{"id":"https://openalex.org/W4403791737","doi":"https://doi.org/10.1145/3664647.3681043","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","display_name":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791737","doi":"https://doi.org/10.1145/3664647.3681043"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.07216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052375254","display_name":"Wenxi Li","orcid":"https://orcid.org/0000-0001-8449-0489"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxi Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035519525","display_name":"Yuchen Guo","orcid":"https://orcid.org/0000-0001-9808-9805"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Guo","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042382742","display_name":"Jilai Zheng","orcid":"https://orcid.org/0000-0003-0850-2446"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilai Zheng","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035352469","display_name":"Haozhe Lin","orcid":"https://orcid.org/0000-0002-3707-3575"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Lin","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704678","display_name":"Chao Ma","orcid":"https://orcid.org/0000-0002-8459-2845"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ma","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664962","display_name":"Lu Fang","orcid":"https://orcid.org/0000-0003-3552-0367"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Fang","raw_affiliation_strings":["Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052375254"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3755,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5771669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4851","last_page":"4860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9894000291824341,"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/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5991425514221191},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5496923327445984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4792518615722656},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41719937324523926},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13809961080551147},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10795372724533081},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08777794241905212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5991425514221191},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5496923327445984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4792518615722656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41719937324523926},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13809961080551147},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10795372724533081},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08777794241905212}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3664647.3681043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.07216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07216","pdf_url":"https://arxiv.org/pdf/2502.07216","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158989","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158989","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.07216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.07216","pdf_url":"https://arxiv.org/pdf/2502.07216","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2768489488","https://openalex.org/W2963037989","https://openalex.org/W2964979676","https://openalex.org/W2989611864","https://openalex.org/W3022917557","https://openalex.org/W3035396860","https://openalex.org/W3046174881","https://openalex.org/W3098218837","https://openalex.org/W3109055651","https://openalex.org/W3131500599","https://openalex.org/W3136761610","https://openalex.org/W3138516171","https://openalex.org/W3174873843","https://openalex.org/W3184439416","https://openalex.org/W4226407477","https://openalex.org/W4312290555","https://openalex.org/W4386101142","https://openalex.org/W4390874619","https://openalex.org/W4402702889","https://openalex.org/W4402716065"],"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":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"an":[4],"increase":[5],"in":[6,27],"the":[7,28,32,73,92,161,177],"use":[8],"of":[9,38,75],"gigapixel-level":[10],"image":[11],"and":[12,16,35,47,56,80,108,114,140,157,171],"video":[13],"capture":[14],"systems":[15],"benchmarks":[17],"with":[18],"high-resolution":[19],"wide":[20],"(HRW)":[21],"shots.":[22,82],"However,":[23],"unlike":[24],"close-up":[25,53,79],"shots":[26],"MS":[29],"COCO":[30],"dataset,":[31],"higher":[33],"resolution":[34],"wider":[36],"field":[37],"view":[39],"raise":[40],"unique":[41],"challenges,":[42],"such":[43],"as":[44],"extreme":[45],"sparsity":[46],"huge":[48,119],"scale":[49,120],"changes,":[50],"causing":[51],"existing":[52],"detectors":[54],"inaccuracy":[55],"inefficiency.":[57],"In":[58,100],"this":[59,101],"paper,":[60],"we":[61],"present":[62],"a":[63,126,141],"novel":[64,127],"model-agnostic":[65],"sparse":[66],"vision":[67],"transformer,":[68],"dubbed":[69],"SparseFormer,":[70],"to":[71,90,117,133,147,169,174],"bridge":[72],"gap":[74],"object":[76],"detection":[77,166],"between":[78],"HRW":[81,154],"The":[83],"proposed":[84,162],"SparseFormer":[85,122,163],"selectively":[86],"uses":[87],"attentive":[88],"tokens":[89],"scrutinize":[91],"sparsely":[93],"distributed":[94],"windows":[95,139],"that":[96,160],"may":[97],"contain":[98],"objects.":[99],"way,":[102],"it":[103],"can":[104],"jointly":[105],"explore":[106],"global":[107],"local":[109],"attention":[110],"by":[111],"fusing":[112],"coarse-":[113],"fine-grained":[115],"features":[116],"handle":[118],"changes.":[121],"also":[123],"benefits":[124],"from":[125,137],"Cross-slice":[128],"non-maximum":[129],"suppression":[130],"(C-NMS)":[131],"algorithm":[132],"precisely":[134],"localize":[135],"objects":[136],"noisy":[138],"simple":[142],"yet":[143],"effective":[144],"multi-scale":[145],"strategy":[146],"improve":[148],"accuracy.":[149],"Extensive":[150],"experiments":[151],"on":[152],"two":[153],"benchmarks,":[155],"PANDA":[156],"DOTA-v1.0,":[158],"demonstrate":[159],"significantly":[164],"improves":[165],"accuracy":[167],"(up":[168,173],"5.8%)":[170],"speed":[172],"3x)":[175],"over":[176],"state-of-the-art":[178],"approaches.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}