42],"they":[43],"require":[44],"huge":[45],"datasets":[46],"high":[49],"computational":[50,107],"costs.":[51,108],"The":[52,125],"inputs":[53],"to":[54,85,94],"are":[57],"usually":[58],"clips":[59,70],"sampled":[60],"out":[61],"video,":[64,91],"length":[67],"is":[71],"limited":[72],"by":[73,119,135],"available":[75],"computing":[76],"resources.":[77],"this":[79],"paper,":[80],"we":[81,110],"introduce":[82,111],"novel":[83,116],"methods":[84],"sample":[86],"tokenize":[88],"input":[90,101],"such":[92],"as":[93,114],"capture":[96],"dynamics":[98],"without":[102],"large":[104],"increase":[105],"in":[106,122],"Moreover,":[109],"MinBlocks":[113,131],"architecture":[117],"inspired":[118],"neural":[120],"processing":[121],"biological":[123],"vision.":[124],"combination":[126],"variable":[128],"tubes":[129],"improves":[132],"network":[133],"10.67%.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}