{"id":"W3005651405","doi":"10.1109/crv50864.2020.00038","title":"SpotNet: Self-Attention Multi-Task Network for Object Detection","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genetec (Canada); Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Computer science; Bounding overwatch; Artificial intelligence; Background subtraction; Task (project management); Object detection; Feature (linguistics); Object (grammar); Computer vision; Pattern recognition (psychology); Machine learning; Pixel","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":[0.001097567,0.002272671,0.0009866975,0.001178728,0.0005497783,0.0009163333,0.003146839,0.002107191,0.004738174],"category_scores_gemma":[0.002782393,0.0008000463,0.0008069463,0.001104255,0.0006224399,0.002671313,0.001505937,0.001863204,0.002307563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001330211,"about_ca_system_score_gemma":0.0009801708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01149258,"about_ca_topic_score_gemma":0.01804431,"domain_scores_codex":[0.9994746,0.0001069798,0.00001886496,0.0002168425,0.00009963375,0.00008316563],"domain_scores_gemma":[0.9991053,0.0003023133,0.00008239596,0.0002328194,0.0002104962,0.00006668613],"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":[0.001163953,0.0008019625,0.002725951,0.0004533935,0.0004327999,0.0003484336,0.0001552921,0.3856935,0.0180443,0.007041099,0.08754239,0.495597],"study_design_scores_gemma":[0.00002807366,0.00005313705,0.0003460105,0.000007353427,0.0000125365,0.00003120339,0.000009358927,0.9903811,0.002964964,0.004378175,0.001778924,0.000009209341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05995756,0.001836537,0.8857884,0.0009532289,0.0004222133,0.0002994129,0.003629178,0.04087754,0.006235967],"genre_scores_gemma":[0.5388138,0.0006868528,0.4219507,0.001218713,0.0003817376,0.0008070925,0.01686355,0.00157299,0.01770468],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01149258,"threshold_uncertainty_score":0.02285135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04839782180162159,"score_gpt":0.3142284967736901,"score_spread":0.2658306749720685,"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."}}