{"id":"https://openalex.org/W7133351324","doi":"https://doi.org/10.1109/ijcb65343.2025.11410820","title":"Detecting Hyper-Realistic Videos Generated by Diffusion Models via Text-Guided Semantic Enhancement","display_name":"Detecting Hyper-Realistic Videos Generated by Diffusion Models via Text-Guided Semantic Enhancement","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133351324","doi":"https://doi.org/10.1109/ijcb65343.2025.11410820"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11410820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"},"type":"article","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/A5128004744","display_name":"Shum Hing Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shum Hing Ling","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029562156","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0000-0002-7453-5759"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ajay Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ajay Kumar","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65554734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.4032000005245209,"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":0.4032000005245209,"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/T11439","display_name":"Video Analysis and Summarization","score":0.10490000247955322,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06019999831914902,"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/generalization","display_name":"Generalization","score":0.7128000259399414},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6021999716758728},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5853000283241272},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5645999908447266},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5565000176429749},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3797999918460846},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173999786376953},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7128000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6854000091552734},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5853000283241272},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46070000529289246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11410820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W3034577585","https://openalex.org/W3094728142","https://openalex.org/W3196551054","https://openalex.org/W4214680478","https://openalex.org/W4224916469","https://openalex.org/W4313042219","https://openalex.org/W4313156423","https://openalex.org/W4383890556","https://openalex.org/W4385245566","https://openalex.org/W4386071464","https://openalex.org/W4386071953","https://openalex.org/W4390190266","https://openalex.org/W4390191016","https://openalex.org/W4390871895","https://openalex.org/W4390872344","https://openalex.org/W4390872570","https://openalex.org/W4390873235","https://openalex.org/W4392904043","https://openalex.org/W4393154086","https://openalex.org/W4399138486","https://openalex.org/W4402753859","https://openalex.org/W4402753903","https://openalex.org/W4402772264","https://openalex.org/W4402915976","https://openalex.org/W4404790764","https://openalex.org/W4406739280","https://openalex.org/W4409368310","https://openalex.org/W4413144718","https://openalex.org/W4415539346","https://openalex.org/W4417131101","https://openalex.org/W7133220737"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"two":[3,64],"key":[4],"challenges":[5],"in":[6],"detecting":[7,145],"diffusion-model":[8],"generated":[9],"videos:":[10],"generalization":[11,143],"to":[12,34],"unseen":[13,119],"but":[14,120],"sophisticated":[15],"video":[16,123],"synthesizers":[17],"and":[18,31,71,91,111,129,137],"threats":[19],"from":[20,118],"the":[21,25,28],"multimodal":[22,42],"manipulations":[23],"where":[24],"deepfakes":[26],"combine":[27],"text":[29,85],"prompts":[30,88],"visual":[32],"synthesis":[33],"create":[35],"realistic":[36],"forgeries.":[37],"We":[38],"propose":[39],"a":[40,46,73,79,92],"novel":[41],"framework":[43,58],"built":[44],"on":[45,105],"transformer-based":[47],"architecture,":[48],"which":[49,77,140],"was":[50],"originally":[51],"designed":[52],"for":[53,144],"image":[54],"forgery":[55],"detection.":[56],"Our":[57,131],"extends":[59],"this":[60],"architecture":[61],"by":[62],"integrating":[63],"complementary":[65],"components:":[66],"(i)":[67],"spatio-temporal":[68],"feature":[69],"extraction":[70],"(ii)":[72],"text-guided":[74],"enrichment":[75],"module":[76],"uses":[78],"frozen":[80],"Vision":[81],"Language":[82],"Models":[83],"(VLMs)":[84],"encoder":[86],"when":[87,99],"are":[89],"available":[90],"small":[93],"set":[94],"of":[95],"learnable":[96],"default":[97],"embeddings":[98],"no":[100],"prompt":[101],"is":[102],"provided.":[103],"Trained":[104],"our":[106],"self-curated":[107],"dataset":[108],"comprising":[109,125],"KlingAI":[110],"StableDiffusion":[112],"Samples,":[113],"we":[114],"present":[115],"cross-dataset":[116],"performance":[117],"hyper-realistic":[121,146],"fake":[122],"generators":[124],"Sora,":[126],"Luma,":[127],"Pika,":[128],"Runway.":[130],"model":[132],"can":[133],"achieve":[134],"high":[135],"accuracy":[136],"outperformance":[138],"results,":[139],"demonstrate":[141],"cross-model":[142],"AI-generated":[147],"videos.":[148]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-03-04T00:00:00"}