{"id":"W2949877132","doi":"10.48550/arxiv.1809.02714","title":"DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Memorial University of Newfoundland","funders":"","keywords":"Computer science; End-to-end principle; Convolutional neural network; Generalization; Artificial intelligence; Set (abstract data type); Architecture; Deep learning; Network architecture; Similarity (geometry); Function (biology); Object (grammar); Layer (electronics); Pattern recognition (psychology); Image (mathematics); Computer network; Mathematics","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":[0.000805487,0.001272792,0.0008495807,0.0006779956,0.0004496863,0.0007443556,0.002331287,0.001338289,0.003039437],"category_scores_gemma":[0.001523461,0.000544861,0.0006247528,0.0007184935,0.0005041141,0.001502735,0.001344111,0.001438274,0.001345477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002823,"about_ca_system_score_gemma":0.001455856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01358222,"about_ca_topic_score_gemma":0.02673463,"domain_scores_codex":[0.9997553,0.00002925301,0.0000116564,0.00009638218,0.00006373633,0.00004359537],"domain_scores_gemma":[0.9996463,0.0000856198,0.00002572146,0.00009730116,0.0001098853,0.00003516934],"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":[0.0002621315,0.00027039,0.0026705,0.0000956516,0.0002046894,0.0001685762,0.000100307,0.4594106,0.01420406,0.008567939,0.01609494,0.4979502],"study_design_scores_gemma":[0.000007261038,0.00002090638,0.0001362667,0.000002123829,0.000005845185,0.00001754744,0.000003135782,0.996056,0.001276407,0.001823071,0.0006473039,0.000004111103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03223383,0.0005016387,0.9536318,0.0002248149,0.0001317698,0.0001145528,0.0004044338,0.009822461,0.002934676],"genre_scores_gemma":[0.5195475,0.0003855185,0.4596721,0.0006047888,0.00009304455,0.0002539175,0.003632077,0.000446803,0.01536417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01358222,"threshold_uncertainty_score":0.02700633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08451138352809662,"score_gpt":0.2303295093750432,"score_spread":0.1458181258469465,"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."}}