{"id":"W2124333148","doi":"10.1109/6046.845016","title":"Automatic key video object plane selection using the shape information in the MPEG-4 compressed domain","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Video tracking; Computer vision; Multiview Video Coding; Artificial intelligence; Video compression picture types; Hausdorff distance; MPEG-4; Block-matching algorithm; Decoding methods; Motion compensation; Object (grammar); Video processing; Coding (social sciences); Data compression; Algorithm; Mathematics","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":[0.000562759,0.0001577617,0.0001578354,0.0002341936,0.0004459603,0.0003011643,0.0005423813,0.0000847816,0.0003063846],"category_scores_gemma":[0.000008727641,0.0001014127,0.00009763861,0.001101903,0.00004489087,0.001087693,0.000001481588,0.000301304,0.0001201832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000817449,"about_ca_system_score_gemma":0.00006031185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003447328,"about_ca_topic_score_gemma":0.0003239317,"domain_scores_codex":[0.9983867,0.0003293435,0.0004083739,0.0001921238,0.0004517314,0.0002317392],"domain_scores_gemma":[0.9991139,0.0003173994,0.0000965113,0.000379889,0.0000522129,0.00004012821],"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":[0.00002997503,0.0002066254,0.0000741931,0.00001643706,0.00005465756,0.00000300159,0.01533415,0.5060198,0.001264285,0.00007514562,0.0002175867,0.4767041],"study_design_scores_gemma":[0.0004575032,0.00004033423,0.001494703,0.00002310718,0.00002583879,0.00001591658,0.000189957,0.9959489,0.0009089438,0.0001013224,0.0006698521,0.0001236306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1701503,0.00001017179,0.8283057,0.0006389614,0.0001971454,0.0003498788,0.000006286833,0.0001125411,0.0002290036],"genre_scores_gemma":[0.9878566,0.00002194034,0.01134866,0.0006441515,0.00003615887,0.00004649627,0.00001049054,0.000006629735,0.00002891645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8177062,"threshold_uncertainty_score":0.413549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01288374106735909,"score_gpt":0.2349184134883682,"score_spread":0.2220346724210091,"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."}}