{"id":"https://openalex.org/W4403792236","doi":"https://doi.org/10.1145/3664647.3680789","title":"LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention","display_name":"LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792236","doi":"https://doi.org/10.1145/3664647.3680789"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680789","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":"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/A5060010090","display_name":"Zewen Du","orcid":"https://orcid.org/0009-0003-7091-8159"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zewen Du","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7091-8159","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenjiang Hu","orcid":"https://orcid.org/0009-0006-5406-7560"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjiang Hu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5406-7560","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046071072","display_name":"Guiyu Zhao","orcid":"https://orcid.org/0009-0002-6103-774X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyu Zhao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6103-774X","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103223707","display_name":"Ying Jin","orcid":"https://orcid.org/0009-0005-6000-8172"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Jin","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-6000-8172","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072523018","display_name":"Hongbin Ma","orcid":"https://orcid.org/0000-0002-5734-3157"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Ma","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5734-3157","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9164,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79863256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4919","last_page":"4927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9908000230789185,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9908000230789185,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9904000163078308,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/upsampling","display_name":"Upsampling","score":0.8316966891288757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283505201339722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45828691124916077},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34247684478759766},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.04061880707740784}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8316966891288757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283505201339722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45828691124916077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34247684478759766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.04061880707740784}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680789","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2737258237","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963857746","https://openalex.org/W2964444661","https://openalex.org/W2985469567","https://openalex.org/W2987322772","https://openalex.org/W2993182889","https://openalex.org/W2999219213","https://openalex.org/W3032984651","https://openalex.org/W3034421924","https://openalex.org/W3034885317","https://openalex.org/W3102710196","https://openalex.org/W3138516171","https://openalex.org/W3170410843","https://openalex.org/W3170544306","https://openalex.org/W3179869055","https://openalex.org/W3180659539","https://openalex.org/W3181096156","https://openalex.org/W3181848549","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W4212774754","https://openalex.org/W4214613769","https://openalex.org/W4297411626","https://openalex.org/W4312691644","https://openalex.org/W4313007769","https://openalex.org/W4386075796","https://openalex.org/W4390873058"],"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":{"Feature":[0],"upsampling":[1,62,76,156],"is":[2,165],"an":[3],"essential":[4],"operation":[5],"in":[6,29,142,220],"constructing":[7],"deep":[8],"convolutional":[9],"neural":[10],"networks.":[11],"However,":[12],"existing":[13,84],"upsamplers":[14,85,93],"either":[15],"lack":[16],"specific":[17],"feature":[18,26,48,61,64,135],"guidance":[19,49],"or":[20],"necessitate":[21],"the":[22,42,47,58,75,81,99,113,117,134,140,145,155,178,217,221],"utilization":[23],"of":[24,32,60,66,83,92,136,150,180,205],"high-resolution":[25],"maps,":[27],"resulting":[28],"a":[30,127],"loss":[31],"performance":[33,203],"and":[34,51,78,106,147,167,193,212],"flexibility.":[35],"In":[36,162],"this":[37],"paper,":[38],"we":[39,70,110],"find":[40],"that":[41,80],"local":[43,72,96,121],"self-attention":[44,73],"naturally":[45],"has":[46],"capability,":[50],"its":[52],"computational":[53],"paradigm":[54],"aligns":[55],"closely":[56],"with":[57],"essence":[59],"(i.e.":[63],"reassembly":[65],"neighboring":[67,108,151],"points).":[68],"Therefore,":[69],"introduce":[71,112],"into":[74,116,172],"task":[77],"demonstrate":[79],"majority":[82],"can":[86,168],"be":[87,169],"regarded":[88],"as":[89],"special":[90],"cases":[91],"based":[94,119],"on":[95,120],"self-attention.":[97],"Considering":[98],"potential":[100],"semantic":[101,194],"gap":[102],"between":[103],"upsampled":[104],"points":[105],"their":[107],"points,":[109,152],"further":[111],"deformation":[114],"mechanism":[115],"upsampler":[118],"self-attention,":[122],"thereby":[123,153],"proposing":[124],"LDA-AQU.":[125],"As":[126],"novel":[128],"dynamic":[129],"kernel-based":[130],"upsampler,":[131],"LDA-AQU":[132,164,181,196],"utilizes":[133],"queries":[137],"to":[138,216],"guide":[139],"model":[141,174],"adaptively":[143],"adjusting":[144],"position":[146],"aggregation":[148],"weight":[149],"meeting":[154],"requirements":[157],"across":[158,182],"various":[159,173],"complex":[160],"scenarios.":[161],"addition,":[163],"lightweight":[166],"easily":[170],"integrated":[171],"architectures.":[175],"We":[176],"evaluate":[177],"effectiveness":[179],"four":[183,223],"dense":[184],"prediction":[185],"tasks:":[186],"object":[187],"detection,":[188],"instance":[189],"segmentation,":[190,192],"panoptic":[191],"segmentation.":[195],"consistently":[197],"outperforms":[198],"previous":[199],"state-of-the-art":[200],"upsamplers,":[201],"achieving":[202],"enhancements":[204],"1.7":[206],"AP,":[207,209],"1.5":[208],"2.0":[210],"PQ,":[211],"2.5":[213],"mIoU":[214],"compared":[215],"baseline":[218],"models":[219],"aforementioned":[222],"tasks,":[224],"respectively.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}