{"id":"W4377832613","doi":"10.18280/ts.400213","title":"TraViQuA: Natural Language Driven Traffic Video Querying Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Natural (archaeology); Natural language processing; Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008787806,0.001636852,0.000644605,0.001305946,0.0004273087,0.001361665,0.002546992,0.001261042,0.006396868],"category_scores_gemma":[0.002875049,0.0005230074,0.001002923,0.0008084136,0.0004680085,0.002945495,0.001839617,0.001571346,0.002204229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001467441,"about_ca_system_score_gemma":0.001153867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02177317,"about_ca_topic_score_gemma":0.03105444,"domain_scores_codex":[0.9991455,0.0001278231,0.00008660986,0.0003237536,0.0002289727,0.00008733186],"domain_scores_gemma":[0.9992828,0.0002922924,0.0000661453,0.0001328148,0.0001688459,0.00005725054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001900375,0.001442587,0.009540274,0.001650119,0.0003909634,0.001434876,0.0008719792,0.05927991,0.07213529,0.009011096,0.1802178,0.6621247],"study_design_scores_gemma":[0.0001145453,0.0002276361,0.001426715,0.00003779161,0.00003142935,0.0002791828,0.0002029336,0.9487358,0.02206293,0.006090547,0.02072754,0.00006293754],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1130261,0.001677861,0.4603526,0.001054488,0.0003548385,0.001411765,0.02742369,0.383467,0.01123165],"genre_scores_gemma":[0.4427832,0.0006598803,0.4773409,0.001378891,0.00008085949,0.0009716463,0.0626443,0.003661907,0.01047854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02177317,"threshold_uncertainty_score":0.04329288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01459287012862945,"score_gpt":0.2499085565516157,"score_spread":0.2353156864229862,"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."}}