{"id":"https://openalex.org/W4394994789","doi":"https://doi.org/10.1109/tmm.2024.3391899","title":"General Deformable RoI Pooling and Semi-Decoupled Head for Object Detection","display_name":"General Deformable RoI Pooling and Semi-Decoupled Head for Object Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394994789","doi":"https://doi.org/10.1109/tmm.2024.3391899"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3391899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3391899","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101936635","display_name":"Bo Han","orcid":"https://orcid.org/0000-0001-6282-5428"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Han","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039837634","display_name":"Lihuo He","orcid":"https://orcid.org/0000-0002-0555-3574"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihuo He","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078167954","display_name":"Ying Yu","orcid":"https://orcid.org/0000-0003-2836-3199"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Yu","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059540876","display_name":"Wen Lu","orcid":"https://orcid.org/0000-0002-8193-6016"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Lu","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101936635"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.6316,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90782492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"9410","last_page":"9422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9678999781608582,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9678999781608582,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9623000025749207,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9376000165939331,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8458317518234253},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6972760558128357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6696847081184387},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.665274441242218},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6280617117881775},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.572342574596405},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5364300608634949},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3836081624031067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458317518234253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6972760558128357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696847081184387},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.665274441242218},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6280617117881775},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.572342574596405},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5364300608634949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3836081624031067},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3391899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3391899","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4395595032","display_name":null,"funder_award_id":"62441601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G463811269","display_name":null,"funder_award_id":"62276203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913836228","display_name":null,"funder_award_id":"62036007","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2601564443","https://openalex.org/W2886904239","https://openalex.org/W2894651257","https://openalex.org/W2901758161","https://openalex.org/W2962721361","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963179609","https://openalex.org/W2963351448","https://openalex.org/W2963786238","https://openalex.org/W2963857746","https://openalex.org/W2964444661","https://openalex.org/W2982770724","https://openalex.org/W2987322772","https://openalex.org/W2989604896","https://openalex.org/W2989676862","https://openalex.org/W3014595575","https://openalex.org/W3018757597","https://openalex.org/W3034307881","https://openalex.org/W3034971973","https://openalex.org/W3035396860","https://openalex.org/W3035473155","https://openalex.org/W3035694605","https://openalex.org/W3107727158","https://openalex.org/W3116271762","https://openalex.org/W3135934332","https://openalex.org/W3137160206","https://openalex.org/W3154360923","https://openalex.org/W3161927037","https://openalex.org/W3172087149","https://openalex.org/W3176839087","https://openalex.org/W3179888767","https://openalex.org/W3190624940","https://openalex.org/W3206600220","https://openalex.org/W3209635225","https://openalex.org/W3213476061","https://openalex.org/W4205334590","https://openalex.org/W4214507171","https://openalex.org/W4214767101","https://openalex.org/W4221079664","https://openalex.org/W4226160848","https://openalex.org/W4233467483","https://openalex.org/W4283807197","https://openalex.org/W4285106469","https://openalex.org/W4285345667","https://openalex.org/W4288325606","https://openalex.org/W4293584584","https://openalex.org/W4297775537","https://openalex.org/W4302773578","https://openalex.org/W4312313652","https://openalex.org/W4312348243","https://openalex.org/W4312609198","https://openalex.org/W4313147673","https://openalex.org/W4320002812","https://openalex.org/W4362653142","https://openalex.org/W4385988955","https://openalex.org/W6737664043","https://openalex.org/W6750227808","https://openalex.org/W6757040593","https://openalex.org/W6763233178","https://openalex.org/W6764322716","https://openalex.org/W6777046832"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Object":[0],"detection":[1,46,138],"aims":[2],"to":[3,54,120,133,146,168],"classify":[4],"interest":[5],"objects":[6],"within":[7],"an":[8,198],"image":[9],"and":[10,21,35,45,105,107,128,136,180,213,236],"pinpoint":[11],"their":[12,154],"positions":[13],"using":[14],"predicted":[15,65],"rectangular":[16],"bounding":[17,66],"boxes.":[18],"However,":[19],"classification":[20,71,104,127],"localization":[22,75,129],"tasks":[23],"are":[24],"heterogeneous,":[25],"not":[26],"only":[27],"spatially":[28],"misaligned":[29],"but":[30,73],"also":[31,162],"differing":[32],"in":[33,60,202],"properties":[34],"feature":[36],"requirements.":[37],"Modern":[38],"detectors":[39],"commonly":[40],"share":[41],"the":[42,64,84,100,110,114,121,140,144,159,186,191,194,219,226,230],"spatial":[43,85,187],"region":[44],"head":[47,116,123,142,161],"for":[48,103],"both":[49],"tasks,":[50],"making":[51],"them":[52],"challenging":[53],"achieve":[55],"optimal":[56],"performance":[57],"altogether,":[58],"resulting":[59],"inconsistent":[61],"accuracy.":[62],"Specifically,":[63],"box":[67],"may":[68],"have":[69],"higher":[70],"confidence":[72],"lower":[74],"quality,":[76],"or":[77],"vice":[78],"versa.":[79],"To":[80],"tackle":[81],"this":[82],"issue,":[83],"decoupling":[86,135,188],"mechanism":[87,97,189],"via":[88],"general":[89],"deformable":[90],"RoI":[91],"pooling":[92],"is":[93,117,242],"first":[94],"proposed.":[95],"This":[96],"separately":[98],"pursues":[99],"favorable":[101],"regions":[102],"localization,":[106],"subsequently":[108],"extracts":[109],"corresponding":[111],"features.":[112],"Then,":[113],"semi-decoupled":[115,141,160,192],"designed.":[118],"Compared":[119],"decoupled":[122],"that":[124,225],"utilizes":[125],"independent":[126],"networks,":[130],"potentially":[131],"leading":[132],"excessive":[134],"compromised":[137],"performance,":[139],"enables":[143],"networks":[145,179],"mutually":[147],"enhance":[148],"each":[149],"other":[150],"while":[151],"concentrating":[152],"on":[153,218],"respective":[155],"tasks.":[156],"In":[157],"addition,":[158],"introduces":[163],"a":[164,233],"redundancy":[165],"suppression":[166],"module":[167],"filter":[169],"out":[170],"redundant":[171],"task-irrelevant":[172],"information":[173],"of":[174],"features":[175],"extracted":[176],"by":[177,232],"separate":[178],"reinforce":[181],"task-related":[182],"information.":[183],"By":[184],"combining":[185],"with":[190,206],"head,":[193],"proposed":[195,227],"detector":[196,228],"achieves":[197],"impressive":[199],"43.7":[200],"AP":[201],"Faster":[203],"R-CNN":[204],"framework":[205],"ResNet-101":[207],"as":[208],"backbone":[209],"network.":[210],"Without":[211],"bells":[212],"whistles,":[214],"extensive":[215],"experimental":[216],"results":[217],"popular":[220],"MS":[221],"COCO":[222],"dataset":[223],"demonstrate":[224],"suppresses":[229],"baseline":[231],"significant":[234],"margin":[235],"outperforms":[237],"some":[238],"state-of-the-art":[239],"detectors.":[240],"Code":[241],"available":[243],"at":[244],"<uri":[245],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[246],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/HB-X/gdpool_semi_dehead</uri>":[247],".":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}