{"id":"W4414521063","doi":"10.1016/j.eswa.2025.129649","title":"GE-adapter: A general and efficient adapter for enhanced video editing with pretrained text-to-image diffusion models","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs","funders":"Hunan Provincial Key Laboratory of Materials Protection for Electric Power and Transportation, Changsha University of Science and Technology; Shenzhen Fundamental Research Program; Science, Technology and Innovation Commission of Shenzhen Municipality; Hunan Provincial Science and Technology Department","keywords":"Adapter (computing); Consistency (knowledge bases); Fidelity; Key (lock); Coherence (philosophical gambling strategy); Consistency model; Temporal database; Flexibility (engineering)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008285934,0.002527975,0.000991862,0.001283008,0.0003236172,0.001411302,0.003156589,0.001779512,0.04178927],"category_scores_gemma":[0.005713909,0.0008735837,0.001276751,0.000841444,0.0002303797,0.001952331,0.001972076,0.00150281,0.0193691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004267429,"about_ca_system_score_gemma":0.0005573483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003273556,"about_ca_topic_score_gemma":0.004900843,"domain_scores_codex":[0.9996412,0.00005131641,0.00004301256,0.0001092489,0.000107735,0.00004747717],"domain_scores_gemma":[0.9989156,0.0004445201,0.00006058317,0.0002855748,0.0002200094,0.00007372124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001503107,0.000266981,0.0009635087,0.0009721437,0.0003423012,0.0007847723,0.0002838282,0.02152894,0.07130278,0.007411103,0.1314946,0.763146],"study_design_scores_gemma":[0.0002541675,0.0001904562,0.001161887,0.0001123032,0.0001089286,0.000876223,0.0001065902,0.7219271,0.1589117,0.01169929,0.1044831,0.0001681456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002991743,0.0002077524,0.7607003,0.00007388402,0.0001409022,0.0001567712,0.002767724,0.2312829,0.001677929],"genre_scores_gemma":[0.07011779,0.0005788644,0.8640617,0.0003136398,0.0001278022,0.0007061343,0.01270578,0.03531562,0.01607271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04178927,"threshold_uncertainty_score":0.139799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008610764350851122,"score_gpt":0.2389338463560828,"score_spread":0.2303230820052317,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}