{"id":"W2964516821","doi":"","title":"TRECVID 2018: Benchmarking Video Activity Detection, Video Captioning and Matching, Video Storytelling Linking and Video Search","year":2018,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Computer science; Closed captioning; Benchmarking; Storytelling; Matching (statistics); Videoconferencing; Artificial intelligence; Video tracking; Computer vision; Video processing; Multimedia; Narrative; Image (mathematics); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006347725,0.0003268609,0.0003085464,0.0003486471,0.001971542,0.001064722,0.001022428,0.0001861616,0.00003915035],"category_scores_gemma":[0.0007481353,0.000365192,0.0000857305,0.0007989797,0.0004238627,0.0009091378,0.0008736761,0.0007389001,0.00004417831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001542734,"about_ca_system_score_gemma":0.0001243973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005838038,"about_ca_topic_score_gemma":0.002759401,"domain_scores_codex":[0.9944513,0.002906316,0.0004470316,0.001155422,0.0005058612,0.0005340141],"domain_scores_gemma":[0.9944305,0.002274196,0.0003634519,0.001554532,0.001079692,0.0002976129],"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":[0.00002328469,0.0002548771,0.02039271,0.0001253393,0.00007811991,0.000003812979,0.03342541,0.0004111464,0.08441661,0.0330046,0.00008388709,0.8277802],"study_design_scores_gemma":[0.0009307119,0.000006512407,0.1200514,0.00108346,0.00004336064,0.00009403013,0.0001909696,0.7802737,0.08460226,0.004731905,0.007134709,0.0008569788],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4296676,0.0002468185,0.5647956,0.002430585,0.0001134026,0.0002248745,0.000002818656,0.0002846771,0.002233649],"genre_scores_gemma":[0.8659985,0.0001323851,0.1331306,0.0001129959,0.00009726835,0.00004573897,0.00001168342,0.00003686492,0.0004339922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8269233,"threshold_uncertainty_score":0.9999723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01279470485631389,"score_gpt":0.2443957575191341,"score_spread":0.2316010526628202,"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."}}