{"id":"W4391274453","doi":"10.1007/978-3-031-53311-2_30","title":"Multi-modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Domain adaptation; Segmentation; Artificial intelligence; Modal; Domain (mathematical analysis); Adaptation (eye); Semantics (computer science); Computer vision; Dual (grammatical number); Adaptability; Natural language processing; 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":[0.0005665653,0.0004328381,0.0004118144,0.0008048717,0.0002195508,0.0008431338,0.0008766526,0.0002068017,0.0000139703],"category_scores_gemma":[0.00002637675,0.000347133,0.0001116175,0.0008077382,0.0002880162,0.0008734691,0.0003751746,0.0004820243,0.00004841569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000360187,"about_ca_system_score_gemma":0.0003881734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005558133,"about_ca_topic_score_gemma":0.0006392195,"domain_scores_codex":[0.9967405,0.00003732123,0.0004714843,0.00139934,0.0009430394,0.000408285],"domain_scores_gemma":[0.99852,0.0001877438,0.0002432689,0.0006614745,0.0002709314,0.0001165526],"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":[0.00002296698,0.00007031737,0.0002092326,0.00009240882,0.0001148254,0.0003302381,0.009208507,0.2990553,0.001361854,0.06453667,0.00001143488,0.6249862],"study_design_scores_gemma":[0.0003753552,0.0001810766,0.0003435708,0.0003132533,0.00003068417,0.00003419776,0.000002814046,0.9301887,0.0005827808,0.06726951,0.0002036327,0.0004743835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002082315,0.0002987031,0.9964043,0.0007612621,0.0008476388,0.000408771,0.000005499901,0.000143223,0.0009222953],"genre_scores_gemma":[0.2030963,0.00003379425,0.7947176,0.0006527425,0.000370235,0.00002460882,0.0000374384,0.0000378548,0.001029443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6311334,"threshold_uncertainty_score":0.9998981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01309883878653341,"score_gpt":0.2357262298425344,"score_spread":0.2226273910560009,"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."}}