{"id":"https://openalex.org/W3196689140","doi":"https://doi.org/10.1145/3460426.3463648","title":"Joint Hand-Object Pose Estimation with Differentiably-Learned Physical Contact Point Analysis","display_name":"Joint Hand-Object Pose Estimation with Differentiably-Learned Physical Contact Point Analysis","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196689140","doi":"https://doi.org/10.1145/3460426.3463648","mag":"3196689140"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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/A5081705021","display_name":"Nan Zhuang","orcid":"https://orcid.org/0009-0006-5023-2661"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nan Zhuang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081705021"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.5493,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65727081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"420","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996999979019165,"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":0.9936000108718872,"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/pose","display_name":"Pose","score":0.7276428937911987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7210519909858704},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6096065640449524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5757156610488892},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5616670846939087},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5080704689025879},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5077000856399536},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4207504391670227},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2972673177719116}],"concepts":[{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7276428937911987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210519909858704},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6096065640449524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5757156610488892},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5616670846939087},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5080704689025879},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5077000856399536},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4207504391670227},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2972673177719116},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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":27,"referenced_works":["https://openalex.org/W2037729465","https://openalex.org/W2140173255","https://openalex.org/W2473634362","https://openalex.org/W2604236302","https://openalex.org/W2605973302","https://openalex.org/W2606627193","https://openalex.org/W2737305288","https://openalex.org/W2750326862","https://openalex.org/W2768879211","https://openalex.org/W2796453247","https://openalex.org/W2796717907","https://openalex.org/W2799191197","https://openalex.org/W2889123596","https://openalex.org/W2892644985","https://openalex.org/W2896229066","https://openalex.org/W2897765997","https://openalex.org/W2951006673","https://openalex.org/W2962067162","https://openalex.org/W2962811204","https://openalex.org/W2963091746","https://openalex.org/W2963601560","https://openalex.org/W2972662547","https://openalex.org/W2984612350","https://openalex.org/W2984624776","https://openalex.org/W3035198432","https://openalex.org/W3108516375","https://openalex.org/W3109047546"],"related_works":["https://openalex.org/W2123263858","https://openalex.org/W3127959533","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4387967917","https://openalex.org/W2142795561","https://openalex.org/W2736638679","https://openalex.org/W4313046826","https://openalex.org/W1968716783"],"abstract_inverted_index":{"Hand-object":[0],"pose":[1,221],"estimation":[2,65,194],"aims":[3],"to":[4,61,106,128,143,169,184],"jointly":[5,107],"estimate":[6],"3D":[7,148,166,193,220],"poses":[8],"of":[9,26,66,80,119,156,219],"hands":[10,19,29,90,157],"and":[11,20,24,30,35,68,91,112,135,158,163,189,205,215],"the":[12,16,22,63,78,84,95,154,175,186,192,213,217],"held":[13],"objects.":[14,92],"During":[15],"interaction":[17,87,113,187],"between":[18,89],"objects,":[21],"position":[23],"motion":[25],"keypoints":[27,131,146,155],"in":[28],"objects":[31,159],"are":[32,178],"tightly":[33],"related":[34],"there":[36],"naturally":[37],"exist":[38],"some":[39],"physical":[40,58,72,96,202],"restrictions,":[41],"which":[42,82],"is":[43,83,103,126,141],"usually":[44],"ignored":[45],"by":[46],"most":[47,85],"previous":[48],"methods.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54],"propose":[55],"a":[56,99,137,181],"learnable":[57],"affinity":[59,97,203],"loss":[60,204],"regularize":[62],"joint":[64],"hand":[67],"object":[69],"poses.":[70],"The":[71,115],"constraints":[73],"mainly":[74],"focus":[75],"on":[76],"enhancing":[77],"stability":[79],"grasping,":[81],"common":[86],"manner":[88],"Together":[93],"with":[94],"loss,":[98],"context-aware":[100,207],"graph":[101,139,151,183,208],"network":[102,209],"also":[104],"proposed":[105],"learn":[108],"independent":[109],"geometry":[110],"prior":[111],"messages.":[114],"whole":[116,182],"pipeline":[117],"consists":[118],"two":[120,161,176],"components.":[121],"First":[122],"an":[123],"image":[124,134],"encoder":[125],"used":[127],"predict":[129],"2D":[130,145],"from":[132],"RGB":[133],"then":[136],"contextual":[138],"module":[140,152],"designed":[142],"convert":[144],"into":[147,180],"estimations.":[149],"Our":[150],"treats":[153],"as":[160],"sub-graphs":[162,177],"estimates":[164],"initial":[165],"coordinates":[167],"according":[168],"their":[170],"topology":[171],"structure":[172],"separately.":[173],"Then":[174],"merged":[179],"capture":[185,212],"information":[188],"further":[190],"refine":[191],"results.":[195],"Experimental":[196],"results":[197],"show":[198],"that":[199],"both":[200],"our":[201,206],"can":[210],"effectively":[211],"relationship":[214],"improve":[216],"accuracy":[218],"estimation.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}