Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
This paper proposes a joint feature-based model indexing and geometric constraint based alignment pipeline for efficient and accurate recognition of 3D objects from a large model ...
Ying Shan, Bogdan Matei, Harpreet S. Sawhney, Rake...
Abstract. In set-based face recognition, each set of face images is often represented as a linear/nonlinear manifold and the Principal Angles (PA) or Kernel PAs are exploited to me...
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...
We present a method for retexturing non-rigid objects from a single viewpoint. Without reconstructing 3D geometry, we create realistic video with shape cues at two scales. At a coa...