Learn More
The presence of occluders significantly impacts performance of systems for object recognition. However, occlu-sion is typically treated as an unstructured source of noise and explicit models for occluders have lagged behind those for object appearance and shape. In this paper we describe a hierarchical deformable part model for face detection and keypoint(More)
Occlusion poses a significant difficulty for object recognition due to the combinatorial diversity of possible oc-clusion patterns. We take a strongly supervised, non-parametric approach to modeling occlusion by learning de-formable models with many local part mixture templates using large quantities of synthetically generated training data. This allows the(More)
—This paper proposes, an efficient method for text independent writer identification using a codebook. The occurrence histogram of the shapes in the codebook is used to create a feature vector for the handwriting. There is a wide variety of different shapes in the connected components obtained from handwriting. Small fragments of connected components should(More)
The presence of occluders significantly impacts object recognition accuracy. However, occlusion is typically treated as an unstruc-tured source of noise and explicit models for occluders have lagged behind those for object appearance and shape. In this paper we describe a hierarchical deformable part model for face detection and landmark localization that(More)
Occlusion poses a significant difficulty for detecting and localizing object keypoints and subsequent fine-grained identification. We propose a part-based face detection model that utilizes bottom-up class-specific segmentation in order to jointly detect and segment out the foreground pixels belonging to the face. The model explicitly represents occlu-sion(More)
CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation(More)
CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This paper makes two contributions: (1) We demonstrate that while the apparent spatial resolution of convolutional feature maps is low, the high-dimensional feature representation(More)
  • 1