{"id":"W2608022654","doi":"10.1109/icpr.2016.7900081","title":"Automatic video description generation via LSTM with joint two-stream encoding","year":2016,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Encoding (memory); Artificial intelligence; Convolutional neural network; Closed captioning; Recurrent neural network; RGB color model; Decoding methods; Deep learning; Component (thermodynamics); Feature extraction; Pattern recognition (psychology); Artificial neural network; Image (mathematics); Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000530934,0.001348052,0.0007283359,0.0009885503,0.0002642865,0.0008099422,0.001921901,0.0009432565,0.004230458],"category_scores_gemma":[0.002004375,0.0003953333,0.0006997842,0.001086286,0.0004110895,0.002461445,0.001090357,0.001482444,0.001894859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009662635,"about_ca_system_score_gemma":0.0008334725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006449508,"about_ca_topic_score_gemma":0.006921914,"domain_scores_codex":[0.9996382,0.00005658678,0.00002447729,0.0001208096,0.000111154,0.00004872306],"domain_scores_gemma":[0.9995059,0.0001657062,0.00004303122,0.00009829424,0.0001523123,0.00003480833],"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":[0.0004350074,0.0002272223,0.0006756501,0.0002928915,0.00009298756,0.0003831875,0.0001224311,0.089741,0.04164555,0.007421372,0.01854047,0.8404222],"study_design_scores_gemma":[0.00002746577,0.00005907381,0.000177293,0.00001480513,0.0000240501,0.0001004677,0.00003361177,0.9666449,0.02434346,0.004512894,0.004045493,0.0000164566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01900011,0.0007563033,0.9613233,0.0003341002,0.0002429307,0.0002015988,0.001079401,0.01362519,0.00343707],"genre_scores_gemma":[0.3416218,0.0008789098,0.638742,0.0004256771,0.0001666061,0.0003599626,0.006339664,0.0006592091,0.01080621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006449508,"threshold_uncertainty_score":0.01415235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02855375016983549,"score_gpt":0.2545483060394659,"score_spread":0.2259945558696304,"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."}}