{"id":"W4413986970","doi":"10.14778/3748191.3748195","title":"Déjà Vu: Efficient Video-Language Query Engine with Learning-Based Inter-Frame Computation Reuse","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Reuse; Déjà vu; Frame (networking); Computation; Artificial intelligence; Natural language processing; Programming language; Computer network; Engineering; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004027556,0.0001977646,0.000206855,0.0002176064,0.0001882411,0.0001323648,0.001445167,0.00004959702,0.00000598591],"category_scores_gemma":[0.0003277276,0.0001392536,0.00008572943,0.0008291865,0.00008308865,0.0001031592,0.0006119481,0.0003679792,0.00001266525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001517321,"about_ca_system_score_gemma":0.00007515073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000276922,"about_ca_topic_score_gemma":0.000003227831,"domain_scores_codex":[0.9985976,0.0000252521,0.0003104807,0.0004346843,0.0003766759,0.00025531],"domain_scores_gemma":[0.9988494,0.0001511196,0.0003040296,0.0003889617,0.0002477748,0.00005871621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001299868,0.001060117,0.01998343,0.0005842034,0.000191637,0.000002187144,0.007576079,0.8319619,0.0627114,0.03501408,0.002186069,0.03859892],"study_design_scores_gemma":[0.0009735391,0.0001721658,0.009407695,0.0003575549,0.00003531475,0.000004584281,0.0001902761,0.9290221,0.05805768,0.000516449,0.001058237,0.0002044034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5481965,0.00007601039,0.4388958,0.009459417,0.0001647735,0.0008095074,0.00000187378,0.0003896156,0.002006523],"genre_scores_gemma":[0.9585493,0.000001424521,0.04070017,0.0003221346,0.00001975098,0.0001203078,0.000002190101,0.00001401959,0.0002707155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4103528,"threshold_uncertainty_score":0.5678598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003793105079189405,"score_gpt":0.2416539932310142,"score_spread":0.2378608881518248,"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."}}