{"id":"W4415535740","doi":"10.1016/j.array.2025.100538","title":"Mamba-caption: Long-range sequence modelling for efficient and accurate image captioning","year":2025,"lang":"en","type":"article","venue":"Array","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"University of Johannesburg","keywords":"Closed captioning; Security token; Convolutional neural network; Trigram; Embedding; Clipping (morphology); Decoding methods; Image (mathematics); Pattern recognition (psychology)","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":[0.001142062,0.00140366,0.000800936,0.0006624313,0.0004508314,0.001796075,0.002400431,0.001778282,0.008609783],"category_scores_gemma":[0.004683312,0.000629055,0.001157049,0.0007384961,0.0008892574,0.003094965,0.001646866,0.002540666,0.005032381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097229,"about_ca_system_score_gemma":0.001169124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00454639,"about_ca_topic_score_gemma":0.008080633,"domain_scores_codex":[0.9994645,0.0001561889,0.00003311207,0.0001742196,0.0001190971,0.00005292087],"domain_scores_gemma":[0.9989003,0.0005309767,0.00006376069,0.0002248531,0.000228811,0.00005131834],"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":[0.0005059229,0.0001466723,0.0008150501,0.0008190927,0.0001151681,0.0004998349,0.0004830781,0.426268,0.05330022,0.04808343,0.03885908,0.4301045],"study_design_scores_gemma":[0.00001399606,0.00005492564,0.00008416074,0.00002500484,0.00001351663,0.0001042096,0.00002703301,0.9608069,0.01492073,0.01361873,0.01031218,0.00001866222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005929156,0.0007363429,0.9770029,0.0004076452,0.0002442152,0.0001226434,0.0006906487,0.01108158,0.003784905],"genre_scores_gemma":[0.2600483,0.00123011,0.7131578,0.000833732,0.0002329335,0.0005602891,0.004373867,0.002865275,0.01669766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008609783,"threshold_uncertainty_score":0.02880257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02984790941700368,"score_gpt":0.3121207670062762,"score_spread":0.2822728575892725,"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."}}