{"id":"W3095478416","doi":"10.1109/cvprw53098.2021.00181","title":"An Improved Attention for Visual Question Answering","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Question answering; Computer science; Benchmark (surveying); Artificial intelligence; Encoder; Context (archaeology); Task (project management); Natural language; Modality (human–computer interaction); Relation (database); Information retrieval; Natural language processing; Data mining","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":[0.0003865671,0.0001861788,0.0001831908,0.00009744058,0.0001348002,0.0006251837,0.0007669559,0.0001927266,0.00001051024],"category_scores_gemma":[0.00006098834,0.0001994537,0.0001212372,0.0001207837,0.00001307701,0.0003117551,0.0005959415,0.0003487318,0.000007817545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000778109,"about_ca_system_score_gemma":0.0001147889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001207432,"about_ca_topic_score_gemma":0.00008165046,"domain_scores_codex":[0.9984669,0.00009255822,0.000256226,0.0008395727,0.0001416295,0.0002030926],"domain_scores_gemma":[0.9985592,0.00005522366,0.0001613847,0.0009033911,0.0002295436,0.00009130679],"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":[0.00001756719,0.0008771219,0.006257091,0.000608336,0.0001195427,0.000003243265,0.001087034,0.04384046,0.2788194,0.07509305,0.00008452355,0.5931927],"study_design_scores_gemma":[0.0001340368,0.00005706428,0.03290651,0.00003676716,0.00001002074,0.000002107132,0.00001714191,0.9642193,0.001022303,0.001295817,0.00007279598,0.0002260855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1767066,0.00001827848,0.8209229,0.0006968892,0.0003977984,0.0005305925,0.000002665738,0.0005851565,0.0001392496],"genre_scores_gemma":[0.607508,0.000002492511,0.3917386,0.00006581052,0.0001161819,0.0003089959,0.0001679521,0.00001352486,0.00007847878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9203789,"threshold_uncertainty_score":0.8133485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01438235687974552,"score_gpt":0.349374374597222,"score_spread":0.3349920177174764,"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."}}