{"id":"W4393147243","doi":"10.1609/aaai.v38i13.29407","title":"XKD: Cross-Modal Knowledge Distillation with Domain Alignment for Video Representation Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Vector Institute","funders":"Mitacs","keywords":"Modal; Representation (politics); Computer science; Domain (mathematical analysis); Artificial intelligence; Computer vision; Mathematics; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005806557,0.0001988771,0.0001854693,0.0001350346,0.0003417048,0.0006917318,0.0009591259,0.00006036211,0.00002016503],"category_scores_gemma":[0.0003006216,0.0001438221,0.000101325,0.0007375325,0.0001942454,0.000457831,0.0002028475,0.0002993773,0.00007079534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008943336,"about_ca_system_score_gemma":0.0001054935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008154387,"about_ca_topic_score_gemma":0.00001043914,"domain_scores_codex":[0.9982537,0.00002469403,0.0004301913,0.0006511091,0.0003699771,0.0002702969],"domain_scores_gemma":[0.9986088,0.0002929282,0.0002445817,0.0002608364,0.0005237153,0.00006919991],"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":[0.00005580997,0.00006515378,0.001265654,0.00008332867,0.00001924979,1.779701e-7,0.002609048,0.002237503,0.01912988,0.9137836,0.00004326772,0.06070739],"study_design_scores_gemma":[0.00004633685,0.0002642725,0.001929363,0.0003093699,0.00001687852,0.000006045495,0.0003333794,0.720797,0.110063,0.1649237,0.0010762,0.0002344272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.301487,0.00003955981,0.6854013,0.003366241,0.0003108179,0.0009887468,0.000005953751,0.0003146116,0.008085832],"genre_scores_gemma":[0.9835305,0.000005153151,0.0157644,0.00003138421,0.0001002058,0.0002078444,0.00000247139,0.00002004021,0.0003379527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7488598,"threshold_uncertainty_score":0.6670385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05995314657169955,"score_gpt":0.365077943104851,"score_spread":0.3051247965331515,"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."}}