{"id":"W4403289479","doi":"10.1016/j.knosys.2024.112610","title":"Vision-and-language navigation based on history-aware cross-modal feature fusion in indoor environment","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Modal; Computer science; Feature (linguistics); Fusion; Artificial intelligence; Computer vision; Human–computer interaction; Linguistics; Materials science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006002862,0.0002876785,0.0002572046,0.0003992326,0.0001421585,0.0002990221,0.0005001181,0.0002051225,0.00003109183],"category_scores_gemma":[0.00004012135,0.0002521207,0.00008936949,0.0003896467,0.00007366311,0.0002034885,0.0001098418,0.0005577733,0.0004587414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001032125,"about_ca_system_score_gemma":0.0002215355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003782444,"about_ca_topic_score_gemma":0.00001587146,"domain_scores_codex":[0.9977785,0.0003186764,0.0003454682,0.0008567174,0.0004047815,0.0002958627],"domain_scores_gemma":[0.998484,0.0004196478,0.00009945693,0.0008082157,0.00004211093,0.0001466259],"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":[0.0003637066,0.004087049,0.09063546,0.008473615,0.0001167296,0.0008352838,0.03235481,0.3997798,0.07182606,0.035354,0.01973466,0.3364388],"study_design_scores_gemma":[0.0006301574,0.0001264074,0.01884729,0.0007409789,0.000005785155,0.000005683935,0.00002244701,0.9583797,0.0002672408,0.00001751734,0.02069672,0.0002600987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5178989,0.01092705,0.4587696,0.002692049,0.002970265,0.002254687,0.00005462627,0.001310747,0.00312206],"genre_scores_gemma":[0.9970167,0.000002718913,0.001493495,0.00007851954,0.0001662793,0.0002878414,0.00007638319,0.00003641216,0.0008416287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5585998,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009174197934916771,"score_gpt":0.2859362663803817,"score_spread":0.2767620684454649,"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."}}