High-level, or holistic, scene understanding involves
reasoning about objects, regions, and the 3D relationships
between them. This requires a representation above the
level of ...
In this paper, we address the problems of deformable object matching (alignment) and segmentation with cluttered background. We propose a novel hierarchical log-linear model (HLLM...
Long Zhu, Yuanhao Chen, Xingyao Ye, Alan L. Yuille
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...