Average Jaccard: 61.3
Papers with Code · CC BY-SA 4.0
Visual Tracking
Visual Tracking is an essential and actively researched problem in the field of computer vision with various real-world applications such as robotic services, smart surveillance systems, autonomous driving, and human-computer interaction. It refers to the automatic estimation of the trajectory of an arbitrary target object, usually specified by a bounding box in the first frame, as it moves around in subsequent video frames.
<span class="description-source">Source: Learning Reinforced Attentional Representation for End-to-End Visual Tracking </span>
논문
Average Jaccard: 64.8Average PCK: 77.4Occlusion Accuracy: 86.2
Average Jaccard: 62.2Average PCK: 75.7Occlusion Accuracy: 89.3
Average Jaccard: 61.4Occlusion Accuracy: 89.7Average PCK: 74.2
AUC: 0.657
ACCURACY: 0.85Normalized Precision: 89.3
AUC: 60.3
AUC: 55.9
precision: 58.1AUC: 56.9
Score: 0.64
Average Jaccard: 0.36
MTE: 4.6δ: 63.45Survival: 88.42
precision: 42.0AUC: 42.0
AUC: 50.7
precision: 62.8AUC: 59.3