{"id":"W2894280539","doi":"10.1609/aaai.v33i01.33019062","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":332,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Intelligence Advanced Research Projects Activity","keywords":"Computer science; Task (project management); CLIPS; Matching (statistics); Metric (unit); Natural language processing; Artificial intelligence; Sentence; Similarity (geometry); Word (group theory); Recurrent neural network; Artificial neural network; Information retrieval; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004735292,0.0001586609,0.0001821918,0.0001244988,0.0001366598,0.0002211631,0.001079666,0.0000724551,0.00002521988],"category_scores_gemma":[0.0007166441,0.0001184636,0.00006216276,0.0003865473,0.00007435679,0.0002787598,0.000299934,0.000213129,0.0001303038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003168616,"about_ca_system_score_gemma":0.00003754468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000071697,"about_ca_topic_score_gemma":0.000005881065,"domain_scores_codex":[0.9986644,0.00001191124,0.0003336774,0.0004887627,0.0002853388,0.0002159507],"domain_scores_gemma":[0.9987778,0.0001916451,0.0002203697,0.0002936944,0.0004355276,0.00008093542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006673208,0.00005309563,0.0002481207,0.00002704873,0.000003739282,1.905445e-8,0.002359251,0.0000441323,0.2908931,0.5551559,0.00004714804,0.1511018],"study_design_scores_gemma":[0.00005187383,0.0003429388,0.003903779,0.0001772233,0.000006165286,0.000001671138,0.0004379546,0.530439,0.4277703,0.03657014,0.000110492,0.0001884757],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8068361,0.000007464449,0.1826206,0.006686264,0.0002138905,0.001210176,0.000007692051,0.00009591871,0.002321842],"genre_scores_gemma":[0.9749306,0.000003208197,0.02439341,0.0002531785,0.00003751437,0.00003596656,8.660089e-7,0.00001114255,0.0003341539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5303949,"threshold_uncertainty_score":0.4830806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04201553110016543,"score_gpt":0.3481929253520091,"score_spread":0.3061773942518437,"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."}}