No abstract

We consider the problem of human parsing with partbased models. Most previous work in part-based models only considers rigid parts (e.g. torso, head, half

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with finegrained labels that describe major components, coarsegrained labels that depict high level abstraction, or a set of labels that reveal attributes. Such categorization at different concept layers can be modeled with label graphs encoding label information. In this paper, we exploit this rich information with a state-of-art deep learning framework, and propose a generic structured model that leverages diverse label relations to improve image classification performance. Our approach employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. We evaluate our method on benchmark image datasets, and empirical results illustrate the efficacy of our model.

No abstract

The SARC-F scale can identify old Chinese people with impaired physical function who may suffered from sarcopenia. SARC-F judgment reflects fear of falling, indicates the hospitalization events and is associated with ability of daily life. Thus, SARC-F may be a simple and useful tool for screening individuals with impaired physical function. Further studies on SARC-F in Chinese people would be worthy.