{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001818627,0.001866257,0.001091334,0.001065029,0.0006220787,0.001195719,0.00319856,0.001844634,0.004373678],"category_scores_gemma":[0.004466989,0.0006308925,0.001140511,0.00100369,0.001083952,0.002628469,0.003897308,0.003771386,0.002035519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111014,"about_ca_system_score_gemma":0.001445176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004392272,"about_ca_topic_score_gemma":0.006282816,"domain_scores_codex":[0.9986628,0.0004027505,0.00006208612,0.0005081915,0.0002282015,0.0001358379],"domain_scores_gemma":[0.9987749,0.0005141965,0.00009637752,0.0003298861,0.0002075126,0.0000771148],"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":[0.0005185932,0.0005339151,0.00181548,0.0004965849,0.0002233465,0.0001920802,0.0002796903,0.1664882,0.01893982,0.01116273,0.0280988,0.7712507],"study_design_scores_gemma":[0.00004939598,0.0001133431,0.0002996499,0.00002919874,0.00002277273,0.00006868949,0.00004779611,0.9728767,0.009805495,0.01218734,0.004475996,0.00002360625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0159161,0.0009301754,0.9705296,0.0003533414,0.0001329363,0.0001418611,0.001067438,0.00872787,0.002200763],"genre_scores_gemma":[0.3852507,0.0005932584,0.5918438,0.001198695,0.0001951815,0.0006787919,0.01006352,0.0007805117,0.009395578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004392272,"threshold_uncertainty_score":0.01463139,"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."}}