{"id":"W3166240918","doi":"10.1145/3452009","title":"A Scale and Rotational Invariant Key-point Detector based on Sparse Coding","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Scale-invariant feature transform; Detector; Artificial intelligence; Computer vision; Scale invariance; Robustness (evolution); Pixel; Invariant (physics); Affine transformation; Coding (social sciences); Rotation (mathematics); Offset (computer science); Algorithm; Pattern recognition (psychology); Mathematics; Feature extraction; Geometry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008974727,0.0007102743,0.001502326,0.00163666,0.0003522958,0.000690844,0.0012965,0.001027342,0.001246049],"category_scores_gemma":[0.002573058,0.0004949588,0.000770277,0.001758221,0.000583796,0.001490276,0.001154648,0.001365316,0.001412757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005282543,"about_ca_system_score_gemma":0.001187041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001832108,"about_ca_topic_score_gemma":0.002290339,"domain_scores_codex":[0.9990337,0.0001204152,0.00004592791,0.0001874957,0.0005341165,0.00007826412],"domain_scores_gemma":[0.9988256,0.0002536463,0.0001060702,0.0001959699,0.0005494331,0.00006928261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002668697,0.0001580778,0.001297383,0.0002283763,0.00009794825,0.0001777135,0.00005848579,0.04321955,0.1333103,0.01296746,0.006425867,0.801792],"study_design_scores_gemma":[0.00003873719,0.0002234467,0.001040327,0.0000152441,0.00004394936,0.0006016415,0.00001952299,0.9419609,0.04675224,0.003380155,0.005864985,0.00005892166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003957815,0.0001630875,0.9949034,0.00006325027,0.00006493541,0.00005394492,0.00005679827,0.0003540547,0.0003827231],"genre_scores_gemma":[0.1263783,0.0004640399,0.8694922,0.0002103759,0.00009149206,0.0001711056,0.000610306,0.00007527404,0.002506834],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001832108,"threshold_uncertainty_score":0.004746318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02368916800040508,"score_gpt":0.2658368325175177,"score_spread":0.2421476645171126,"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."}}