{"id":"W1581862991","doi":"10.1109/tpami.2015.2505297","title":"Saying What You're Looking For: Linguistics Meets Video Search","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Laboratory; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology; University of Waterloo; Purdue University","keywords":"Computer science; Natural language processing; Parsing; Sentence; Artificial intelligence; Meaning (existential); Semantics (computer science); Noun; Natural language; Object (grammar); Information retrieval; Linguistics; 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":[0.0006963615,0.000254832,0.0003385933,0.0005626563,0.0003684509,0.0005613812,0.0006970653,0.00008573849,0.00002891836],"category_scores_gemma":[0.00006661414,0.0002403948,0.0002371171,0.001080791,0.00006767028,0.0002770573,0.00001620953,0.0003943797,0.00003807199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007481202,"about_ca_system_score_gemma":0.00005058457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002506417,"about_ca_topic_score_gemma":0.0008831087,"domain_scores_codex":[0.9979855,0.0001136928,0.0004249132,0.0007171892,0.0004102844,0.000348401],"domain_scores_gemma":[0.9981008,0.0003795654,0.0001164058,0.0007583804,0.0003612088,0.0002836974],"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":[0.00001061995,0.0001221264,0.001121263,0.00002167815,0.0002843542,0.000003448263,0.001327683,0.1999682,0.000089348,0.0006708187,0.0000114841,0.7963689],"study_design_scores_gemma":[0.0001539876,0.0001204004,0.0003496317,0.00004203819,0.0003126093,0.000004883569,0.0002436005,0.9798831,0.01690864,0.0006522698,0.001013361,0.0003155201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002208607,0.000237975,0.9951988,0.001414758,0.0003710655,0.0002478937,0.00002438961,0.0001620687,0.0001344789],"genre_scores_gemma":[0.9792982,0.00021757,0.0197453,0.0004634784,0.0000741506,0.00006620416,0.00001008839,0.0000210382,0.0001039954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9770896,"threshold_uncertainty_score":0.9803016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04908248354753265,"score_gpt":0.3303374245799985,"score_spread":0.2812549410324659,"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."}}