{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003532783,0.000746318,0.0009578855,0.000764528,0.0005260928,0.0007399145,0.000930879,0.0006897453,0.001243989],"category_scores_gemma":[0.000898729,0.0003464988,0.0005778099,0.001038326,0.0003334262,0.001426441,0.001610901,0.0008011383,0.0006425924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002849792,"about_ca_system_score_gemma":0.0009777658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007357296,"about_ca_topic_score_gemma":0.01044496,"domain_scores_codex":[0.9996576,0.00002932327,0.00001436105,0.0001299747,0.00008845686,0.00008018054],"domain_scores_gemma":[0.9997534,0.00004407432,0.00003225663,0.00004000662,0.00009924964,0.00003088458],"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":[0.0009233421,0.0004139239,0.007099905,0.0001728972,0.0002277888,0.0004293149,0.0003775403,0.09856034,0.1076806,0.004693744,0.005559495,0.7738611],"study_design_scores_gemma":[0.00001678573,0.0001117752,0.004065318,0.00001296464,0.00006929362,0.0001734504,0.00009509953,0.9729185,0.01730046,0.003855219,0.001334508,0.00004674474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1141727,0.0007959423,0.8788373,0.0002174164,0.0002220499,0.00004193703,0.000290202,0.002294832,0.003127782],"genre_scores_gemma":[0.8657166,0.0003226795,0.1302841,0.0001466003,0.00007134485,0.00004476363,0.0005281826,0.0001024423,0.002783277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007357296,"threshold_uncertainty_score":0.01462895,"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."}}