{"id":"W2821470430","doi":"10.1109/mdm.2018.00031","title":"A Semi-Supervised Approach for the Semantic Segmentation of Trajectories","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Trajectory; Minimum description length; Pattern recognition (psychology); Ground truth; Image segmentation; Set (abstract data type); Machine learning","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":[0.0002100635,0.00005219811,0.00006002565,0.00002937833,0.0000896199,0.00008524275,0.0005601819,0.00001104282,0.00001376953],"category_scores_gemma":[0.000009635713,0.00003127086,0.00003095244,0.0002012098,0.00005066032,0.0003864609,0.0001106199,0.00001481602,0.000004729682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004284875,"about_ca_system_score_gemma":0.000009025624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000260859,"about_ca_topic_score_gemma":0.0000049374,"domain_scores_codex":[0.9995172,0.00001148582,0.0001014958,0.0001460973,0.0001224086,0.0001012857],"domain_scores_gemma":[0.9995353,0.00005820452,0.0000334508,0.000307523,0.00005302935,0.00001255079],"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":[0.00003735265,0.0003543575,0.001389262,0.0003121788,0.0002771119,6.423689e-7,0.007764973,0.0001106586,0.007944228,0.4271681,0.04308875,0.5115525],"study_design_scores_gemma":[0.0003868995,0.0001266957,0.0007656159,0.000003717085,0.00001879705,6.358512e-7,0.0005578389,0.9800356,0.01502394,0.001096589,0.001896081,0.00008759743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001243761,0.00001866088,0.994625,0.0002711343,0.0001684397,0.0003064125,0.000003064136,0.0000487016,0.003314795],"genre_scores_gemma":[0.5120866,0.000008384935,0.4856036,0.0002487097,0.0001677083,0.00005701621,0.00001761083,0.000005179031,0.001805242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9799249,"threshold_uncertainty_score":0.1275189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02972571744245137,"score_gpt":0.2608870646256659,"score_spread":0.2311613471832145,"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."}}