{"id":"W3155731499","doi":"10.48550/arxiv.2104.09752","title":"Flow-based Video Segmentation for Human Head and Shoulders","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Computer vision; Optical flow; Background subtraction; Videoconferencing; Convolutional neural network; Encoder; Process (computing); Computer graphics (images); Image (mathematics); Multimedia; Pixel","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001612208,0.0002466681,0.0002453719,0.0001962998,0.0002400488,0.0002630761,0.0007718839,0.000176643,0.000004958642],"category_scores_gemma":[0.00003723079,0.0003154032,0.000110577,0.0002803979,0.0001081232,0.0006074045,0.0008355256,0.0002725954,0.000001022816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001774526,"about_ca_system_score_gemma":0.0001789791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003790565,"about_ca_topic_score_gemma":0.00004760694,"domain_scores_codex":[0.9984335,0.00006260795,0.0001548008,0.001035938,0.00006989921,0.0002432862],"domain_scores_gemma":[0.9987077,0.00008565492,0.0001872739,0.0007051746,0.0002196329,0.00009453298],"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":[0.000311162,0.001232399,0.008925299,0.005399021,0.0005985999,0.001291627,0.00384483,0.6269916,0.06629659,0.1814282,0.002518078,0.1011626],"study_design_scores_gemma":[0.0005876074,0.00006832389,0.000134593,0.0001940459,0.00004497465,0.000001888072,0.0000630248,0.9205852,0.008560598,0.06926052,0.0001018378,0.0003974116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03564202,0.00009517829,0.962952,0.0001526147,0.000132819,0.0003952473,0.000008314364,0.0004979406,0.000123835],"genre_scores_gemma":[0.5871692,0.0000216131,0.4124272,0.0001748395,0.00001895687,0.00000516594,0.00003762137,0.00001490101,0.0001305878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5515271,"threshold_uncertainty_score":0.9999298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09743156365197027,"score_gpt":0.2564366743295602,"score_spread":0.1590051106775899,"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."}}