{"id":"W2963499204","doi":"","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives.","year":2018,"lang":"en","type":"article","venue":"British Machine Vision Conference","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":230,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Modal; Ranking (information retrieval); Information retrieval; Learning to rank; Artificial intelligence; Simple (philosophy); Image retrieval; Image (mathematics); Machine learning; Data mining; Pattern recognition (psychology)","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":[0.002019302,0.002154962,0.00135451,0.001751601,0.0005357601,0.001588575,0.002230057,0.001556172,0.005029542],"category_scores_gemma":[0.01103893,0.0004473596,0.0009276638,0.001412285,0.0009563417,0.004684827,0.003259375,0.001961862,0.004707535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005045528,"about_ca_system_score_gemma":0.0007210181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00186724,"about_ca_topic_score_gemma":0.003003387,"domain_scores_codex":[0.9983743,0.0004745629,0.0001009962,0.0003546106,0.0005726981,0.0001227213],"domain_scores_gemma":[0.9975063,0.0007613799,0.0001913725,0.0008554801,0.0005920529,0.00009339352],"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":[0.0007223589,0.0007782765,0.003052091,0.0005696344,0.0001913602,0.0001962813,0.0001823499,0.0399479,0.0272205,0.01428023,0.05327483,0.8595842],"study_design_scores_gemma":[0.0001101798,0.0006539277,0.001261823,0.0000782761,0.00007711967,0.0005975178,0.0002419209,0.9062929,0.02828174,0.03556922,0.02675942,0.00007586795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06114625,0.002165731,0.9096893,0.0005135356,0.0005613486,0.0003406352,0.00259586,0.01501827,0.007969151],"genre_scores_gemma":[0.4582328,0.0007878417,0.499397,0.0009950993,0.0003744088,0.0005242042,0.01667294,0.001641488,0.02137415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005029542,"threshold_uncertainty_score":0.01682544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01003198278439735,"score_gpt":0.2815968184575066,"score_spread":0.2715648356731092,"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."}}