{"id":"W2892270085","doi":"10.1016/j.neucom.2018.08.039","title":"Deep saliency detection via channel-wise hierarchical feature responses","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Softmax function; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Feature extraction; Benchmark (surveying); Channel (broadcasting); Feature learning; Deep learning; Cross entropy; Entropy (arrow of time)","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":[0.0003023081,0.0005060541,0.0004662755,0.0005381503,0.0001933289,0.0005055571,0.0005690383,0.0004683477,0.002200469],"category_scores_gemma":[0.001443959,0.0001888488,0.0003456703,0.0004842117,0.0002333046,0.000798623,0.000746237,0.0006313746,0.0004301317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003762437,"about_ca_system_score_gemma":0.0005052378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002843125,"about_ca_topic_score_gemma":0.004892469,"domain_scores_codex":[0.9998349,0.0000286914,0.000004936574,0.00004512117,0.00003807647,0.00004838446],"domain_scores_gemma":[0.9996634,0.0001394988,0.00003335022,0.00003455106,0.00009092173,0.00003828709],"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":[0.0006511753,0.0002666143,0.00279149,0.000171268,0.0001283435,0.0001386649,0.0001305238,0.0789344,0.2348,0.0164919,0.009998932,0.6554967],"study_design_scores_gemma":[0.00001150812,0.00008138028,0.002949008,0.000008030612,0.00002103845,0.00004809956,0.00001682522,0.9618928,0.02345064,0.01044284,0.001063088,0.00001471263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09078541,0.0004286148,0.9040725,0.0002922715,0.00009681472,0.00003940934,0.0002595518,0.001155435,0.002870059],"genre_scores_gemma":[0.8914312,0.0002184049,0.1043662,0.0001393302,0.00009657842,0.00003477241,0.0003119663,0.0000848999,0.003316561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002843125,"threshold_uncertainty_score":0.007361233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01617082142043701,"score_gpt":0.274293262200596,"score_spread":0.258122440780159,"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."}}