{"id":"W4407352310","doi":"10.2139/ssrn.5131396","title":"V-Sparse: Temporal-Spatial Visual Compression and Coarse-to-Fine Alignment for Text-Video Retrieval","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Video retrieval; Pattern recognition (psychology); Computer vision","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":[0.0006177362,0.001253899,0.001342042,0.002085536,0.0005533358,0.001377341,0.001412551,0.001299051,0.007482001],"category_scores_gemma":[0.003898398,0.0004718079,0.0006855218,0.003443767,0.0006389734,0.002094685,0.002089229,0.001433021,0.003358211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004863284,"about_ca_system_score_gemma":0.001161824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005291436,"about_ca_topic_score_gemma":0.007876691,"domain_scores_codex":[0.9992867,0.0001166196,0.00004940519,0.0001441753,0.000316952,0.00008612663],"domain_scores_gemma":[0.9990327,0.0003268047,0.00008919446,0.0002751117,0.0002073667,0.00006887604],"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":[0.0005317167,0.0001698892,0.0003638928,0.0002342122,0.00006018773,0.0001158047,0.00008553161,0.02459257,0.04266366,0.00877497,0.02097396,0.9014335],"study_design_scores_gemma":[0.0001237478,0.0003241261,0.000911466,0.0000546915,0.00005972756,0.0003813304,0.000113743,0.9050983,0.04580909,0.03000024,0.01707567,0.00004790533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006945136,0.0008651184,0.9843196,0.0002146026,0.0002077857,0.0001369956,0.0006817603,0.005257276,0.001371742],"genre_scores_gemma":[0.1358428,0.001374756,0.8484643,0.0003989513,0.0006095414,0.0003970228,0.003665947,0.000816848,0.008429641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007482001,"threshold_uncertainty_score":0.02502978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121976333115473,"score_gpt":0.282626849278032,"score_spread":0.2704292159664847,"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."}}