{"id":"https://openalex.org/W4413017530","doi":"https://doi.org/10.1109/access.2025.3595822","title":"Faster Image2Video Generation: A Closer Look at CLIP Image Embedding\u2019s Impact on Spatio-Temporal Cross-Attentions","display_name":"Faster Image2Video Generation: A Closer Look at CLIP Image Embedding\u2019s Impact on Spatio-Temporal Cross-Attentions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413017530","doi":"https://doi.org/10.1109/access.2025.3595822"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3595822","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595822","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3595822","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023139332","display_name":"Ashkan Taghipour","orcid":"https://orcid.org/0000-0002-1950-5143"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ashkan Taghipour","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1950-5143","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019512958","display_name":"Morteza Ghahremani","orcid":"https://orcid.org/0000-0001-6423-6475"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Morteza Ghahremani","raw_affiliation_strings":["Munich Center for Machine Learning (MCML), Technical University of Munich (TUM), Munich, Germany","Munich Center for Machine Learning (MCML), Technical University of Munich (TUM), Germany"],"raw_orcid":"https://orcid.org/0000-0001-6423-6475","affiliations":[{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Technical University of Munich (TUM), Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Technical University of Munich (TUM), Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079424927","display_name":"Aref Miri Rekavandi","orcid":"https://orcid.org/0000-0001-9542-759X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aref Miri Rekavandi","raw_affiliation_strings":["Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Australia","Faculty of Engineering and Information Technology, The University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Faculty of Engineering and Information Technology, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060586887","display_name":"Zinuo Li","orcid":"https://orcid.org/0000-0003-0945-6621"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zinuo Li","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0945-6621","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002077138","display_name":"Hamid Laga","orcid":"https://orcid.org/0000-0002-4758-7510"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hamid Laga","raw_affiliation_strings":["School of Information Technology, Murdoch University, Murdoch, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4758-7510","affiliations":[{"raw_affiliation_string":"School of Information Technology, Murdoch University, Murdoch, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014216530","display_name":"Farid Boussa\u00efd","orcid":"https://orcid.org/0000-0001-7250-7407"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farid Boussaid","raw_affiliation_strings":["Department of Electrical, Electronic, and Computer Engineering, The University of Western Australia, Perth, Australia","Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7250-7407","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic, and Computer Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5544,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66084814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"141313","last_page":"141327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9904999732971191,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9904999732971191,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.965499997138977,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9577999711036682,"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":0.7102598547935486},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5532841682434082},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4849148392677307},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47599923610687256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45012781023979187},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3489131033420563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102598547935486},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5532841682434082},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4849148392677307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47599923610687256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45012781023979187},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3489131033420563}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3595822","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595822","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/ec0db9c6-7782-45c4-963e-189eb83fc527","is_oa":true,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/ec0db9c6-7782-45c4-963e-189eb83fc527","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Taghipour, A, Ghahremani, M, Bennamoun, M, Miri Rekavandi, A, Li, Z, Laga, H & Boussaid, F 2025, 'Faster Image2Video Generation : A Closer Look at CLIP Image Embedding\u2019s Impact on Spatio-Temporal Cross-Attentions', IEEE Access, vol. 13, pp. 141313-141327. https://doi.org/10.1109/ACCESS.2025.3595822","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:989140c051a641648248a6ec36043d90","is_oa":true,"landing_page_url":"https://doaj.org/article/989140c051a641648248a6ec36043d90","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 