{"id":"W4386065828","doi":"10.1109/cvpr52729.2023.00612","title":"MED-VT: Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Encoder; Artificial intelligence; Segmentation; Decoding methods; Computer vision; Transformer; Image segmentation; Optical flow; Pattern recognition (psychology); Algorithm; Voltage; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007921544,0.001017389,0.0005913224,0.000901664,0.0002746989,0.0009066046,0.001338314,0.0009539275,0.004232666],"category_scores_gemma":[0.003216266,0.0003624914,0.0004899069,0.0006460595,0.0005219357,0.001277617,0.001436453,0.001056348,0.001107506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00070005,"about_ca_system_score_gemma":0.000948987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004719093,"about_ca_topic_score_gemma":0.00735244,"domain_scores_codex":[0.9996516,0.00006196148,0.00001856233,0.0001040577,0.0001241609,0.00003967626],"domain_scores_gemma":[0.9995435,0.0001698695,0.00003592311,0.00009683195,0.00009878869,0.0000550858],"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":[0.0006067774,0.0002471589,0.001291054,0.0002039944,0.0001023339,0.0003425165,0.000142019,0.1474994,0.07995796,0.02012412,0.01497635,0.7345062],"study_design_scores_gemma":[0.00002681559,0.0001007645,0.0001737898,0.000008893069,0.00001206005,0.0001472767,0.00001697099,0.9674742,0.02293442,0.006453466,0.002638597,0.00001273687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01563618,0.0003755477,0.9715163,0.0001886398,0.000110851,0.0001384978,0.0003771977,0.00949321,0.002163563],"genre_scores_gemma":[0.3450588,0.00033157,0.6476495,0.0003202801,0.00009550885,0.0001249785,0.0013668,0.0009069087,0.004145594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004719093,"threshold_uncertainty_score":0.01415968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01363357354793676,"score_gpt":0.2875084556489704,"score_spread":0.2738748821010336,"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."}}