{"id":"W1578197944","doi":"10.1007/11744023_27","title":"Learning and Incorporating Top-Down Cues in Image Segmentation","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Conditional random field; Segmentation; Image segmentation; Classifier (UML); Pattern recognition (psychology); Image (mathematics); Object (grammar); Segmentation-based object categorization; Modular design; Exploit; Computer vision; Scale-space segmentation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007292852,0.0003728659,0.000379983,0.0007803625,0.0001925977,0.0005497529,0.0009248946,0.0001865896,0.000003858238],"category_scores_gemma":[0.0001142251,0.0003597854,0.00004823689,0.0006045683,0.0004531879,0.00137755,0.0009285487,0.0008221763,0.000005252966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000227206,"about_ca_system_score_gemma":0.0001579825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004990142,"about_ca_topic_score_gemma":0.0000563074,"domain_scores_codex":[0.9974393,0.00004240869,0.0004754387,0.001101363,0.0005277941,0.0004136862],"domain_scores_gemma":[0.998766,0.0002999584,0.0003074107,0.0004143274,0.0001390645,0.00007326213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000299635,0.00001189477,0.001099503,0.0000344787,0.000001719665,0.0001034953,0.0003526782,0.00234497,0.002518756,0.00226346,0.000008227118,0.9912578],"study_design_scores_gemma":[0.000582611,0.000590005,0.0009930155,0.001076861,0.000007488066,0.0001177023,0.000001701263,0.4383957,0.06877055,0.487133,0.0008926407,0.001438738],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004013912,0.0004657843,0.9955311,0.0001956509,0.0001973775,0.0003132658,0.000001104829,0.0002085156,0.002685782],"genre_scores_gemma":[0.09430722,0.0001075467,0.9047968,0.0003189257,0.0001623002,0.00000869719,0.000006678712,0.00002477485,0.000267103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9898191,"threshold_uncertainty_score":0.9998854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01012384088604272,"score_gpt":0.2721488084768841,"score_spread":0.2620249675908414,"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."}}