141313-141327 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3595822","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3595822","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7481564637","display_name":"Shape4D: Modelling the Spatiotemporal Deformation Patterns in 3D Shapes.","funder_award_id":"DP220102197","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G8657801208","display_name":"Intelligent Virtual Human Companions","funder_award_id":"DP210101682","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2971871555","https://openalex.org/W3035595647","https://openalex.org/W3096719817","https://openalex.org/W3109908659","https://openalex.org/W4214745154","https://openalex.org/W4225433975","https://openalex.org/W4312973876","https://openalex.org/W4360993849","https://openalex.org/W4381327795","https://openalex.org/W4385270985","https://openalex.org/W4386071957","https://openalex.org/W4386075779","https://openalex.org/W4386076424","https://openalex.org/W4386736435","https://openalex.org/W4390872414","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4394711270","https://openalex.org/W4399453834","https://openalex.org/W4402660110","https://openalex.org/W4402753903","https://openalex.org/W4402754023","https://openalex.org/W4402961675","https://openalex.org/W4404965423","https://openalex.org/W4404965692","https://openalex.org/W4407574876","https://openalex.org/W4413145916","https://openalex.org/W4413222003","https://openalex.org/W6748197083","https://openalex.org/W6756789066","https://openalex.org/W6791353385","https://openalex.org/W6840815571","https://openalex.org/W6843218176","https://openalex.org/W6846959760","https://openalex.org/W6847076894","https://openalex.org/W6851800889","https://openalex.org/W6852838584","https://openalex.org/W6853269751","https://openalex.org/W6854463369","https://openalex.org/W6855459923","https://openalex.org/W6857114289","https://openalex.org/W6857542131","https://openalex.org/W6857963408","https://openalex.org/W6858062379","https://openalex.org/W6858529799","https://openalex.org/W6858865347","https://openalex.org/W6859163441","https://openalex.org/W6860986541","https://openalex.org/W6861379416","https://openalex.org/W6861484782","https://openalex.org/W6862589453","https://openalex.org/W6862744404","https://openalex.org/W6863162126","https://openalex.org/W6866287167","https://openalex.org/W6868612551","https://openalex.org/W6868717842","https://openalex.org/W6869652458","https://openalex.org/W6870070775","https://openalex.org/W6871069014","https://openalex.org/W6873187413","https://openalex.org/W6873980008","https://openalex.org/W6874496036","https://openalex.org/W6875960949","https://openalex.org/W6876194322","https://openalex.org/W6877648623","https://openalex.org/W6929424553","https://openalex.org/W6948069902","https://openalex.org/W6966993273","https://openalex.org/W6967232889"],"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":{"This":[0,136],"paper":[1],"explores":[2],"the":[3,9,26,64,90,119,162,177],"effectiveness\u2014specifically":[4],"in":[5,18,45,63,182],"improving":[6],"video":[7,19,91,169],"consistency\u2014and":[8],"computational":[10,87,111],"burden":[11,88],"of":[12,70],"Contrastive":[13],"Language-Image":[14],"Pre-Training":[15],"(CLIP)":[16],"embeddings":[17],"generation.":[20],"The":[21,42],"investigation":[22],"is":[23],"conducted":[24],"using":[25],"Stable":[27],"Video":[28,99],"Diffusion":[29],"(SVD)":[30],"framework,":[31],"a":[32,85,103,125],"state-of-the-art":[33],"method":[34,107],"for":[35,179],"generating":[36],"high-quality":[37,168],"videos":[38,48],"from":[39],"image":[40],"inputs.":[41],"diffusion":[43],"process":[44,73],"SVD":[46,163],"generates":[47],"by":[49,149,154],"iteratively":[50],"denoising":[51,72],"noisy":[52],"inputs":[53],"over":[54],"multiple":[55],"steps.":[56,135],"Our":[57],"analysis":[58],"reveals":[59],"that":[60,108],"employing":[61],"CLIP":[62],"cross-attention":[65,123],"mechanism":[66],"at":[67],"every":[68],"step":[69],"this":[71],"has":[74],"limited":[75],"impact":[76],"on":[77,89],"maintaining":[78],"subject":[79],"and":[80,131,151,174,186],"background":[81],"consistency":[82],"while":[83],"imposing":[84],"significant":[86],"generation":[92,170],"network.":[93],"To":[94],"address":[95],"this,":[96],"we":[97],"propose":[98],"Computation":[100],"Cut":[101],"(VCUT),":[102],"novel,":[104],"training-free":[105],"optimization":[106],"significantly":[109],"reduces":[110,138],"demands":[112],"without":[113],"compromising":[114],"output":[115],"quality.":[116],"VCUT":[117],"replaces":[118],"computationally":[120],"intensive":[121],"temporal":[122],"with":[124],"one-time":[126],"computed":[127],"linear":[128],"layer,":[129],"cached":[130],"reused":[132],"across":[133],"inference":[134],"innovation":[137],"up":[139],"to":[140,157],"322T":[141],"MACs":[142],"per":[143],"25-frame":[144],"video,":[145],"decreases":[146],"model":[147],"parameters":[148],"50M,":[150],"cuts":[152],"latency":[153],"20%":[155],"compared":[156],"baseline":[158],"methods.":[159],"By":[160],"streamlining":[161],"architecture,":[164],"our":[165],"approach":[166],"makes":[167],"more":[171],"accessible,":[172],"cost-effective,":[173],"eco-friendly,":[175],"paving":[176],"way":[178],"real-time":[180],"applications":[181],"telemedicine,":[183],"remote":[184],"learning,":[185],"automated":[187],"content":[188],"creation.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-08-07T00:00:00"}