关键词：探测器；可用性计算机
摘 要：Part detectors are a common way to handle the variability in appearance in high-level computer vision problems, such as detection and semantic segmentation. Identifying good parts, however, remains an open question. Anatomical parts, such as arms and legs, are
difficult to detect reliably because parallel lines are common in natural images. In contrast, a visual conjunction such as "half of a frontal face and a left shoulder" may be a perfectly good discriminative visual pattern. We propose a new computer vision part, called a poselet,
wich is trained to respond to a given part of the object at a given viewpoint and pose. There is a wide variety of poselets { a frontal face, a pro le face, a head-and-shoulder con guration, etc. A requirement for training poselets is that the visual correspondence of object parts
in the training images be provided. We create a new dataset, H3D, in which we annotate the locations of keypoints of people, infer their 3D pose and label their parts (the face, hair, upper clothes, etc.). Our richly annotated dataset allows for creation of poselets as well as
other queries not possible with traditional datasets.
索取原文[78 页]
027-87841330