{"id":"https://openalex.org/W4407231232","doi":"https://doi.org/10.1109/iccv51701.2025.01052","title":"Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent","display_name":"Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407231232","doi":"https://doi.org/10.1109/iccv51701.2025.01052"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.03207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112471126","display_name":"Xinyao Liao","orcid":"https://orcid.org/0009-0008-4487-7505"},"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":"Xinyao Liao","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/A5022110331","display_name":"Xianfang Zeng","orcid":"https://orcid.org/0000-0003-1251-2129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianfang Zeng","raw_affiliation_strings":["StepFun"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456421","display_name":"Liao Wang","orcid":"https://orcid.org/0000-0002-7934-2956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao Wang","raw_affiliation_strings":["StepFun"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["StepFun"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029912845","display_name":"Guosheng Lin","orcid":"https://orcid.org/0000-0002-0329-7458"},"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":"Guosheng Lin","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/A5074359769","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0001-5427-2966"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11305","last_page":"11316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9904999732971191,"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/T12290","display_name":"Human Motion and Animation","score":0.9904999732971191,"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":0.9757999777793884,"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/T11448","display_name":"Face recognition and analysis","score":0.9638000130653381,"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/field","display_name":"Field (mathematics)","score":0.5118491053581238},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4972434341907501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49142658710479736},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3550497591495514},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2618243992328644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08029785752296448}],"concepts":[{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5118491053581238},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4972434341907501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49142658710479736},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3550497591495514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2618243992328644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08029785752296448},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.03207","pdf_url":"https://arxiv.org/pdf/2502.03207","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"},{"id":"doi:10.48550/arxiv.2502.03207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.03207","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.03207","pdf_url":"https://arxiv.org/pdf/2502.03207","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,121],"propose":[1],"MotionAgent,":[2],"enabling":[3],"fine-grained":[4,97],"motion":[5,16,21,28,34,45,68,132,146],"control":[6,89,117],"for":[7,95],"text-guided":[8],"image-to-video":[9,92],"generation.":[10],"The":[11,100],"key":[12],"technique":[13],"is":[14],"the":[15,37,40,48,86,90,104,129,135,138],"field":[17],"agent":[18,38],"that":[19,112],"converts":[20,51],"information":[22,133],"in":[23,47,70,103,134],"text":[24,49,136],"prompts":[25],"into":[26,53,76],"explicit":[27],"fields,":[29],"providing":[30],"flexible":[31],"and":[32,43,50,56,73,137],"precise":[33,116],"guidance.":[35],"Specifically,":[36],"extracts":[39],"object":[41,54],"movement":[42],"camera":[44,57,119],"described":[46],"them":[52,75],"trajectories":[55],"extrinsics,":[58],"respectively.":[59],"An":[60,81],"analytical":[61],"optical":[62,79,82],"flow":[63,83,87],"composition":[64],"module":[65],"integrates":[66],"these":[67],"representations":[69],"3D":[71],"space":[72],"projects":[74],"a":[77,123],"unified":[78],"flow.":[80],"adapter":[84],"takes":[85],"to":[88,127],"base":[91],"diffusion":[93],"model":[94],"generating":[96],"controlled":[98],"videos.":[99],"significant":[101],"improvement":[102],"Video-Text":[105],"Camera":[106],"Motion":[107],"metrics":[108],"on":[109,145],"VBench":[110,126],"indicates":[111],"our":[113],"method":[114],"achieves":[115],"over":[118],"motion.":[120],"construct":[122],"subset":[124],"of":[125,131],"evaluate":[128],"alignment":[130],"generated":[139],"video,":[140],"outperforming":[141],"other":[142],"advanced":[143],"models":[144],"generation":[147],"accuracy.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}