{"id":"W4308222681","doi":"10.1145/3536221.3556597","title":"A Framework for Video-Text Retrieval with Noisy Supervision","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Closed captioning; Artificial intelligence; Modal; Relevance (law); Context (archaeology); Task (project management); Natural language processing; Domain (mathematical analysis); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003350689,0.001233461,0.001471403,0.001858957,0.0008461996,0.002007094,0.003872073,0.002137466,0.003463763],"category_scores_gemma":[0.007702605,0.0007362156,0.001573197,0.00210449,0.001320108,0.003120277,0.002878226,0.002313948,0.002064795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001880877,"about_ca_system_score_gemma":0.002179025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01248245,"about_ca_topic_score_gemma":0.01427422,"domain_scores_codex":[0.9981664,0.000559186,0.0001108069,0.0006203745,0.0004269971,0.0001163476],"domain_scores_gemma":[0.9981021,0.0007938957,0.0002014236,0.0003817605,0.0004115956,0.0001092466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003874254,0.0003236078,0.0009208766,0.0005364422,0.0002361735,0.000439223,0.0004572241,0.4518329,0.01290198,0.1666053,0.03119862,0.3341602],"study_design_scores_gemma":[0.00002041306,0.00004498394,0.0001200118,0.00001693986,0.00001808842,0.0000725529,0.00002475952,0.9545362,0.001262281,0.03895916,0.004903167,0.00002137178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000992337,0.0002341585,0.9969073,0.0001825628,0.00002961372,0.00006754017,0.0002046373,0.000845797,0.0005360263],"genre_scores_gemma":[0.1090136,0.0007141618,0.8787915,0.0005547287,0.0003394359,0.0009329414,0.002819811,0.0004564493,0.006377316],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01248245,"threshold_uncertainty_score":0.02481961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01734851815095571,"score_gpt":0.2900835527978527,"score_spread":0.272735034646897,"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."}}