{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001390453,0.0009676269,0.0009949583,0.001086938,0.0004326721,0.0009168033,0.002480404,0.001418118,0.0016776],"category_scores_gemma":[0.003676578,0.000722133,0.000658127,0.0006098142,0.00122819,0.001390479,0.001481661,0.001079938,0.0007336392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007033653,"about_ca_system_score_gemma":0.0007646278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002550426,"about_ca_topic_score_gemma":0.005214139,"domain_scores_codex":[0.9992292,0.0001393777,0.00002313212,0.0003067515,0.0002054315,0.00009609087],"domain_scores_gemma":[0.9980245,0.0007121357,0.0002648134,0.0005334334,0.0003520588,0.0001131557],"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":[0.0004362933,0.0003389109,0.003277014,0.0002620115,0.000148294,0.0002918353,0.0004937515,0.3574154,0.0867481,0.009772041,0.006889798,0.5339265],"study_design_scores_gemma":[0.00001040939,0.00004431636,0.0005389393,0.000006402443,0.000008081206,0.00009154574,0.00001360461,0.9816108,0.01371346,0.003281371,0.0006731068,0.000007994252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03799953,0.0001766065,0.9576837,0.0001157797,0.00003847944,0.00007968178,0.00006179555,0.002379665,0.001464856],"genre_scores_gemma":[0.5019842,0.0001572264,0.4927736,0.0002278606,0.00009104984,0.0001132596,0.0003813244,0.0005027591,0.003768713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002550426,"threshold_uncertainty_score":0.007353544,"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."}}