{"id":"https://openalex.org/W4415708738","doi":"https://doi.org/10.1109/icme59968.2025.11209800","title":"Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution","display_name":"Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708738","doi":"https://doi.org/10.1109/icme59968.2025.11209800"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100383452","display_name":"Yiwen Wang","orcid":"https://orcid.org/0000-0002-7594-1396"},"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":"Yiwen Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037457833","display_name":"Xinning Chai","orcid":"https://orcid.org/0009-0007-7310-6796"},"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":"Xinning Chai","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004323368","display_name":"Yuhong Zhang","orcid":"https://orcid.org/0009-0000-8902-0013"},"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":"Yuhong Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071945287","display_name":"Zhengxue Cheng","orcid":"https://orcid.org/0000-0001-8258-6364"},"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":"Zhengxue Cheng","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013558185","display_name":"Jungong Zhao","orcid":"https://orcid.org/0000-0001-5823-2179"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhao","raw_affiliation_strings":["Tencent,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577089","display_name":"Rong Xie","orcid":"https://orcid.org/0000-0002-8261-5337"},"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":"Rong Xie","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"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":"Li Song","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9745000004768372,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9745000004768372,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.00839999970048666,"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":0.006399999838322401,"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/fidelity","display_name":"Fidelity","score":0.525600016117096},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4846000075340271},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.423799991607666},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.41130000352859497},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3553999960422516},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3521000146865845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5455999970436096},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2953823547","https://openalex.org/W2962785568","https://openalex.org/W3157035436","https://openalex.org/W3176148916","https://openalex.org/W3217246126","https://openalex.org/W4214745154","https://openalex.org/W4214768308","https://openalex.org/W4312933868","https://openalex.org/W4382462760","https://openalex.org/W4390874113","https://openalex.org/W4402698357","https://openalex.org/W4402702958","https://openalex.org/W4402727736","https://openalex.org/W4402754171","https://openalex.org/W4402961786","https://openalex.org/W4403947068","https://openalex.org/W4403947072","https://openalex.org/W4404769990"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,19,65,120],"video":[3,133],"super-resolution":[4,134],"(VSR)":[5],"models":[6],"have":[7],"demonstrated":[8],"impressive":[9],"results":[10],"enhancing":[12],"low-resolution":[13,31],"videos.":[14],"However,":[15],"due":[16],"to":[17,70],"limitations":[18],"adequately":[20],"controlling":[21],"the":[22,30,66],"generation":[23],"process,":[24],"achieving":[25],"high":[26],"fidelity":[27],"alignment":[28],"with":[29],"input":[32],"while":[33],"maintaining":[34],"temporal":[35,83,97],"consistency":[36],"across":[37],"frames":[38],"remains":[39],"a":[40,55,88],"significant":[41],"challenge.":[42],"In":[43],"this":[44],"work,":[45],"we":[46],"propose":[47],"Semantic":[48],"and":[49,62,79,82,95,125],"Temporal":[50],"Guided":[51],"Video":[52],"Super-Resolution":[53],"(SeTe-VSR),":[54],"novel":[56],"approach":[57,86],"that":[58,115],"incorporates":[59],"both":[60],"semantic":[61,77],"temporal-spatio":[63],"guidance":[64],"latent":[67],"diffusion":[68],"space":[69],"address":[71],"these":[72],"challenges.":[73],"By":[74],"incorporating":[75],"high-level":[76],"information":[78],"integrating":[80],"spatial":[81],"information,":[84],"our":[85],"achieves":[87],"seamless":[89],"balance":[90],"between":[91],"recovering":[92],"intricate":[93],"details":[94],"ensuring":[96],"coherence.":[98],"Our":[99],"method":[100],"not":[101],"only":[102],"preserves":[103],"high-reality":[104],"visual":[105],"content":[106],"but":[107],"also":[108],"significantly":[109],"enhances":[110],"fidelity.":[111],"Extensive":[112],"experiments":[113],"demonstrate":[114],"SeTe-VSR":[116],"outperforms":[117],"existing":[118],"methods":[119],"terms":[121],"of":[122],"detail":[123],"recovery":[124],"perceptual":[126],"quality,":[127],"highlighting":[128],"its":[129],"effectiveness":[130],"for":[131],"complex":[132],"tasks.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
