{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002165988,0.000112972,0.00009417864,0.0002005642,0.0001562193,0.0001001006,0.0002452957,0.00004181105,0.00004641536],"category_scores_gemma":[0.000006245093,0.00008846952,0.00004169762,0.001187062,0.00001444797,0.0005233168,0.00001814379,0.00005906536,0.001184581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004305017,"about_ca_system_score_gemma":0.00002280567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008685307,"about_ca_topic_score_gemma":0.0003891587,"domain_scores_codex":[0.9988063,0.00003359814,0.0001918572,0.0003970178,0.0003455738,0.0002256625],"domain_scores_gemma":[0.9994997,0.0000270292,0.00003579427,0.0002595318,0.00007242901,0.0001054965],"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":[0.00005581631,0.0001972763,0.001995377,0.00004554815,0.00004403674,0.000006186426,0.006281973,0.006270997,0.3160947,0.009959716,0.004922768,0.6541256],"study_design_scores_gemma":[0.001757006,0.0008234311,0.04630503,0.0000340653,0.00002260372,0.00003392767,0.001132883,0.5655103,0.3697531,0.001864298,0.01197616,0.0007872245],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04774023,0.000002401591,0.9459705,0.002041034,0.0001486723,0.0004659421,0.000001376648,0.0006760471,0.002953795],"genre_scores_gemma":[0.9735735,0.000006912979,0.02216516,0.0007393815,0.00003306273,0.0002632561,0.00001444414,0.00001230014,0.003191978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9258333,"threshold_uncertainty_score":0.9995931,"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."}}