Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods. In this paper, we propose a learnable histogram layer, which learns histogram features within deep neural networks in end-to-end training. Such a layer is able to back-propagate (BP) errors, learn optimal bin centers and bin widths, and be jointly optimized with other layers in deep networks during training. Two vision problems, semantic segmentation and object detection, are explored by integrating the learnable histogram layer into deep networks, which show that the proposed layer could be well generalized to different applications. In-depth investigations are conducted to provide insights on the newly introduced layer.
The relationship between tourism and landscape has been extensively studied, but a conceptual framework to study cultural relationships between tourism and landscape is not specified in the literature. On the basis of the theory of social imaginary, this article takes China's Honghe Hani Terraces as an example to study how the landscape is imagined in tourism and the potential cultural conflicts. Content analysis on tourist discourses and images in social media was conducted in order to identify tourist imaginaries about the landscape. A gap between tourism imaginaries and the Hani landscape was found: the latter was imagined as an overlooking view of stereotyped terraced imagery, a schema separated and independent from other landscape components. In-depth interviews on stakeholders and participant observations were used to study the production process of tourism imaginaries. Findings show that the viewing platforms and roads provided an enclave space from local contexts, wherein the Hani landscape was staged for gazing. The tourism company's strategies dominated the process, leading to local communities' marginalization and threats to the landscape. We suggest that tourism planning and marketing should maintain the integrity of landscape in tourism imaginaries and empower the local communities, thereby reducing cultural tensions between tourism and the landscape.
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.