{"id":"https://openalex.org/W7138515899","doi":"https://doi.org/10.1609/aaai.v40i8.37533","title":"Mask2IV: Interaction-Centric Video Generation via Mask Trajectories","display_name":"Mask2IV: Interaction-Centric Video Generation via Mask Trajectories","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138515899","doi":"https://doi.org/10.1609/aaai.v40i8.37533"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i8.37533","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37533","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37533/41495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37533/41495","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129696786","display_name":"Gen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gen Li","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670885","display_name":"Bo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690294","display_name":"Jianfei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jianfei Yang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129657493","display_name":"Laura Sevilla-Lara","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laura Sevilla-Lara","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6091","last_page":"6099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39899998903274536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39899998903274536,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2680000066757202,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.13439999520778656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.7361999750137329},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.6269000172615051},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5889000296592712},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.569100022315979},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5620999932289124},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5582000017166138},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5210000276565552},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.43529999256134033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7361999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6360999941825867},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5256999731063843},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5210000276565552},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5156000256538391},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i8.37533","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37533","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37533/41495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37533","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37533","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37533/41495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138515899.pdf","grobid_xml":"https://content.openalex.org/works/W7138515899.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"interaction-centric":[1,89],"videos,":[2],"such":[3,42],"as":[4,18,55],"those":[5],"depicting":[6],"humans":[7],"or":[8,161],"robots":[9],"interacting":[10],"with":[11],"objects,":[12],"is":[13],"crucial":[14],"for":[15,26,73,88,104,122],"embodied":[16],"intelligence,":[17],"they":[19],"provide":[20],"rich":[21],"and":[22,32,44,59,65,107,141,153,169,178,185,199],"diverse":[23,176],"visual":[24,197],"priors":[25],"robot":[27],"learning,":[28],"manipulation":[29,187],"policy":[30],"training,":[31],"affordance":[33],"reasoning.":[34],"However,":[35],"existing":[36,203],"methods":[37],"often":[38],"struggle":[39],"to":[40,132,146,202],"model":[41],"complex":[43],"dynamic":[45],"interactions.":[46],"While":[47],"recent":[48],"studies":[49],"show":[50],"that":[51,98,192],"masks":[52],"can":[53],"serve":[54],"effective":[56],"control":[57],"signals":[58],"enhance":[60],"generation":[61],"quality,":[62],"obtaining":[63],"dense":[64,123],"precise":[66],"mask":[67,124],"annotations":[68],"remains":[69],"a":[70,83,94,111],"major":[71],"challenge":[72],"real-world":[74],"use.":[75],"To":[76,165],"overcome":[77],"this":[78],"limitation,":[79],"we":[80,171],"introduce":[81],"Mask2IV,":[82],"novel":[84],"framework":[85],"specifically":[86],"designed":[87],"video":[90,112],"generation.":[91],"It":[92],"adopts":[93],"decoupled":[95],"two-stage":[96],"pipeline":[97],"first":[99],"predicts":[100],"plausible":[101],"motion":[102,156],"trajectories":[103],"both":[105,182],"actor":[106],"object,":[108],"then":[109],"generates":[110],"conditioned":[113],"on":[114],"these":[115],"trajectories.":[116],"This":[117],"design":[118],"eliminates":[119],"the":[120,130,134,148,155],"need":[121],"inputs":[125],"from":[126],"users":[127,145],"while":[128],"preserving":[129],"flexibility":[131],"manipulate":[133],"interaction":[135,152,184],"process.":[136],"Furthermore,":[137],"Mask2IV":[138],"supports":[139],"versatile":[140],"intuitive":[142],"control,":[143],"allowing":[144],"specify":[147],"target":[149],"object":[150,179],"of":[151],"guide":[154],"trajectory":[157],"through":[158],"action":[159,177],"descriptions":[160],"spatial":[162],"position":[163],"cues.":[164],"support":[166],"systematic":[167],"training":[168],"evaluation,":[170],"curate":[172],"two":[173],"benchmarks":[174],"covering":[175],"categories":[180],"across":[181],"human-object":[183],"robotic":[186],"scenarios.":[188],"Extensive":[189],"experiments":[190],"demonstrate":[191],"our":[193],"method":[194],"achieves":[195],"superior":[196],"realism":[198],"controllability":[200],"compared":[201],"baselines.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
