{"id":"https://openalex.org/W4401201684","doi":"https://doi.org/10.1145/3664647.3680597","title":"ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models","display_name":"ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4401201684","doi":"https://doi.org/10.1145/3664647.3680597"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.19370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peiming Li","orcid":"https://orcid.org/0009-0000-1869-7043"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Peiming Li","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","Center for Research in Computer Vision, University of Central Florida Orlando, USA"],"raw_orcid":"https://orcid.org/0009-0000-1869-7043","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyi Wang","orcid":"https://orcid.org/0009-0006-5169-1464"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Ziyi Wang","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","Center for Research in Computer Vision, University of Central Florida Orlando, USA"],"raw_orcid":"https://orcid.org/0009-0006-5169-1464","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705474","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0003-4036-9315"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","Center for Research in Computer Vision, University of Central Florida Orlando, USA"],"raw_orcid":"https://orcid.org/0000-0003-4036-9315","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","Center for Research in Computer Vision, University of Central Florida Orlando, USA"],"raw_orcid":"https://orcid.org/0000-0002-7498-6541","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3957-7061","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8238,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72431527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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/grasp","display_name":"GRASP","score":0.9261012077331543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887412309646606},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5153014659881592},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4929923713207245},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.466929167509079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46690255403518677},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.46177637577056885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3875355124473572},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3466041684150696},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17153826355934143}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9261012077331543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887412309646606},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5153014659881592},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4929923713207245},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.466929167509079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46690255403518677},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.46177637577056885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3875355124473572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3466041684150696},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17153826355934143},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.19370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19370","pdf_url":"https://arxiv.org/pdf/2407.19370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.19370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19370","pdf_url":"https://arxiv.org/pdf/2407.19370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8283459870","display_name":null,"funder_award_id":"62203476","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401201684.pdf","grobid_xml":"https://content.openalex.org/works/W4401201684.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2054657387","https://openalex.org/W2069135200","https://openalex.org/W2227547437","https://openalex.org/W2963601560","https://openalex.org/W2980216391","https://openalex.org/W2981378444","https://openalex.org/W3015055137","https://openalex.org/W3107825842","https://openalex.org/W3127909800","https://openalex.org/W3170924787","https://openalex.org/W3173636439","https://openalex.org/W3177075049","https://openalex.org/W3199621649","https://openalex.org/W3202948970","https://openalex.org/W3204221554","https://openalex.org/W4285531802","https://openalex.org/W4297683907","https://openalex.org/W4382457661","https://openalex.org/W4386066131","https://openalex.org/W4386076108","https://openalex.org/W4386076633","https://openalex.org/W4390872595","https://openalex.org/W4390889780","https://openalex.org/W4391305822"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W2657478029","https://openalex.org/W4248427955","https://openalex.org/W2106333554","https://openalex.org/W2626503888","https://openalex.org/W2037306763","https://openalex.org/W2080808138","https://openalex.org/W2129483190"],"abstract_inverted_index":{"Grasp":[0],"generation":[1,17,54,62,164],"aims":[2],"to":[3,30,96,103,146,156],"create":[4],"complex":[5,107],"hand-object":[6,34],"interactions":[7,35],"with":[8,186],"a":[9,51,59,66,114],"specified":[10],"object.":[11],"While":[12],"traditional":[13],"approaches":[14],"for":[15],"hand":[16],"have":[18],"primarily":[19],"focused":[20],"on":[21,130,166],"visibility":[22],"and":[23,42,56,102,162,168,181],"diversity":[24],"under":[25],"scene":[26],"constraints,":[27],"they":[28],"tend":[29],"overlook":[31],"the":[32,77,80,106,121,135,152,172,179],"fine-grained":[33,67,131],"such":[36],"as":[37],"contacts,":[38],"resulting":[39],"in":[40],"inaccurate":[41],"undesired":[43],"grasps.":[44,149],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49,112],"propose":[50,113],"controllable":[52,60,157],"grasp":[53,84,158],"task":[55],"introduce":[57],"ClickDiff,":[58,184],"conditional":[61],"model":[63,105],"that":[64],"leverages":[65],"Semantic":[68,92,122],"Contact":[69,93,136],"Map":[70],"(SCM).":[71],"Particularly":[72],"when":[73],"synthesizing":[74],"interactive":[75],"grasps,":[76],"method":[78],"enables":[79],"precise":[81],"control":[82],"of":[83,110,174,183],"synthesis":[85],"through":[86],"either":[87],"user-specified":[88],"or":[89],"algorithmically":[90],"predicted":[91],"Map.":[94],"Specifically,":[95],"optimally":[97],"utilize":[98],"contact":[99,127,132,140],"supervision":[100],"constraints":[101],"accurately":[104],"physical":[108],"structure":[109],"hands,":[111],"Dual":[115],"Generation":[116],"Framework.":[117],"Within":[118],"this":[119],"framework,":[120],"Conditional":[123,137],"Module":[124,138],"generates":[125],"reasonable":[126],"maps":[128,141],"based":[129],"information,":[133],"while":[134],"utilizes":[139],"alongside":[142],"object":[143],"point":[144],"clouds":[145],"generate":[147],"realistic":[148],"We":[150],"evaluate":[151],"evaluation":[153],"criteria":[154],"applicable":[155],"generation.":[159],"Both":[160],"unimanual":[161],"bimanual":[163],"experiments":[165],"GRAB":[167],"ARCTIC":[169],"datasets":[170],"verify":[171],"validity":[173],"our":[175],"proposed":[176],"method,":[177],"demonstrating":[178],"efficacy":[180],"robustness":[182],"even":[185],"previously":[187],"unseen":[188],"objects.":[189],"Our":[190],"code":[191],"is":[192],"available":[193],"at":[194],"https://github.com/adventurer-w/ClickDiff.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2024-08-01T00:00:00"}