{"id":"W1995820507","doi":"10.1109/cvpr.2013.340","title":"A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching","year":2013,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":294,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Interior Business Center; Defense Advanced Research Projects Agency; U.S. Department of the Interior; Simon Fraser University; National Science Foundation","keywords":"Computer science; Image stitching; Artificial intelligence; Natural language processing; Natural language; Object (grammar); Probabilistic logic; Image (mathematics); Language model; Annotation; Natural language generation; Information retrieval; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009175241,0.0006201326,0.0004956338,0.001629692,0.0004424361,0.001042037,0.0009010676,0.0006991843,0.001633606],"category_scores_gemma":[0.005076235,0.0003328977,0.0007279789,0.001237,0.0005681436,0.002517625,0.001175071,0.001099756,0.0008708909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007395279,"about_ca_system_score_gemma":0.0006394507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008098359,"about_ca_topic_score_gemma":0.009755483,"domain_scores_codex":[0.9994306,0.0001878018,0.00003667258,0.0001570898,0.0001339556,0.00005389682],"domain_scores_gemma":[0.9986756,0.0004806171,0.0001667568,0.0003233006,0.0002893141,0.00006428408],"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":[0.0008319698,0.000170485,0.006583968,0.0003532885,0.0001365438,0.000805636,0.001820062,0.04197271,0.04741967,0.01828252,0.01855282,0.8630702],"study_design_scores_gemma":[0.00003076738,0.0001326696,0.004331086,0.00007965259,0.00008725578,0.0006566847,0.0007114306,0.9229225,0.02994592,0.0246462,0.0163714,0.00008444411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08455831,0.0008990722,0.9041079,0.0006911561,0.0001003455,0.0001620927,0.001497761,0.004781284,0.003202019],"genre_scores_gemma":[0.4743637,0.0008605722,0.5145702,0.0003277732,0.0001522855,0.0002080691,0.00429937,0.0004751237,0.004742889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008098359,"threshold_uncertainty_score":0.01610243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03467305324326582,"score_gpt":0.2914807309224713,"score_spread":0.2568076776792055,"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."}}