{"id":"W2975627343","doi":"10.1109/mmsp.2019.8901826","title":"Semantic Segmentation in Compressed Videos","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Segmentation; Residual frame; Frame (networking); RGB color model; Image segmentation; Residual; Reference frame; Block-matching algorithm; Data compression; Motion compensation; Pattern recognition (psychology); Video tracking; Video processing; Algorithm","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":[0.00009092778,0.00005866634,0.00008370695,0.0000802128,0.00001244712,0.00004643253,0.0002904565,0.00002161422,0.00005398816],"category_scores_gemma":[0.000009019464,0.00005097658,0.00001870044,0.0002675806,0.000006919069,0.0007225507,0.00009525637,0.00005706666,0.0001848141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000224037,"about_ca_system_score_gemma":0.0000109892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002464802,"about_ca_topic_score_gemma":0.000004449111,"domain_scores_codex":[0.9994317,0.00002119582,0.000121724,0.0001869036,0.0001153067,0.0001232105],"domain_scores_gemma":[0.9996173,0.0000450735,0.00002917296,0.000264179,0.00002313312,0.00002111913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002788298,0.0002630171,0.07433137,0.0001174108,0.0000148298,0.00005286193,0.0009986985,0.0004217224,0.4314228,0.1215967,0.002020469,0.3687322],"study_design_scores_gemma":[0.0007286484,0.0001476774,0.01825376,0.00005055953,0.000001330189,0.000005387207,0.00004930916,0.08113647,0.8768356,0.01987452,0.002645865,0.0002708763],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02815848,0.00003302068,0.9647673,0.0001840859,0.00006626212,0.0002227134,1.294241e-7,0.0002191957,0.006348781],"genre_scores_gemma":[0.871806,0.00001629526,0.1268851,0.000458729,0.000006238578,0.000006698344,9.688077e-7,0.000003515032,0.0008164864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8436475,"threshold_uncertainty_score":0.2375473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00968904469861931,"score_gpt":0.2721372317792807,"score_spread":0.2624481870806614,"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."}}