{"id":"W4323322511","doi":"10.1016/j.cviu.2023.103664","title":"Weakly supervised multi-class semantic video segmentation for road scenes","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; National Research Foundation of Korea; Information Technology Research Centre; Ministry of Science, ICT and Future Planning","keywords":"Computer science; Segmentation; Artificial intelligence; Computer vision; Pixel; Feature (linguistics); Class (philosophy); Object (grammar); Key (lock); Computation; Pattern recognition (psychology); Image segmentation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009365728,0.000204596,0.000254776,0.0003097929,0.0004456484,0.0007214904,0.0003368586,0.00006478909,0.000003840794],"category_scores_gemma":[0.00004181293,0.0001826855,0.0001007252,0.000553544,0.00006230098,0.0008754139,0.0002687213,0.00009201712,0.00002610237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008146311,"about_ca_system_score_gemma":0.00002867203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007582657,"about_ca_topic_score_gemma":0.000006781189,"domain_scores_codex":[0.9983955,0.0001411913,0.0002851814,0.0005655278,0.0002266617,0.0003859143],"domain_scores_gemma":[0.9990217,0.0003849821,0.00008314892,0.0003204915,0.00007491612,0.0001147631],"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":[0.0000999181,0.0002116919,0.002343727,0.0006691142,0.0001538834,0.0001208183,0.005154992,0.0006288312,0.1097059,0.0274532,0.01363328,0.8398246],"study_design_scores_gemma":[0.001459462,0.0001721515,0.004706071,0.0001198054,0.000008314605,0.00001532246,0.0002564183,0.9857203,0.001875266,0.004999788,0.0003944406,0.0002726947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01381923,0.00007758468,0.9829777,0.001395126,0.0008641637,0.0003391378,0.00000379799,0.00046426,0.00005899221],"genre_scores_gemma":[0.5413908,0.000119602,0.4577389,0.0004503014,0.0001397561,0.00001640017,0.00002010443,0.00002575764,0.00009834961],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9850914,"threshold_uncertainty_score":0.7449698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0966125858195375,"score_gpt":0.351806053681381,"score_spread":0.2551934678618435,"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."}}