{"id":"W2089298051","doi":"10.1006/jvci.2000.0465","title":"Video Segmentation in the Wavelet Compressed Domain","year":2001,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Wavelet; Computer science; Artificial intelligence; Wavelet transform; Computer vision; Search engine indexing; Data compression; Segmentation; Wavelet packet decomposition; Lifting scheme; Video compression picture types; Motion compensation; Pattern recognition (psychology); Video tracking; Video processing","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":[0.001372854,0.00007251631,0.0001433663,0.0002120138,0.0001425755,0.0003296767,0.000531194,0.00003047355,0.00001032429],"category_scores_gemma":[0.000115292,0.00005275895,0.00005735741,0.0005891145,0.00004711989,0.001481359,0.00008413521,0.0001666646,0.000002565251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000299539,"about_ca_system_score_gemma":0.00002365068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004646063,"about_ca_topic_score_gemma":0.00002601982,"domain_scores_codex":[0.9981592,0.0007954808,0.0005123391,0.0001038717,0.0003423986,0.00008671926],"domain_scores_gemma":[0.9986842,0.0002865914,0.00042117,0.000347063,0.0002277309,0.00003323572],"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":[0.0003668092,0.002284791,0.08521283,0.00006460462,0.0002331985,0.0001135074,0.0568837,0.001309494,0.1639957,0.04848263,0.008000323,0.6330525],"study_design_scores_gemma":[0.006916109,0.0008392704,0.4455428,0.0002365406,0.0001189589,0.00078816,0.02267055,0.4610997,0.008111489,0.0414952,0.01155399,0.0006272095],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2506594,0.0004178022,0.7403745,0.007093685,0.00004679642,0.0001538147,2.833502e-7,0.00001030123,0.001243397],"genre_scores_gemma":[0.9695283,0.001539931,0.02846132,0.0003945324,0.00003308159,0.000004844883,0.00001268154,0.000003635665,0.00002167851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7188689,"threshold_uncertainty_score":0.317908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02380629968287007,"score_gpt":0.3424204120009918,"score_spread":0.3186141123181217,"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."}}