{"id":"W1970842225","doi":"10.1007/s10994-013-5336-9","title":"Learning semantic representations of objects and their parts","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agence Nationale de la Recherche; Compute Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; WordNet; Object (grammar); Embedding; Artificial intelligence; Image retrieval; Annotation; Set (abstract data type); Image (mathematics); Information retrieval; Automatic image annotation; Learning object; Cognitive neuroscience of visual object recognition; Machine learning; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0001849084,0.0001048404,0.0001559784,0.00009451788,0.0001667331,0.00008761133,0.0002048658,0.00003044598,0.00002727125],"category_scores_gemma":[0.0002588005,0.0000846462,0.00003696787,0.0002606444,0.00004523687,0.0005619738,0.0002457395,0.0002624753,0.00001183573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006741988,"about_ca_system_score_gemma":0.00001036412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001664888,"about_ca_topic_score_gemma":0.000003968249,"domain_scores_codex":[0.9991919,0.0001203846,0.0001743383,0.000238919,0.0001011092,0.0001733476],"domain_scores_gemma":[0.9993412,0.0002026036,0.0001232898,0.0002079424,0.0000728877,0.00005204908],"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":[0.000006396354,0.00006511856,0.1615254,0.0001117739,0.00004661701,0.00001396557,0.01014374,0.003172213,0.05572446,0.005644753,0.0001959181,0.7633496],"study_design_scores_gemma":[0.0007475115,0.0009300808,0.06300277,0.0002143673,0.00001659501,0.0001063951,0.001279079,0.669373,0.2321862,0.0223574,0.009065222,0.0007213471],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1085294,0.0005910223,0.886584,0.0003614336,0.00003349761,0.0001789759,2.493892e-7,0.0003737063,0.003347698],"genre_scores_gemma":[0.9822151,0.0001116314,0.01681304,0.00005588475,0.0000174252,0.00001182402,0.000002466007,0.000009948215,0.0007626495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8736857,"threshold_uncertainty_score":0.3451772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01081827026464842,"score_gpt":0.2673789469826173,"score_spread":0.2565606767179689,"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."}}