{"id":"W3122240496","doi":"10.1109/iccv48922.2021.01003","title":"Self-Supervised Representation Learning from Flow Equivariance","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Representation (politics); Segmentation; Feature learning; Computer vision; Frame (networking); Object (grammar); Transformation (genetics); Transformation geometry; Pattern recognition (psychology)","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003123391,0.0003667382,0.0003568252,0.0002227313,0.0003215061,0.001151149,0.001822012,0.0001630641,0.001546688],"category_scores_gemma":[0.00014095,0.0003910657,0.0001965427,0.000615834,0.00003836422,0.0007859069,0.0007526921,0.0007740338,0.0014815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002151113,"about_ca_system_score_gemma":0.0002611759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002609678,"about_ca_topic_score_gemma":0.00002115304,"domain_scores_codex":[0.9959667,0.00048197,0.0006208299,0.001463379,0.001082266,0.0003849107],"domain_scores_gemma":[0.9968647,0.0005111247,0.0003001268,0.001123475,0.0009853501,0.0002151926],"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":[0.000101713,0.001282622,0.003414479,0.00003367701,0.0004415474,0.0004007863,0.002963508,0.1010386,0.03272901,0.1977051,0.007870507,0.6520185],"study_design_scores_gemma":[0.0008142681,0.0001224257,0.006255243,0.000132773,0.00001119434,0.00002332974,0.00003207623,0.9794156,0.002520355,0.004081417,0.006197445,0.0003938763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02463537,0.00003251941,0.9485203,0.01368455,0.002678174,0.000245216,0.0000203895,0.0004841571,0.009699302],"genre_scores_gemma":[0.6216665,0.00008454893,0.3751277,0.001051401,0.000809895,0.00005376399,0.0002741205,0.00002876214,0.0009032884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.878377,"threshold_uncertainty_score":0.9998857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.045308909399612,"score_gpt":0.3297275159253669,"score_spread":0.2844186065257549,"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."}}