{"id":"https://openalex.org/W4405785809","doi":"https://doi.org/10.1109/iros58592.2024.10802156","title":"Robot Shape and Location Retention in Video Generation Using Diffusion Models","display_name":"Robot Shape and Location Retention in Video Generation Using Diffusion Models","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785809","doi":"https://doi.org/10.1109/iros58592.2024.10802156"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100395956","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0001-9895-394X"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH","institution_ids":["https://openalex.org/I11983389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025698469","display_name":"Zhihao Guo","orcid":"https://orcid.org/0000-0001-8315-5152"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhihao Guo","raw_affiliation_strings":["Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH","institution_ids":["https://openalex.org/I11983389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113280438","display_name":"Abdul Latheef Sait","orcid":null},"institutions":[{"id":"https://openalex.org/I883357","display_name":"Fashion Institute of Technology","ror":"https://ror.org/03jwrn541","country_code":"US","type":"education","lineage":["https://openalex.org/I883357"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdul Latheef Sait","raw_affiliation_strings":["JD Sports Fashion PLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Sports Fashion PLC","institution_ids":["https://openalex.org/I883357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064632322","display_name":"Minh Huy Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minh Huy Pham","raw_affiliation_strings":["Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University,Department of Computing and Mathematics,Manchester,UK,M15 6BH","institution_ids":["https://openalex.org/I11983389"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59700678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7375","last_page":"7382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8827000260353088,"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/T11448","display_name":"Face recognition and analysis","score":0.8827000260353088,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.86080002784729,"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":0.8406000137329102,"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":0.6277925968170166},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6226820349693298},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5356805920600891},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5237616896629333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45271220803260803},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36171984672546387},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08173039555549622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277925968170166},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6226820349693298},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5356805920600891},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5237616896629333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45271220803260803},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36171984672546387},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08173039555549622},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311699","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2159498975","https://openalex.org/W2962974533","https://openalex.org/W4312443924","https://openalex.org/W4360884927","https://openalex.org/W4384472141","https://openalex.org/W4387806972","https://openalex.org/W4390873435","https://openalex.org/W4390874575","https://openalex.org/W4394597513","https://openalex.org/W6679045638","https://openalex.org/W6779823529","https://openalex.org/W6839081181"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,39,57,101],"have":[2,102],"marked":[3],"a":[4,33],"significant":[5],"mile-stone":[6],"in":[7,106],"the":[8,22,48,73,90,108,125],"enhancement":[9],"of":[10,26,52,93,112],"image":[11],"and":[12,24,50,67,75,95,110],"video":[13,120],"generation":[14,121],"technologies.":[15],"However,":[16],"generating":[17],"videos":[18,44],"that":[19,45],"precisely":[20],"retain":[21],"shape":[23,49,94,109],"location":[25,51,111],"moving":[27],"objects":[28],"such":[29,60],"as":[30,61,115,117],"robots":[31],"remains":[32],"challenge.":[34],"This":[35],"paper":[36],"presents":[37],"diffusion":[38,127],"specifically":[40],"tailored":[41],"to":[42,84,124],"generate":[43],"accurately":[46],"maintain":[47],"mobile":[53],"robots.":[54],"The":[55],"proposed":[56],"incorporate":[58],"techniques":[59,81],"embedding":[62],"accessible":[63],"robot":[64],"pose":[65],"information":[66],"applying":[68],"semantic":[69],"mask":[70],"regulation":[71],"within":[72],"scalable":[74],"efficient":[76],"ConvNext":[77],"backbone":[78],"network.":[79],"These":[80],"are":[82],"designed":[83],"refine":[85],"intermediate":[86],"outputs,":[87],"therefore":[88],"improving":[89],"retention":[91],"performance":[92],"location.":[96],"Through":[97],"extensive":[98],"experimentation,":[99],"our":[100],"demonstrated":[103],"notable":[104],"improvements":[105],"maintaining":[107],"different":[113],"robots,":[114],"well":[116],"enhancing":[118],"overall":[119],"quality,":[122],"compared":[123],"benchmark":[126],"model.":[128],"Codes":[129],"will":[130],"be":[131],"open-sourced":[132],"at:":[133],"https://github.com/PengPaulWang/diffusion-robots.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}