{"id":"W4402261906","doi":"10.1109/tip.2024.3451938","title":"Privacy-Preserving Autoencoder for Collaborative Object Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Face recognition and analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Alliance de recherche numérique du Canada","keywords":"Computer science; Artificial intelligence; Autoencoder; Bottleneck; Information bottleneck method; Computer vision; Codec; Information privacy; Decoding methods; Feature extraction; Object detection; Cloud computing; Artificial neural network; Machine learning; Data mining; Pattern recognition (psychology); Cluster analysis; Computer security; Embedded system","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002041303,0.0001586939,0.0001446478,0.000359988,0.0004947308,0.00107697,0.0003137615,0.00006327536,0.00004432935],"category_scores_gemma":[0.00001763708,0.0001485144,0.0001425421,0.001425734,0.00003726803,0.00168327,0.000003414051,0.0002008671,0.00006025555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009221889,"about_ca_system_score_gemma":0.0001922253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006329915,"about_ca_topic_score_gemma":0.00003215409,"domain_scores_codex":[0.9988289,0.00004535579,0.0002113267,0.0004646248,0.0002091652,0.0002405939],"domain_scores_gemma":[0.9992715,0.0001328168,0.00004513233,0.0002230143,0.0002568293,0.00007070621],"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":[0.00001521172,0.0000816311,1.79827e-7,0.0002942655,0.00007072653,0.000008060912,0.001658023,0.003624247,0.05167892,0.00003629479,0.0002050753,0.9423274],"study_design_scores_gemma":[0.0001472371,0.00004830124,0.000001438443,0.0001523724,0.00004152886,0.000009063052,0.0001578425,0.755207,0.2420957,0.0007952906,0.001189321,0.0001549342],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003403262,0.0002640318,0.9961861,0.001117645,0.0004506209,0.0002233977,0.00001600664,0.0006797075,0.0007221882],"genre_scores_gemma":[0.830074,0.00003125734,0.1683861,0.0001540477,0.00005823007,0.0001851608,0.000001484559,0.00002475112,0.001085005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9421724,"threshold_uncertainty_score":0.99996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02053213404869664,"score_gpt":0.2858990334323385,"score_spread":0.2653668993836418,"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."}}