{"id":"W4386159122","doi":"10.1109/icme55011.2023.00259","title":"CHAN: Cross-Modal Hybrid Attention Network for Temporal Language Grounding in Videos","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"China Postdoctoral Science Foundation","keywords":"Computer science; Modality (human–computer interaction); Modalities; Modal; Semantics (computer science); Sentence; Frame (networking); Key (lock); Artificial intelligence; Natural language processing; Word (group theory); Task (project management); Focus (optics); Speech recognition; Linguistics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007943106,0.001557658,0.000825549,0.001489422,0.0005213437,0.000602668,0.001795101,0.00107889,0.00309387],"category_scores_gemma":[0.001996344,0.0004021987,0.0007946088,0.001121985,0.0005073521,0.001775142,0.001610919,0.00114439,0.000692189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333774,"about_ca_system_score_gemma":0.000988748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02596678,"about_ca_topic_score_gemma":0.03296496,"domain_scores_codex":[0.9995592,0.00008419964,0.0000147398,0.0001769133,0.00007406446,0.00009079883],"domain_scores_gemma":[0.9996091,0.0001706435,0.00003822496,0.00004402713,0.0001021355,0.00003591512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008500445,0.0003694794,0.00303554,0.0002861904,0.0002913558,0.0004497115,0.0003246653,0.1373189,0.03959001,0.007030446,0.02082344,0.7896302],"study_design_scores_gemma":[0.00002563258,0.0001008288,0.000947397,0.00001760645,0.00005669637,0.0000778535,0.00006074517,0.9842067,0.005922065,0.006241498,0.002323134,0.00001984888],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07734124,0.002906062,0.9016078,0.0005872579,0.0002748402,0.000296419,0.001404816,0.00902285,0.006558872],"genre_scores_gemma":[0.8169597,0.0009654678,0.1651076,0.0009121654,0.0002573926,0.0003334274,0.003712232,0.0003733116,0.01137864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02596678,"threshold_uncertainty_score":0.05163127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02041856827068133,"score_gpt":0.3406524902880305,"score_spread":0.3202339220173491,"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."}}