{"id":"https://openalex.org/W4324286749","doi":"https://doi.org/10.1145/3579109.3579124","title":"Multi-scale Convolutional Feature Fusion For 6D Pose Estimation","display_name":"Multi-scale Convolutional Feature Fusion For 6D Pose Estimation","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4324286749","doi":"https://doi.org/10.1145/3579109.3579124"},"language":"en","primary_location":{"id":"doi:10.1145/3579109.3579124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579109.3579124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Video and Image Processing","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/A5073785755","display_name":"Yan Ren","orcid":"https://orcid.org/0000-0002-9116-5825"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Ren","raw_affiliation_strings":["School of Information Science and Engineering, Shenyang University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shenyang University of Technology, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090192467","display_name":"Jiamin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Liu","raw_affiliation_strings":["School of Information Science and Engineering, Shenyang University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shenyang University of Technology, China","institution_ids":["https://openalex.org/I157507598"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073785755"],"corresponding_institution_ids":["https://openalex.org/I157507598"],"apc_list":null,"apc_paid":null,"fwci":0.302,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56190015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9890000224113464,"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":0.9890000224113464,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7214713096618652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7181149125099182},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6510966420173645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6440854072570801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6026947498321533},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5843276977539062},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5556424260139465},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5524866580963135},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5515317320823669},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5508872270584106},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5349076986312866},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4475284218788147},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4393857717514038},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43280211091041565},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33152902126312256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2100900113582611}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7214713096618652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181149125099182},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6510966420173645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6440854072570801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6026947498321533},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5843276977539062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5556424260139465},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5524866580963135},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5515317320823669},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5508872270584106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5349076986312866},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4475284218788147},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4393857717514038},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43280211091041565},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33152902126312256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2100900113582611},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579109.3579124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3579109.3579124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 6th International Conference on Video and Image Processing","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/W4253893311","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W4287600488","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4281696776","https://openalex.org/W4318148659","https://openalex.org/W4387967917","https://openalex.org/W4299867837"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,20,61,66,72,108],"obtain":[3,73],"accurate":[4],"pose":[5,12,37,190],"estimate":[6],"and":[7,30,76,125,136,145,168],"satisfy":[8],"real-time":[9],"needs,":[10],"6D":[11,36,189],"estimation":[13,38,191],"of":[14,69,84,93,105,113,122,182],"objects":[15,176],"is":[16,59,99,164,185],"an":[17],"important":[18],"task":[19,192],"handle":[21],"challenging":[22],"under":[23],"certain":[24],"circumstances,":[25],"such":[26],"as":[27],"noisy":[28],"background,":[29],"lighting":[31],"fluctuations.":[32],"We":[33],"propose":[34],"a":[35,116],"method":[39,184],"with":[40,96,152],"the":[41,48,53,62,67,78,85,88,91,102,106,111,119,123,133,153,158,178,188,195],"multi-scale":[42,54,74],"convolutional":[43,55,94],"feature":[44,56],"fusion":[45,57],"based":[46,156,193],"on":[47,140,157,194],"correspondence":[49,159],"point":[50,160],"method.":[51,161],"First,":[52],"module":[58],"added":[60,100],"encoder-decoder":[63],"structure":[64],"corresponding":[65,196],"extraction":[68],"critical":[70],"points":[71],"information,":[75],"enrich":[77],"features":[79],"extracted":[80],"from":[81],"each":[82],"layer":[83],"network.":[86],"At":[87],"same":[89],"time,":[90],"chain":[92],"layers":[95],"residual":[97],"learning":[98],"in":[101,177,187],"skip":[103],"connections":[104],"network":[107,155],"effectively":[109],"solve":[110],"problem":[112],"too":[114],"large":[115],"gap":[117],"between":[118],"semantic":[120],"information":[121],"higher":[124],"lower":[126],"layers.":[127],"The":[128,162,180],"experimental":[129],"results":[130],"demonstrate":[131],"that":[132],"ADD(-S)":[134],"metric":[135,139],"2D":[137],"projection":[138],"LINEMOD":[141],"dataset":[142],"reaches":[143],"96.22%":[144],"92.5%,":[146],"respectively,":[147,172],"which":[148],"are":[149],"improved":[150,165],"compared":[151],"DPOD":[154],"accuracy":[163],"by":[166],"9.3":[167],"9.8":[169],"percentage":[170],"points,":[171],"for":[173],"smaller":[174],"size":[175],"dataset.":[179],"effectiveness":[181],"this":[183],"demonstrated":[186],"point.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}