{"id":"https://openalex.org/W4391306502","doi":"https://doi.org/10.1109/vcip59821.2023.10402608","title":"Transformer-based spatial-temporal feature lifting for 3D hand mesh reconstruction","display_name":"Transformer-based spatial-temporal feature lifting for 3D hand mesh reconstruction","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391306502","doi":"https://doi.org/10.1109/vcip59821.2023.10402608"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402608","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5108897077","display_name":"Meng-Xue Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Meng-Xue Lin","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Dept. of Computer Science,HsinChu,Taiwan","Dept. of Computer Science, National Yang Ming Chiao Tung University, HsinChu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Dept. of Computer Science,HsinChu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Dept. of Computer Science, National Yang Ming Chiao Tung University, HsinChu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062746436","display_name":"Wen-Jiin Tsai","orcid":"https://orcid.org/0000-0001-9030-5139"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Jiin Tsai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Dept. of Computer Science,HsinChu,Taiwan","Dept. of Computer Science, National Yang Ming Chiao Tung University, HsinChu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Dept. of Computer Science,HsinChu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Dept. of Computer Science, National Yang Ming Chiao Tung University, HsinChu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108897077"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18884399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9801999926567078,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.9801999926567078,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9781000018119812,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/computer-science","display_name":"Computer science","score":0.5910323262214661},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5501304268836975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4628886580467224},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44584667682647705},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41450926661491394},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.4110298454761505},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3493148684501648},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22736039757728577},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18031054735183716},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06553637981414795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5910323262214661},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5501304268836975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4628886580467224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44584667682647705},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41450926661491394},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.4110298454761505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3493148684501648},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22736039757728577},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18031054735183716},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06553637981414795},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402608","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5799999833106995,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2768683308","https://openalex.org/W2990138404","https://openalex.org/W3013785695","https://openalex.org/W3097149808","https://openalex.org/W3119787773","https://openalex.org/W3175199633","https://openalex.org/W4214684804","https://openalex.org/W4285542095","https://openalex.org/W4298014233","https://openalex.org/W4312395531","https://openalex.org/W4312648215"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2755342338","https://openalex.org/W2256933480","https://openalex.org/W2775347418","https://openalex.org/W2370081953","https://openalex.org/W2027854990"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,22],"novel":[4],"model":[5,14],"for":[6,70],"reconstructing":[7],"hand":[8],"meshes":[9],"in":[10,86],"video":[11],"sequences.":[12],"The":[13,40],"extends":[15],"the":[16,25,44,62,67,71,95,101,104],"MobRecon":[17],"[1]":[18],"pipeline":[19],"and":[20,33,51,90],"incorporates":[21],"variant":[23],"of":[24,88,103],"Transformer":[26,41,63],"architecture":[27],"which":[28],"effectively":[29],"models":[30],"both":[31],"spatial":[32],"temporal":[34,57],"relationships":[35,50],"using":[36],"distinct":[37],"positional":[38],"encodings.":[39],"encoder":[42],"enhances":[43,66],"feature":[45,68,96],"representation":[46,69],"by":[47],"modeling":[48],"joint":[49],"learning":[52],"hidden":[53],"depth":[54],"information.":[55],"Leveraging":[56],"information":[58],"from":[59],"consecutive":[60],"frames,":[61],"decoder":[64],"further":[65],"mesh":[72],"decoder\u2019s":[73],"final":[74],"prediction.":[75],"Additionally,":[76],"we":[77],"incorporate":[78],"techniques":[79],"such":[80],"as":[81],"Twice-LN,":[82],"confidence-based":[83],"attention,":[84],"scaling":[85],"place":[87],"Softmax,":[89],"learnable":[91],"encodings":[92],"to":[93],"improve":[94],"representation.":[97],"Experimental":[98],"results":[99],"demonstrate":[100],"superiority":[102],"proposed":[105],"method":[106],"over":[107],"existing":[108],"approaches.":[109]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}