{"id":"W4293868279","doi":"10.1109/crv55824.2022.00038","title":"3DVQA: Visual Question Answering for 3D Environments","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Question answering; Computer science; Task (project management); Artificial intelligence; Domain (mathematical analysis); Modality (human–computer interaction); Relation (database); Point (geometry); Baseline (sea); Natural language processing; Information retrieval; Computer vision; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002163813,0.00005677047,0.00005035934,0.00004373768,0.0003303425,0.00003454472,0.0003664819,0.00001114175,0.00007484586],"category_scores_gemma":[0.00001538895,0.00006128337,0.00002569693,0.0001092365,0.000008441841,0.0001160937,0.0003171229,0.00009329182,0.00003699486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007058852,"about_ca_system_score_gemma":0.00001147917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001129093,"about_ca_topic_score_gemma":0.000001535786,"domain_scores_codex":[0.9993334,0.00004225468,0.00009448679,0.0002448086,0.0001539042,0.0001311771],"domain_scores_gemma":[0.9996358,0.00005678752,0.00003853727,0.0002292296,0.000004481048,0.00003518818],"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":[0.00001705986,0.0005788752,0.01167266,0.00001742982,0.00003191783,0.000002687049,0.001023212,0.1037585,0.03524809,0.3157928,0.001280456,0.5305763],"study_design_scores_gemma":[0.0001793807,0.00008645045,0.01701978,6.714658e-7,0.000001924094,0.000003703551,0.000011882,0.9272864,0.0005099086,0.0007976117,0.05400833,0.00009391992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02652223,0.000009323361,0.9710537,0.001121713,0.00009773209,0.000220909,0.000001790905,0.0001566486,0.0008159348],"genre_scores_gemma":[0.7504317,5.143253e-7,0.2481215,0.0002333321,0.00002386658,0.0003299786,0.000008210895,0.000006186234,0.0008447953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8235279,"threshold_uncertainty_score":0.2540761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009262272345025406,"score_gpt":0.2886512940798796,"score_spread":0.2793890217348541,"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."}}