{"id":"W3211033922","doi":"10.1109/tpami.2021.3123902","title":"Self-Supervised Human Detection and Segmentation via Background Inpainting","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Artificial intelligence; Segmentation; Computer science; Object detection; Computer vision; Image segmentation; Inpainting; Segmentation-based object categorization; Pattern recognition (psychology); Exploit; Scale-space segmentation; Supervised learning; Object (grammar); ENCODE; Image (mathematics); Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002589256,0.0001812693,0.0002141433,0.0003927046,0.0004876495,0.0002845573,0.0001341051,0.00006731617,0.00009326782],"category_scores_gemma":[0.000002157817,0.0001796008,0.0001544524,0.001142839,0.00003291113,0.0004094272,0.000007915417,0.000206477,0.00001443413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000448656,"about_ca_system_score_gemma":0.00001016478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004060884,"about_ca_topic_score_gemma":0.002003344,"domain_scores_codex":[0.9985002,0.0001658224,0.0003534414,0.0005578027,0.0002416119,0.0001811789],"domain_scores_gemma":[0.999352,0.00005593919,0.00009276794,0.0002819867,0.0001101672,0.0001071905],"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":[0.00000355669,0.0001704282,0.0005274507,0.00003300412,0.0002920704,0.000008452912,0.000524304,0.0009618345,0.03392349,0.00005959696,3.570064e-7,0.9634954],"study_design_scores_gemma":[0.0001480238,0.0001360542,0.002430384,0.00001191003,0.0002774127,0.00004157471,0.0002217306,0.5621364,0.4341067,0.0002366592,0.00002164879,0.000231498],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1011666,0.00005221723,0.898185,0.0001336667,0.000191828,0.00008580594,0.000003251469,0.0001332557,0.00004837032],"genre_scores_gemma":[0.9960281,0.0001771824,0.003367132,0.0002814403,0.00002038226,0.00001792883,0.000004663911,0.000008885184,0.00009433808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9632639,"threshold_uncertainty_score":0.7323908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02516518285223742,"score_gpt":0.2905083761976039,"score_spread":0.2653431933453665,"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."}}