{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006786029,0.0001050005,0.0001199838,0.0001438581,0.0001813021,0.0002128692,0.0005100369,0.0000357914,0.0000134177],"category_scores_gemma":[0.00006753462,0.0001037975,0.00006495661,0.0007319894,0.00001946044,0.0003217034,0.0002022083,0.0001282483,0.0002109927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005111095,"about_ca_system_score_gemma":0.00002145106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001061092,"about_ca_topic_score_gemma":0.0001423043,"domain_scores_codex":[0.9988121,0.00004052878,0.0002205989,0.0003896258,0.0001541513,0.0003829795],"domain_scores_gemma":[0.9992873,0.0001741055,0.00006927192,0.0003816065,0.00003134686,0.00005638353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000266789,0.0001328349,0.6175849,0.00009093495,0.00003297441,0.00004282747,0.001389316,0.03811435,0.003853695,0.2381687,0.007261515,0.09330128],"study_design_scores_gemma":[0.0003414419,0.00002217573,0.3204786,0.00001146162,0.000001248922,0.000003327513,0.00002186108,0.6745865,0.00007191549,0.003610168,0.0007299496,0.0001213356],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5391114,0.00001045371,0.4582437,0.001163103,0.0002008755,0.0003278598,0.00000279349,0.0005193587,0.000420383],"genre_scores_gemma":[0.9501343,0.000001098969,0.04788259,0.000154289,0.000274237,0.000232117,0.00006072904,0.0000145045,0.001246108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6364722,"threshold_uncertainty_score":0.4232738,"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."}}