Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponc...
This paper presents an effective strategy to extract the buildings and to reconstruct 3-D buildings using high-resolution multispectral stereo satellite images. Proposed scheme con...
In this paper, three baseline face recognition algorithms are evaluated on the CAS-PEAL-R1 face database which is publicly released from a large-scale Chinese face database: CAS-PE...
In this paper, we present a novel design of a wavelet-based video coding algorithm within a conventional hybrid framework of temporal motion-compensated prediction and transform co...