{"id":"W4312545381","doi":"10.1109/cvpr52688.2022.00312","title":"Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University; Vector Institute","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Interpolation (computer graphics); Consistency (knowledge bases); Constraint (computer-aided design); Computer vision; Scale (ratio); Shadow (psychology); Generalization; Pixel; Pattern recognition (psychology); Image (mathematics); Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001221409,0.0003718116,0.0004472808,0.0004619968,0.0007887181,0.0005167943,0.0005109917,0.0001096691,0.0007409012],"category_scores_gemma":[0.00002525023,0.0003836749,0.0001583347,0.000508967,0.00007129676,0.0006988232,0.0003297488,0.0006455978,0.00009823842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008069492,"about_ca_system_score_gemma":0.000088444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001274458,"about_ca_topic_score_gemma":0.0001909973,"domain_scores_codex":[0.996317,0.0009948974,0.000632855,0.000995373,0.0006452133,0.0004146267],"domain_scores_gemma":[0.9984009,0.0003264946,0.0003720967,0.0004921123,0.0002191635,0.0001892485],"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":[0.00006524533,0.0001139233,0.001445959,0.0000271405,0.00002872757,0.00003780317,0.001556028,0.00004614043,0.001136561,0.0001365834,0.000334453,0.9950714],"study_design_scores_gemma":[0.00187313,0.002405629,0.01347549,0.0002242144,0.00002555228,0.0003567737,0.0002856589,0.9615908,0.001340849,0.01454645,0.002874277,0.001001194],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1257852,0.00003291064,0.8691393,0.0009242541,0.00273095,0.0003619162,0.0000411386,0.0003063828,0.0006779574],"genre_scores_gemma":[0.9852942,0.000035667,0.01155703,0.002513383,0.0002554745,0.0001044459,0.0001584332,0.00002814537,0.00005328415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9940702,"threshold_uncertainty_score":0.9998615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07243037119685516,"score_gpt":0.2973142349716297,"score_spread":0.2248838637747745,"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."}}