{"id":"W2273269588","doi":"10.1016/j.sigpro.2016.01.016","title":"Rotation invariant HOG for object localization in web images","year":2016,"lang":"en","type":"article","venue":"Signal Processing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Artificial intelligence; Invariant (physics); Histogram; Computer vision; Robustness (evolution); Histogram of oriented gradients; Rotation (mathematics); Computer science; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Mathematics; Feature extraction; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002965039,0.00009017282,0.00009962499,0.0001261626,0.00009083348,0.0001183889,0.0002353621,0.000041805,0.000004183457],"category_scores_gemma":[0.0001181,0.00006407108,0.00002464989,0.0003723877,0.00003048531,0.001695662,0.00004987976,0.00004133517,0.000004167076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005771521,"about_ca_system_score_gemma":0.0001226748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000249298,"about_ca_topic_score_gemma":0.000003354077,"domain_scores_codex":[0.9991841,0.00003011698,0.0001927487,0.0002660473,0.0001359241,0.0001910069],"domain_scores_gemma":[0.9995286,0.00009410003,0.00009750707,0.0001088921,0.0001408252,0.00003001399],"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":[0.00001843874,0.000021284,0.0002537054,0.00004639269,0.000001274307,0.000004091702,0.0001553958,0.00004032994,0.1129062,0.001507674,0.0001673276,0.8848779],"study_design_scores_gemma":[0.0007939867,0.0001740674,0.0002400696,0.0005104165,0.000004075179,0.000007404818,0.00003064124,0.1357927,0.7684325,0.09210257,0.001629794,0.0002817478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003446385,0.0002365921,0.9982628,0.0004406278,0.00002072933,0.0002280589,0.000001766922,0.0001860187,0.0002787613],"genre_scores_gemma":[0.8969045,0.0000248627,0.1026849,0.0002176403,0.00004595732,0.00004247604,0.00000157338,0.00000969006,0.00006839452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8965599,"threshold_uncertainty_score":0.2612743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878560405998516,"score_gpt":0.2912272856869152,"score_spread":0.2724416816269301,"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."}}