{"id":"https://openalex.org/W7138267311","doi":"https://doi.org/10.1609/aaai.v40i6.42480","title":"DAPE: Harmonizing Content-Position Encoding for Versatile Dense Visual Prediction","display_name":"DAPE: Harmonizing Content-Position Encoding for Versatile Dense Visual Prediction","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138267311","doi":"https://doi.org/10.1609/aaai.v40i6.42480"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i6.42480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42480/46441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42480/46441","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069152360","display_name":"Xiuquan Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiuquan Hou","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101628778","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0001-8428-5098"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["Zhejiang University\nXi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University\nXi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124068888","display_name":"Senlin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senlin Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129728659","display_name":"Shaoyi Du","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyi Du","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069152360"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56151645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4780","last_page":"4788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9395999908447266,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9395999908447266,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01590000092983246,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.01489999983459711,"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/encoding","display_name":"Encoding (memory)","score":0.7854999899864197},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.775600016117096},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.741100013256073},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6581000089645386},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6322000026702881},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4596000015735626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4207000136375427}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7854999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771000266075134},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.775600016117096},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.741100013256073},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6581000089645386},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010000109672546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2500999867916107},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i6.42480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42480/46441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/42480/46441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.77827388048172,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2593274190","display_name":null,"funder_award_id":"62327808","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138267311.pdf","grobid_xml":"https://content.openalex.org/works/W7138267311.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"visual":[1,85],"prediction":[2,28,156],"tasks,":[3,86],"including":[4],"object":[5,18,161],"detection":[6,167],"and":[7,12,20,52,58,78,128,131,165],"segmentation,":[8,164],"inherently":[9],"require":[10],"precise":[11],"discriminative":[13],"positional":[14],"information":[15],"to":[16,34,99],"delineate":[17],"boundaries":[19],"pixel":[21],"regions.":[22],"Recent":[23],"DETR-based":[24],"frameworks":[25],"advance":[26],"dense":[27,84,155],"tasks":[29],"through":[30],"iterative":[31],"attention":[32,141],"applied":[33],"content":[35,57,101,127],"queries,":[36,130],"with":[37,90],"sampled":[38],"proposals":[39],"as":[40],"position":[41,59,97,129],"references.":[42],"However,":[43],"this":[44,110],"paradigm":[45,74],"suffers":[46],"from":[47],"the":[48,56,63,72,124,145],"misaligned":[49],"sampling":[50],"distribution":[51],"insufficient":[53],"interaction":[54],"between":[55,123],"features,":[60],"thereby":[61],"limiting":[62],"encoding":[64,73,98],"effectiveness.":[65],"To":[66,108],"overcome":[67],"these":[68],"limitations,":[69],"we":[70],"investigate":[71],"for":[75,83,153],"content-position":[76],"harmonization":[77],"propose":[79],"an":[80],"effective":[81],"predictor":[82],"termed":[87],"DAPE":[88,94,112,148,171],"(DETR":[89],"hArmonized":[91],"content-Position":[92],"Encoding).":[93],"introduces":[95],"explicit":[96],"facilitate":[100],"enhancement":[102],"while":[103,175],"maintaining":[104],"low":[105],"memory":[106,177],"overhead.":[107],"achieves":[109,172],"process,":[111],"comprises":[113],"a":[114,132,150],"Shifted":[115],"Query":[116],"Sampler":[117],"(SQS)":[118],"that":[119,138,170],"enforces":[120],"strict":[121],"alignment":[122],"distributions":[125],"of":[126],"2D":[133],"Low-Rank":[134],"Position":[135],"Encoder":[136],"(LRPE)":[137],"progressively":[139],"modulates":[140],"maps":[142],"based":[143],"on":[144,160],"aligned":[146],"representations.":[147],"provides":[149],"unified":[151],"solution":[152],"various":[154],"tasks.":[157],"Extensive":[158],"experiments":[159],"detection,":[162],"instance":[163],"few-shot":[166],"benchmarks":[168],"demonstrate":[169],"state-of-the-art":[173],"performance":[174],"reducing":[176],"consumption.":[178]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}