{"id":"W3162696321","doi":"10.1609/aaai.v36i2.20012","title":"SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Point cloud; Computer science; Convolution (computer science); Transformer; Artificial intelligence; Optical flow; Algorithm; Computer vision; Pattern recognition (psychology); Artificial neural network; 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":[0.0006024871,0.001200968,0.0008722084,0.001089705,0.0004172448,0.0006405193,0.001965955,0.0009353373,0.002581781],"category_scores_gemma":[0.001912891,0.0005549502,0.0008571106,0.001121091,0.0005799582,0.001786671,0.001301919,0.001388278,0.0007681235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023566,"about_ca_system_score_gemma":0.001393914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0167641,"about_ca_topic_score_gemma":0.01638964,"domain_scores_codex":[0.9996846,0.00004312586,0.00001479661,0.00009496122,0.0001042382,0.00005832053],"domain_scores_gemma":[0.9996445,0.0001082872,0.0000446055,0.00006787304,0.0001014256,0.00003336136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002464777,0.0001477752,0.001793804,0.00009433208,0.00009378097,0.0001191045,0.00008918474,0.492171,0.01863439,0.01120249,0.006967572,0.4684401],"study_design_scores_gemma":[0.000003789699,0.00001172895,0.0000827563,0.000001976579,0.000003781684,0.00001358839,0.000003005528,0.9964407,0.001445108,0.001588785,0.0004014551,0.000003352912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009497067,0.0001047687,0.9874889,0.00007341438,0.00003556305,0.00003608384,0.0001361371,0.001809243,0.000818833],"genre_scores_gemma":[0.4328202,0.0003592457,0.5587171,0.0003030537,0.00009507495,0.0001929156,0.002116073,0.0003664444,0.005029885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0167641,"threshold_uncertainty_score":0.03333306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06960887381939476,"score_gpt":0.3081054479267099,"score_spread":0.2384965741073151,"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."}}