{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009117155,0.0003896211,0.0003962401,0.0003597082,0.001055059,0.0008326814,0.0009489253,0.0001227464,0.0007739217],"category_scores_gemma":[0.0000510013,0.0004004747,0.0002045095,0.0004817372,0.00009146509,0.0005154152,0.0006113024,0.0007279167,0.0002586124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001008564,"about_ca_system_score_gemma":0.00008053974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001447064,"about_ca_topic_score_gemma":0.00001557296,"domain_scores_codex":[0.9965428,0.0004558158,0.0005904011,0.001220293,0.0007019428,0.0004888052],"domain_scores_gemma":[0.9978715,0.0004890683,0.0003623997,0.000753598,0.0002879748,0.000235526],"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":[0.0002102397,0.000495816,0.002233502,0.0000938766,0.00005334415,0.00002502774,0.001131958,0.0008315018,0.005460713,0.001172657,0.005133914,0.9831575],"study_design_scores_gemma":[0.002652379,0.001570998,0.03714852,0.0001139557,0.00002778954,0.0001019096,0.0001020817,0.9497818,0.0008196452,0.003096568,0.003813624,0.0007707585],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4102937,0.00002858537,0.5840504,0.003054244,0.001019537,0.0007496413,0.0002072467,0.0003365198,0.0002601201],"genre_scores_gemma":[0.9874263,0.000024654,0.007792443,0.003156452,0.0003643972,0.0003236913,0.0004684079,0.00004390033,0.0003997702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9823867,"threshold_uncertainty_score":0.9998447,"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."}}