{"id":"https://openalex.org/W4412673663","doi":"https://doi.org/10.1145/3731165","title":"Interspatial Attention for Efficient 4D Human Video Generation","display_name":"Interspatial Attention for Efficient 4D Human Video Generation","publication_year":2025,"publication_date":"2025-07-27","ids":{"openalex":"https://openalex.org/W4412673663","doi":"https://doi.org/10.1145/3731165"},"language":"en","primary_location":{"id":"doi:10.1145/3731165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731165","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3731165","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078824028","display_name":"Ruizhi Shao","orcid":"https://orcid.org/0000-0003-2188-1348"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhi Shao","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-1348","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019024625","display_name":"Yinghao Xu","orcid":"https://orcid.org/0000-0003-2696-9664"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghao Xu","raw_affiliation_strings":["Stanford University, Stanford, USA"],"raw_orcid":"https://orcid.org/0000-0003-2696-9664","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Shen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3801-6705","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025976462","display_name":"Ceyuan Yang","orcid":"https://orcid.org/0000-0003-1417-1938"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ceyuan Yang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1417-1938","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zheng","orcid":"https://orcid.org/0009-0002-6586-7775"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zheng","raw_affiliation_strings":["Stanford University, Stanford, USA"],"raw_orcid":"https://orcid.org/0009-0002-6586-7775","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118519923","display_name":"Changan Chen","orcid":"https://orcid.org/0000-0003-3990-6873"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changan Chen","raw_affiliation_strings":["Stanford University, Stanford, USA"],"raw_orcid":"https://orcid.org/0000-0003-3990-6873","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032875389","display_name":"Yebin Liu","orcid":"https://orcid.org/0000-0003-3215-0225"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yebin Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3215-0225","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014044649","display_name":"Gordon Wetzstein","orcid":"https://orcid.org/0000-0002-9243-6885"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wetzstein","raw_affiliation_strings":["Stanford University, Stanford, USA"],"raw_orcid":"https://orcid.org/0000-0002-9243-6885","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72623586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"44","issue":"4","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9998000264167786,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9998000264167786,"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":0.9994000196456909,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.6886980533599854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.480217307806015},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.45485547184944153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41924434900283813},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34170520305633545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886980533599854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.480217307806015},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.45485547184944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41924434900283813},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34170520305633545}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731165","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171816","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171816","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1145/3731165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731165","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2769666294","https://openalex.org/W2962785568","https://openalex.org/W2964002510","https://openalex.org/W2965813579","https://openalex.org/W3013175169","https://openalex.org/W3023742835","https://openalex.org/W3180770160","https://openalex.org/W4200502498","https://openalex.org/W4283753473","https://openalex.org/W4288363486","https://openalex.org/W4312633146","https://openalex.org/W4312891300","https://openalex.org/W4312933868","https://openalex.org/W4385275452","https://openalex.org/W4385489997","https://openalex.org/W4386076280","https://openalex.org/W4390190334","https://openalex.org/W4390871746","https://openalex.org/W4390874306","https://openalex.org/W4400518679","https://openalex.org/W4402660110","https://openalex.org/W4402727211","https://openalex.org/W4402727213","https://openalex.org/W4402774699","https://openalex.org/W6600903635","https://openalex.org/W6601152313","https://openalex.org/W6680120035"],"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":{"Generating":[0],"photorealistic":[1],"videos":[2],"of":[3,15,80,92,112,136],"digital":[4,49],"humans":[5],"in":[6],"a":[7,13,56,63,77,96,103,109],"controllable":[8],"manner":[9],"is":[10,76],"crucial":[11],"for":[12,67,89,120],"plethora":[14],"applications.":[16],"Existing":[17],"approaches":[18],"either":[19],"build":[20],"on":[21,108],"methods":[22],"that":[23,83],"employ":[24],"template-based":[25],"3D":[26],"representations":[27],"or":[28,38,47],"emerging":[29],"video":[30,72,98,113,123],"generation":[31,73,91],"models":[32],"but":[33],"suffer":[34],"from":[35],"poor":[36],"quality":[37],"limited":[39],"consistency":[40,128],"and":[41,129,139,144],"identity":[42,130],"preservation":[43,131],"when":[44],"generating":[45],"individual":[46],"multiple":[48],"humans.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,101],"introduce":[55],"new":[57,78],"interspatial":[58],"attention":[59,82],"(ISA)":[60],"mechanism":[61],"as":[62],"scalable":[64],"building":[65],"block":[66],"modern":[68],"diffusion":[69,106],"transformer":[70],"(DiT)-based":[71],"models.":[74],"ISA":[75],"type":[79],"cross":[81],"uses":[84],"relative":[85],"positional":[86],"encodings":[87],"tailored":[88],"the":[90,137],"human":[93,122],"videos.":[94],"Leveraging":[95],"custom-developed":[97],"variation":[99],"autoencoder,":[100],"train":[102],"latent":[104],"ISA-based":[105],"model":[107,116,145],"large":[110],"corpus":[111],"data.":[114],"Our":[115,142],"achieves":[117],"state-of-the-art":[118],"performance":[119],"4D":[121],"synthesis,":[124],"demonstrating":[125],"remarkable":[126],"motion":[127],"while":[132],"providing":[133],"precise":[134],"control":[135],"camera":[138],"body":[140],"poses.":[141],"code":[143],"are":[146],"publicly":[147],"released":[148],"at":[149],"https://dsaurus.github.io/isa4d/.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
