{"id":"https://openalex.org/W4406857624","doi":"https://doi.org/10.1109/tmm.2025.3535321","title":"Stream-ViT: Learning Streamlined Convolutions in Vision Transformer","display_name":"Stream-ViT: Learning Streamlined Convolutions in Vision Transformer","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857624","doi":"https://doi.org/10.1109/tmm.2025.3535321"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535321","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":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/10814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041154840","display_name":"Yehao Li","orcid":"https://orcid.org/0000-0002-9603-1113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yehao Li","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010722442","display_name":"Chong\u2010Wah Ngo","orcid":"https://orcid.org/0000-0003-4182-8261"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["School of Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085403640"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8723,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94296219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"3755","last_page":"3765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9293000102043152,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9293000102043152,"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/T10320","display_name":"Neural Networks and Applications","score":0.9253000020980835,"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":0.8315047025680542},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5578641295433044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49432969093322754},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41560885310173035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3508341908454895},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10657021403312683},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0963873565196991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315047025680542},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5578641295433044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49432969093322754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41560885310173035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3508341908454895},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10657021403312683},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0963873565196991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3535321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535321","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"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11816","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10814","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TMM.2025.3535321","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11816","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10814","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/TMM.2025.3535321","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G163158741","display_name":null,"funder_award_id":"20240484681","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2507296351","https://openalex.org/W2549139847","https://openalex.org/W2787091153","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W2922509574","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2981413347","https://openalex.org/W2983446232","https://openalex.org/W2998508940","https://openalex.org/W3014641072","https://openalex.org/W3016719260","https://openalex.org/W3034421924","https://openalex.org/W3034885317","https://openalex.org/W3035284526","https://openalex.org/W3035396860","https://openalex.org/W3035682985","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3109269658","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3160694286","https://openalex.org/W3171038842","https://openalex.org/W3172509117","https://openalex.org/W3172752666","https://openalex.org/W3172801447","https://openalex.org/W3175515048","https://openalex.org/W3183430956","https://openalex.org/W3214466318","https://openalex.org/W4214493665","https://openalex.org/W4214634256","https://openalex.org/W4214636423","https://openalex.org/W4214669216","https://openalex.org/W4246193833","https://openalex.org/W4282964635","https://openalex.org/W4282968790","https://openalex.org/W4295308583","https://openalex.org/W4312363311","https://openalex.org/W4312443924","https://openalex.org/W4312453657","https://openalex.org/W4312800447","https://openalex.org/W4312832682","https://openalex.org/W4315705623","https://openalex.org/W4319663728","https://openalex.org/W4366352791","https://openalex.org/W4384080715","https://openalex.org/W4385245566","https://openalex.org/W4386072307","https://openalex.org/W4392940320","https://openalex.org/W4402727704","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6726497184","https://openalex.org/W6737664043","https://openalex.org/W6757585730","https://openalex.org/W6757817989","https://openalex.org/W6762718338","https://openalex.org/W6763367864","https://openalex.org/W6764990469","https://openalex.org/W6767312599","https://openalex.org/W6779586474","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6791978202","https://openalex.org/W6793164127","https://openalex.org/W6794345597","https://openalex.org/W6795140394","https://openalex.org/W6795308139","https://openalex.org/W6796526935","https://openalex.org/W6796931752","https://openalex.org/W6797235774","https://openalex.org/W6798016242"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recently":[0],"Vision":[1],"Transformer":[2,53],"(ViT)":[3],"and":[4,22,158,164],"Convolution":[5],"Neural":[6],"Network":[7],"(CNN)":[8],"start":[9],"to":[10,57,100,126],"emerge":[11],"as":[12],"a":[13,51,65,80,97,119,127,145],"hybrid":[14,28],"deep":[15],"architecture":[16,54,95],"with":[17,35,61,141,167],"better":[18],"model":[19],"capacity,":[20],"generalization,":[21],"latency":[23],"trade-off.":[24],"Most":[25],"of":[26,67,73,82,118,130,138,152],"these":[27],"architectures":[29],"often":[30],"directly":[31],"stack":[32],"self-attention":[33,139],"module":[34,140],"static":[36],"convolution":[37,75,122,132],"or":[38],"fuse":[39],"their":[40],"outputs":[41],"through":[42],"two":[43],"pathways":[44],"within":[45],"each":[46,74],"block.":[47],"Instead,":[48],"we":[49],"present":[50],"new":[52,94],"(namely":[55],"Stream-ViT)":[56],"novelly":[58],"integrate":[59],"ViT":[60,163],"streamlined":[62,121],"convolutions,":[63],"i.e.,":[64],"series":[66],"high-to-low":[68],"resolution":[69],"convolutions.":[70],"The":[71,93],"kernels":[72,88],"are":[76],"dynamically":[77,109],"learnt":[78,110],"on":[79],"basis":[81],"current":[83],"input":[84],"features":[85],"plus":[86],"pre-learnt":[87],"throughout":[89],"the":[90,106,116,136,150],"whole":[91],"network.":[92],"incorporates":[96],"critical":[98],"pathway":[99],"streamline":[101],"kernel":[102],"generation":[103],"that":[104],"triggers":[105],"interactions":[107],"between":[108],"convolutions":[111],"across":[112],"different":[113],"layers.":[114],"Moreover,":[115],"introduction":[117],"layer-wise":[120],"is":[123],"functionally":[124],"equivalent":[125],"squeezed":[128],"version":[129],"multi-branch":[131],"structure,":[133],"thereby":[134],"improving":[135],"capacity":[137],"enlarged":[142],"cardinality":[143],"in":[144],"cost-efficient":[146],"manner.":[147],"We":[148],"validate":[149],"superiority":[151],"Stream-ViT":[153],"over":[154],"multiple":[155],"vision":[156],"tasks,":[157],"its":[159],"performances":[160],"surpass":[161],"state-of-the-art":[162],"CNN":[165],"backbones":[166],"comparable":[168],"FLOPs.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}