{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001598557,0.0001013386,0.000150354,0.0000778757,0.00005827844,0.0001341338,0.0002637617,0.00005863995,0.00002371997],"category_scores_gemma":[0.00009292857,0.00008621168,0.00002534277,0.000245666,0.00003436148,0.0004537012,0.0001807377,0.0001974552,0.00001779517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002386241,"about_ca_system_score_gemma":0.00003174603,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131833,"about_ca_topic_score_gemma":0.0003293597,"domain_scores_codex":[0.9991281,0.00005951701,0.0002386699,0.0002716206,0.0001352332,0.0001668465],"domain_scores_gemma":[0.9994229,0.00009264296,0.000082946,0.0003117643,0.00004768318,0.00004206787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001282946,0.0004414339,0.3448424,0.0001516091,0.00004389466,0.000008452717,0.04384996,0.007412512,0.01207548,0.06864105,0.0004542721,0.5220661],"study_design_scores_gemma":[0.0005080694,0.00007846687,0.6498637,0.0001012292,0.00000763195,0.0000100929,0.0003554249,0.3361834,0.001394134,0.0108812,0.0003860701,0.0002306106],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551668,0.00009424034,0.2423448,0.00114789,0.00006085684,0.0002490835,3.309542e-7,0.00007755071,0.0008584856],"genre_scores_gemma":[0.8276151,0.00002341639,0.1719897,0.000166369,0.00003841679,0.0000310991,6.803372e-7,0.000005287536,0.0001299236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5218355,"threshold_uncertainty_score":0.993388,"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."}}