Against the backdrop of the fierce competition in the market nowadays, a closed innovation model based on internal knowledge is no longer sufficient to support enterprises in search of high-performance innovation. Instead, corporations are desperately required to search for resources of external knowledge to meet their innovation goals. Existing studies on open innovation in corporate management failed to fully elaborate on the mechanism of how the external knowledge search could impose an impact on sustaining innovation and disruptive innovation. In this study, the external knowledge search was divided into three categories according to the knowledge-based theory, namely, the scientific knowledge search, the market knowledge search, and the supply-chain knowledge search. While taking into account the moderating role of the focus of attention of the manager, we analyzed the statistical results of 485 questionnaires collected from manufacturing enterprises to elaborate on the mechanism of how the specialized knowledge search could impose an impact on sustaining innovation and disruptive innovation. Our research conclusions are expected to enrich existing studies on the factors contributing to corporate innovation, including but not limited to sustaining innovation and disruptive innovation. In addition, the research findings are expected to lay an empirical foundation by summarizing previous theoretical opinions while providing references for subsequent in-depth studies in the meantime. Moreover, the paper has put forward practical management measures and suggestions that could enable enterprises in developing countries to search and effectively transform the external knowledge into innovative outcomes. Last but not least, this study is expected to provide both theoretical and practical guidance for enterprises to further facilitate innovation by means of knowledge search.
Recovering the geometry of an object from a single depth image is an interesting yet challenging problem. While previous learning based approaches have demonstrated promising performance, they don’t fully explore spatial relationships of objects, which leads to unfaithful and incomplete 3D reconstruction. To address these issues, we propose a
Spatial Relationship Preserving Adversarial Network (SRPAN)
consisting of
3D Capsule Attention Generative Adversarial Network (3DCAGAN)
and
2D Generative Adversarial Network (2DGAN)
for coarse-to-fine 3D reconstruction from a single depth view of an object. Firstly, 3DCAGAN predicts the coarse geometry using an encoder-decoder based generator and a discriminator. The generator encodes the input as latent capsules represented as stacked activity vectors with local-to-global relationships (i.e., the contribution of components to the whole shape), and then decodes the capsules by modeling local-to-local relationships (i.e., the relationships among components) in an attention mechanism. Afterwards, 2DGAN refines the local geometry slice-by-slice, by using a generator learning a global structure prior as guidance, and stacked discriminators enforcing local geometric constraints. Experimental results show that SRPAN not only outperforms several state-of-the-art methods by a large margin on both synthetic datasets and real-world datasets, but also reconstructs unseen object categories with a higher accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.