Recent researches on transfer learning exploit deep structures for discriminative feature representation to tackle cross-domain disparity. However, few of them are able to joint feature learning and knowledge transfer in a unified deep framework. In this paper, we develop a novel approach, called Deep Low-Rank Coding (DLRC), for transfer learning. Specifically, discriminative low-rank coding is...

Abstract In a world where technology is an ordinary part of everyday life, it particularly important for making, coding, and educational robotics to feature in school programs. On one hand, the construction elements that are peculiar digital fabrication make pedagogical perspective active; on other, they can support development active teaching practices. Although appears be kind revolution, som...

Neural coding for texture features of visual objects was investigated in monkey inferior temporal cortex by inactivating intrinsic GABAergic inhibition. The inactivation enabled a substantial number of cells to respond to originally ineffective texture pattern that had a particular feature distinct from the originally effective pattern, or to ineffective texture and non-texture stimuli that pos...

One popular approach for human action recognition is to extract features from videos as representations, subsequently followed by a classification procedure of the representations. In this paper, we investigate and compare hand-crafted and random feature representation for human action recognition on YouTube dataset. The former is built on 3D HoG/HoF and SIFT descriptors while the latter bases ...

Deep convolutional neural networks (CNNs) have demonstrated dominant performance in person reidentification (Re-ID). Existing CNN based methods utilize global average pooling (GAP) to aggregate intermediate convolutional features for Re-ID. However, this strategy only considers the first-order statistics of local features and treats local features at different locations equally important, leadi...