Abstract-Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.
The feature-based visualization method can separate important areas for users from flow field data, which can better highlight the feature structure. However, most of the current feature extraction methods are only applicable to single typical features, and they need complex mathematical analysis. Based on the above reasons, this paper proposes a universal feature visualization method, recognizes demand in the region of flow data, shows the characteristics of structure protruding from the global visual effect in the design of a multi-dimension parallel convolution kernel that contains the recognition model, and further puts forward the method of feature visualization based on a convolutional neural network. Compared with the classical three level BP neural network model, our model gets a high accuracy rate. We verify the effectiveness of the method and solve the problem of insufficient expansion of existing methods.
Psychology-grounded research on heuristics and biases in decision making has become increasingly influential in the field of management studies. However, although this line of inquiry is recognized as a valuable perspective for advancing understanding of decision processes in the upper echelons of firms, extant research remains unbalanced, the bulk of previous endeavours having been focused on managerial overconfidence, with insights from more recent dual-process theory and ecological rationality conceptions of heuristics less explored. This introductory article to the special issue of the Journal of Management Studies, entitled 'the heuristics and biases of top managers: Past, present, and future', offers a reflective review of prior work addressing its focal theme and places the articles incorporated into the special issue within this broader context. In addition, it sets out a number of directions for future work, with a view to inspiring the continuing advancement of conceptual and empirical knowledge and management practice.
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.