{"id":"W1586939924","doi":"10.1109/iccv.2015.512","title":"Describing Videos by Exploiting Temporal Structure","year":2015,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":956,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Université de Montréal; Université de Sherbrooke","funders":"Compute Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Representation (politics); Convolutional neural network; Context (archaeology); Motion (physics); Natural language; Pattern recognition (psychology); Artificial neural network; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001737518,0.00009927893,0.00008602525,0.00004359493,0.000100677,0.0001700968,0.0006514225,0.00004011915,0.00003102961],"category_scores_gemma":[0.0001573386,0.00008709614,0.00002263113,0.000243386,0.00001715946,0.0004048717,0.0002205726,0.0001652223,0.0000841919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000427815,"about_ca_system_score_gemma":0.00006080805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008014744,"about_ca_topic_score_gemma":0.00001373262,"domain_scores_codex":[0.9990841,0.00004663747,0.0001468775,0.000298987,0.0002194558,0.0002039861],"domain_scores_gemma":[0.9991681,0.0000459589,0.00006069779,0.0004357616,0.00007060624,0.0002188892],"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":[0.000008782599,0.0001664712,0.1433324,0.00001951631,0.00004657258,0.00001625023,0.006366433,0.00602422,0.0639423,0.274059,0.1415468,0.3644712],"study_design_scores_gemma":[0.0008543529,0.00008275752,0.002639114,0.00002530433,0.00000581225,0.00004566377,0.0003628123,0.9424486,0.01356776,0.01223302,0.0270967,0.0006381651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1526503,0.00003605978,0.8389517,0.00299369,0.00009229914,0.0001130836,0.000002306081,0.0005633858,0.004597207],"genre_scores_gemma":[0.7728828,1.496458e-7,0.2263172,0.0005680012,0.00004049879,0.000008729146,0.000006698652,0.000007490547,0.0001683585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9364243,"threshold_uncertainty_score":0.3551678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05364504113686984,"score_gpt":0.2721015833326518,"score_spread":0.2184565421957819,"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."}}