{"id":"W4312372711","doi":"10.1109/cvpr52688.2022.00495","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Focus (optics); Information retrieval; Representation (politics); ENCODE; Pooling; Recall; Natural language processing; Artificial intelligence; Similarity (geometry); Text retrieval; Code (set theory); Function (biology); Image (mathematics); Linguistics","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":[0.001272262,0.002048034,0.0015465,0.001951143,0.0005282754,0.001148195,0.003410534,0.001796134,0.007246877],"category_scores_gemma":[0.002471823,0.000464227,0.001587637,0.00131923,0.0006294205,0.002682947,0.002054155,0.001507324,0.003044774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001564969,"about_ca_system_score_gemma":0.001106776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01519648,"about_ca_topic_score_gemma":0.01573423,"domain_scores_codex":[0.999424,0.0000904245,0.00002906484,0.0002252226,0.000132795,0.00009843796],"domain_scores_gemma":[0.9995549,0.000162802,0.00003804755,0.00009124653,0.0001082084,0.00004476445],"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":[0.001072542,0.0006627087,0.001616056,0.0005054881,0.0003622572,0.0003517152,0.0002099437,0.05156916,0.05345302,0.004378988,0.04002761,0.8457906],"study_design_scores_gemma":[0.0001092372,0.000370326,0.001009057,0.00003937401,0.0001346427,0.0003361755,0.00006895575,0.9640018,0.02062264,0.006575952,0.006683908,0.00004786703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04358679,0.005199775,0.9148979,0.0005577985,0.0003960676,0.0006978968,0.001645763,0.02789606,0.005121961],"genre_scores_gemma":[0.471549,0.001866285,0.4915252,0.002287125,0.0006040695,0.001009883,0.007063023,0.001165796,0.02292954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01519648,"threshold_uncertainty_score":0.03021604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03439024797878233,"score_gpt":0.3264412100324542,"score_spread":0.2920509620536719,"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."}}