{"id":"W2892523344","doi":"10.1109/tits.2018.2867183","title":"Deep Saliency With Channel-Wise Hierarchical Feature Responses for Traffic Sign Detection","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China; Shandong University","keywords":"Feature (linguistics); Computer science; Artificial intelligence; Feature extraction; Benchmark (surveying); Channel (broadcasting); Pattern recognition (psychology); Traffic sign; Convolution (computer science); Sign (mathematics); Traffic sign recognition; Fuse (electrical); Computer vision; Artificial neural network; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000346248,0.0007652256,0.0006190408,0.0008828583,0.0002027989,0.000401487,0.0007698598,0.0004462522,0.001613874],"category_scores_gemma":[0.001280197,0.0002110581,0.0004689667,0.0005240324,0.0002658924,0.0009412604,0.0007028847,0.0006586745,0.0004916157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004085067,"about_ca_system_score_gemma":0.0005955197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003791667,"about_ca_topic_score_gemma":0.00616746,"domain_scores_codex":[0.9998354,0.0000211967,0.000006350265,0.00003822333,0.00005063469,0.0000481691],"domain_scores_gemma":[0.9997261,0.00007551273,0.0000308465,0.0000364119,0.0001049499,0.00002605072],"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":[0.0005080599,0.0002599304,0.003567507,0.0001607256,0.0001047671,0.0002280105,0.0001274293,0.120438,0.107824,0.004829135,0.006790126,0.7551622],"study_design_scores_gemma":[0.0000118459,0.0000800132,0.001571891,0.000007055826,0.00002433421,0.00008367051,0.00001796035,0.974564,0.0199978,0.002524154,0.001104995,0.00001218856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07245796,0.0003043048,0.9224283,0.000127729,0.00006710404,0.00007842213,0.0002049547,0.002438989,0.001892288],"genre_scores_gemma":[0.8153548,0.0002092077,0.1804157,0.0001375661,0.00006603276,0.00005957383,0.0006989932,0.0001098069,0.002948286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003791667,"threshold_uncertainty_score":0.007539153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02609194596795961,"score_gpt":0.2769648431240884,"score_spread":0.2508728971561288,"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."}}