{"id":"W1609886867","doi":"10.1007/11552499_47","title":"Semantic-Based Cross-Media Image Retrieval","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Image retrieval; Visual Word; Feature (linguistics); Annotation; Automatic image annotation; Artificial intelligence; Image (mathematics)","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001227562,0.0006407332,0.0005825758,0.0009534102,0.0003171984,0.001383199,0.004624566,0.0004876032,0.00008189786],"category_scores_gemma":[0.0002870045,0.0005845182,0.0002314217,0.001013173,0.001541206,0.00104463,0.000962598,0.00105697,0.0002207453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004377846,"about_ca_system_score_gemma":0.001175946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007311323,"about_ca_topic_score_gemma":0.000008648649,"domain_scores_codex":[0.9950539,0.0000403595,0.0007383226,0.00182636,0.001528634,0.0008124597],"domain_scores_gemma":[0.9960815,0.000583465,0.0004103787,0.002044046,0.0006297418,0.0002508209],"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":[0.00004077274,0.0001279671,0.00008537025,0.0001224311,0.00001563997,0.0002695771,0.0005227577,0.0008229078,0.008093879,0.02912254,0.00008746077,0.9606887],"study_design_scores_gemma":[0.0008059668,0.0003007535,0.001006664,0.0006421905,0.00001891982,0.0001088164,1.182703e-7,0.5557288,0.2874888,0.1398376,0.0119341,0.002127247],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003310766,0.0003526692,0.9924309,0.001607668,0.001140471,0.0003940959,0.00001130366,0.0006304788,0.003399304],"genre_scores_gemma":[0.04760146,0.00007448743,0.9472478,0.002613467,0.001042322,0.000007817529,0.00001643631,0.00006600138,0.001330173],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9585615,"threshold_uncertainty_score":0.9996606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174032661270686,"score_gpt":0.2724945060011456,"score_spread":0.2550912398740769,"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."}}