{"id":"https://openalex.org/W4402979916","doi":"https://doi.org/10.1109/icme57554.2024.10687501","title":"SDViT: Towards Efficient Visual Foundation Model via Unifying Sparse and Dense Representation Learning","display_name":"SDViT: Towards Efficient Visual Foundation Model via Unifying Sparse and Dense Representation Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979916","doi":"https://doi.org/10.1109/icme57554.2024.10687501"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687501","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5085120580","display_name":"Yin Tang","orcid":"https://orcid.org/0000-0003-4675-9074"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Tang","raw_affiliation_strings":["Nanjing Tech University,College of Computer and IE & AI,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and IE & AI,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436460","display_name":"Guang Yang","orcid":"https://orcid.org/0000-0001-7344-7733"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":["Nanjing Normal University,College of Computer and EI & AI,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Normal University,College of Computer and EI & AI,Nanjing,China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058933449","display_name":"Xili Wan","orcid":"https://orcid.org/0000-0001-9160-8246"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xili Wan","raw_affiliation_strings":["Nanjing Tech University,College of Computer and IE & AI,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Tech University,College of Computer and IE & AI,Nanjing,China","institution_ids":["https://openalex.org/I134687103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15185618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9937999844551086,"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":0.9937999844551086,"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":0.9937000274658203,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9898999929428101,"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/foundation","display_name":"Foundation (evidence)","score":0.7800609469413757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217060327529907},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6433607935905457},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5181804299354553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5056493282318115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3395427167415619}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7800609469413757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217060327529907},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6433607935905457},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5181804299354553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056493282318115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3395427167415619},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687501","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Although":[0],"window-based":[1,14],"self-attention":[2],"stands":[3],"out":[4],"as":[5],"efficient":[6],"and":[7,38,41,67,115,126,152],"effective,":[8],"a":[9,84,106,130,142],"limitation":[10],"in":[11,17],"many":[12],"previous":[13],"approaches":[15],"lies":[16],"their":[18],"reliance":[19],"on":[20,141],"fixed":[21],"partition":[22,61],"patterns":[23],"within":[24,129],"each":[25,72,102],"encoder":[26],"layer.":[27],"This":[28],"constraint":[29],"restricts":[30],"the":[31,43,119,134,157],"potential":[32],"for":[33],"flexible":[34],"interaction":[35,128],"between":[36],"query":[37,103],"key-value":[39,88],"pairs":[40,89],"limits":[42],"effective":[44],"receptive":[45],"field.":[46],"To":[47],"address":[48],"this":[49],"issue,":[50],"we":[51,95],"introduce":[52,96],"SParse":[53],"Windows":[54],"Attention":[55,99],"(SPWA),":[56],"which":[57],"includes":[58],"three":[59],"meta":[60],"patterns:":[62],"square":[63],"window,":[64,66],"stripes":[65],"dilation":[68],"window.":[69],"In":[70],"SPWA,":[71],"pattern":[73],"is":[74],"an":[75],"independent":[76],"encoding":[77,117],"branch,":[78],"allowing":[79],"queries":[80],"to":[81,105],"interact":[82],"with":[83],"broader":[85],"set":[86,107],"of":[87,108,136,144,159],"while":[90],"maintaining":[91],"linear":[92],"complexity.":[93],"Additionally,":[94],"Dense":[97],"Regional":[98],"(DRA),":[100],"where":[101],"attends":[104],"aggregated":[109],"regions.":[110],"By":[111],"empirically":[112],"combining":[113],"sparse":[114],"dense":[116],"schedules,":[118],"derived":[120],"network,":[121],"SDViT,":[122],"achieves":[123],"both":[124],"coarse":[125],"fine-grained":[127],"single":[131],"layer,":[132],"prompting":[133],"capability":[135],"multi-scale":[137],"learning.":[138],"Empirical":[139],"experiments":[140],"variety":[143],"tasks":[145],"including":[146],"ImageNet-1k":[147],"classification,":[148],"MS-COCO":[149],"object":[150],"detection,":[151],"ADE20K":[153],"semantic":[154],"segmentation":[155],"validate":[156],"effectiveness":[158],"our":[160],"approach.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}