{"id":"W4387698524","doi":"10.1145/3628432","title":"Sparsity-guided Discriminative Feature Encoding for Robust Keypoint Detection","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Discriminative model; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Neural coding; Regularization (linguistics); Feature learning; Encoding (memory); Coding (social sciences); Constraint (computer-aided design); Representation (politics); Machine learning; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003829213,0.0002055832,0.0002014014,0.0003502942,0.001789297,0.0001552016,0.001550057,0.0001052307,0.000001493464],"category_scores_gemma":[0.0001096468,0.0002122695,0.0001135202,0.001278703,0.0001713083,0.0003664866,0.0001903826,0.0003833382,0.0000232603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007770285,"about_ca_system_score_gemma":0.00003613879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001894656,"about_ca_topic_score_gemma":0.00002168883,"domain_scores_codex":[0.9986686,0.00008502787,0.0002963813,0.0004933589,0.0001563798,0.0003002633],"domain_scores_gemma":[0.9957547,0.001620954,0.0001487033,0.002118139,0.0002415893,0.0001158795],"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":[0.000004646602,0.0001396178,0.00001299768,0.00002502638,0.00003048616,2.953185e-7,0.0007960123,0.0007759599,0.003394528,0.003436231,0.0001826495,0.9912016],"study_design_scores_gemma":[0.000748479,0.0001823443,0.0009052639,0.0000993511,0.00006874454,0.00002366008,0.000590034,0.9107704,0.03165473,0.01614049,0.03825801,0.0005585265],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002133746,0.0001089479,0.9922462,0.004790884,0.0000746181,0.001155561,0.00003725349,0.001129594,0.0002435629],"genre_scores_gemma":[0.3509853,0.0007942846,0.6471284,0.0001424644,0.00004776044,0.0006582303,0.00004972898,0.00002163236,0.0001722316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.990643,"threshold_uncertainty_score":0.9995102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07712045144821042,"score_gpt":0.345314355031146,"score_spread":0.2681939035829356,"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."}}