{"id":"W2963062932","doi":"10.1609/aaai.v30i1.10475","title":"SentiCap: Generating Image Descriptions with Sentiments","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":214,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Research Council; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Australian Government; Institute for Catastrophic Loss Reduction; Nvidia","keywords":"Closed captioning; Computer science; Natural language processing; Stylized fact; Artificial intelligence; Image (mathematics); Vocabulary; Sentiment analysis; Regularization (linguistics); Quality (philosophy); Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957853,0.0001885012,0.0001654244,0.0001000487,0.0002923767,0.0002587122,0.001541168,0.00004763782,0.00007672366],"category_scores_gemma":[0.0002455769,0.0001053771,0.00006966459,0.0005313052,0.0002799639,0.0004938535,0.0003321489,0.000182876,0.0002410354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000471017,"about_ca_system_score_gemma":0.00006829986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006174154,"about_ca_topic_score_gemma":0.000006898375,"domain_scores_codex":[0.9983716,0.00001978829,0.0003757595,0.0004888818,0.0004341989,0.0003097699],"domain_scores_gemma":[0.9985126,0.00008541869,0.000316476,0.0004007908,0.0005941935,0.00009052127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009600783,0.00008342704,0.0008255178,0.000007732024,0.00001106123,2.066533e-7,0.0002740649,0.00001889268,0.4297092,0.5332761,0.00005358721,0.0357306],"study_design_scores_gemma":[0.00006760168,0.0001567251,0.002149968,0.0003224641,0.00001953539,0.00001188372,0.0001509321,0.1255988,0.8098933,0.0612125,0.00009694558,0.0003193583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4194016,0.000004246828,0.5598478,0.01202518,0.0001607896,0.0004507,0.000005529188,0.0001917544,0.007912401],"genre_scores_gemma":[0.9397037,0.000005368086,0.05968139,0.0001239099,0.00004416889,0.0000516675,2.268129e-7,0.00001273135,0.0003768132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5203021,"threshold_uncertainty_score":0.4297155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05085603367949731,"score_gpt":0.2937594390146995,"score_spread":0.2429034053352022,"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."}}