{"id":"W4411119193","doi":"10.18653/v1/2025.naacl-srw.37","title":"ELIOT: Zero-Shot Video-Text Retrieval through Relevance-Boosted Captioning and Structural Information Extraction","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Closed captioning; Shot (pellet); Relevance (law); Computer science; Zero (linguistics); Information retrieval; Feature extraction; Artificial intelligence; Extraction (chemistry); Natural language processing; Speech recognition; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001876872,0.0001350606,0.0001228797,0.0001453768,0.0003791437,0.0003610883,0.0003030538,0.00008967378,0.00002885541],"category_scores_gemma":[0.0002613482,0.0001275472,0.00003161175,0.000666247,0.00004433067,0.002641377,0.0001665934,0.0002813515,0.00006608206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009082389,"about_ca_system_score_gemma":0.00006142888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006542549,"about_ca_topic_score_gemma":0.00001519325,"domain_scores_codex":[0.998941,0.00005283486,0.0003261266,0.0002754295,0.0002113859,0.0001932062],"domain_scores_gemma":[0.999043,0.000213976,0.000143976,0.0004089685,0.0001453772,0.00004468496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006941021,0.00002582797,0.00618535,0.00009510278,0.00004973132,0.00000130367,0.00293677,0.00925018,0.01450812,0.7222518,0.001864746,0.2427617],"study_design_scores_gemma":[0.0008266741,0.00005209137,0.2105846,0.00006048735,0.00001721184,0.00003791471,0.0001080339,0.7414425,0.004879538,0.02744995,0.01421429,0.0003267191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.182985,0.00006874561,0.8018888,0.002943435,0.0002563718,0.0002562923,0.000001499681,0.000378267,0.01122153],"genre_scores_gemma":[0.916199,0.00002470673,0.08268702,0.0006083397,0.00002422941,0.00001292369,0.00001599864,0.000004131157,0.0004236129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.733214,"threshold_uncertainty_score":0.5201222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01266419305219626,"score_gpt":0.3036114091008882,"score_spread":0.290947216048692,"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."}}