{"id":"W2025368022","doi":"10.1109/crv.2014.43","title":"Indoor Scene Recognition with a Visual Attention-Driven Spatial Pooling Strategy","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pooling; Pattern recognition (psychology); Mixture model; Computer vision; Histogram; Gaussian; Leverage (statistics); Scale-invariant feature transform; Discriminative model; Classifier (UML); Bag-of-words model in computer vision; Feature extraction; Image retrieval; Image (mathematics); Visual Word","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004083375,0.0009106077,0.001348715,0.00078015,0.000297846,0.0006506608,0.001541596,0.0005866787,0.002742511],"category_scores_gemma":[0.0006401074,0.0004013237,0.001240945,0.0008695692,0.0004516424,0.001202591,0.00128226,0.0005299733,0.000747479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005642922,"about_ca_system_score_gemma":0.000692128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005077683,"about_ca_topic_score_gemma":0.005954768,"domain_scores_codex":[0.9997346,0.00002846814,0.00001284521,0.00008976385,0.00006771783,0.0000665853],"domain_scores_gemma":[0.9998281,0.00002990005,0.00002245712,0.00004638374,0.0000492826,0.00002400548],"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":[0.0004062095,0.000236842,0.0005936374,0.0001792311,0.0002329011,0.0002735835,0.0001292444,0.14368,0.1535369,0.009416652,0.005966416,0.6853483],"study_design_scores_gemma":[0.00001489652,0.0001114132,0.0006844508,0.000005786219,0.0000534807,0.000117133,0.00001770237,0.9727693,0.0192173,0.005585627,0.001402353,0.0000204823],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02458634,0.0003133506,0.971622,0.0001084117,0.00004934526,0.00005383627,0.0001059358,0.001494577,0.001666214],"genre_scores_gemma":[0.6241618,0.0004036778,0.3682008,0.0003453751,0.0001440508,0.000122932,0.0006689645,0.0002264148,0.005726067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005077683,"threshold_uncertainty_score":0.01009625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01625364250267388,"score_gpt":0.2716648923135859,"score_spread":0.255411249810912,"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."}}