Image semantic segmentation is the task of partitioning image into several regions based on semantic concepts. In this paper, we learn a weakly supervised semantic segmentation model from social images whose labels are not pixellevel but image-level; furthermore, these labels might be noisy. We present a joint conditional random field model leveraging various contexts to address this issue. More specifically, we extract global and local features in multiple scales by convolutional neural network and topic model. Inter-label correlations are captured by visual contextual cues and label co-occurrence statistics. The label consistency between image-level and pixel-level is finally achieved by iterative refinement. Experimental results on two realworld image datasets PASCAL VOC2007 and SIFT-Flow demonstrate that the proposed approach outperforms stateof-the-art weakly supervised methods and even achieves accuracy comparable with fully supervised methods. bridge river sky tree Weakly Labeled Social Images sky field tree field sky tree Traditional Semantic Segmentation System
Knowledge graph completion can make knowledge graphs more complete, which is a meaningful research topic. However, the existing methods do not make full use of entity semantic information. Another challenge is that a deep model requires large-scale manually labelled data, which greatly increases manual labour. In order to alleviate the scarcity of labelled data in the field of cultural relics and capture the rich semantic information of entities, this paper proposes a model based on the Bidirectional Encoder Representations from Transformers (BERT) with entity-type information for the knowledge graph completion of the Chinese texts of cultural relics. In this work, the knowledge graph completion task is treated as a classification task, while the entities, relations and entity-type information are integrated as a textual sequence, and the Chinese characters are used as a token unit in which input representation is constructed by summing token, segment and position embeddings. A small number of labelled data are used to pre-train the model, and then, a large number of unlabelled data are used to fine-tune the pre-training model. The experiment results show that the BERT-KGC model with entity-type information can enrich the semantics information of the entities to reduce the degree of ambiguity of the entities and relations to some degree and achieve more effective performance than the baselines in triple classification, link prediction and relation prediction tasks using 35% of the labelled data of cultural relics.
Geometry images parameterise a mesh with a square domain and store the information in a single chart. A one-to-one correspondence between the 2D plane and the 3D model is convenient for processing 3D models. However, the parameterised vertices are not all located at the intersection of the gridlines the existing geometry images. Thus, errors are unavoidable when a 3D mesh is reconstructed from the chart. In this paper, we propose parameterise surface onto a novel geometry image that preserves the constraint of topological neighbourhood information at integer coordinate points on a 2D grid and ensures that the shape of the reconstructed 3D mesh does not change from supplemented image data. We find a collection of edges that opens the mesh into simply connected surface with a single boundary. The point distribution with approximate blue noise spectral characteristics is computed by capacity-constrained delaunay triangulation without retriangulation. We move the vertices to the constrained mesh intersection, adjust the degenerate triangles on a regular grid, and fill the blank part by performing a local affine transformation between each triangle in the mesh and image. Unlike other geometry images, the proposed method results in no error in the reconstructed surface model when floating-point data are stored in the image. High reconstruction accuracy is achieved when the xyz positions are in a 16-bit data format in each image channel because only rounding errors exist in the topology-preserving geometry images, there are no sampling errors. This method performs one-to-one mapping between the 3D surface mesh and the points in the 2D image, while foldovers do not appear in the 2D triangular mesh, maintaining the topological structure. This also shows the potential of using a 2D image processing algorithm to process 3D models.
An improved back projection imaging algorithm for subsurface target detection is presented in this paper.Firstly, the characteristic of the scattering data at each time-delay curve in the traditional back projection imaging procedure is analyzed. Secondly, a weight factor is designed for each focal point and an improved back projection imaging algorithm is presented. Thirdly, the simulation of the improved imaging algorithm is processed. The imaging results of both the simulation data and the real ground penetrating radar data show the effectiveness of this imaging algorithm.
High-quality development of energy finance (HQDEF) is not only a key component of high-quality economic development, but also an important solution to the current difficulties of China’s energy industry, such as environmental pollution and supply security. This study first clarifies the connotation and mechanism of high-quality energy finance, and then uses static super-efficiency DEA model as well as dynamic Malmquist index to evaluate the HQDEF from the perspective of input and output. We find that the overall effect of the HQDEF is at a low level. The scale efficiency and technical efficiency are deviating, where the former (latter) continues to expand (decline). The dynamic Malmquist index shows a slight decline in the efficiency of the HQDEF. Further studies on five dimensions of the HQDEF show that innovation has the highest correlation with each new energy industry. Lacking of innovation is the main bottleneck that restricts the development of the current new energy industry. The correlations among different industries have a tendency of “symmetry” and “convergence.” Our study provides countermeasures and suggestions for the high-quality and stable development of China’s energy finance from the perspectives of optimizing the financial support structure, building a technological innovation platform, optimizing the industrial structure, rationally making green investments and open development.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.