High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks ...first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet .
Cultural geography is once again concerned with representations. In this report I focus on how, in the wake of various non-representational theories, recent work stays with what texts, images, words, ...and other representations do. I argue that this work is animated by a concern with the force of representations: their capacities to affect and effect, to make a difference. Accompanying this orientation to questions of force is a shift in the unit of analysis to ‘representations-in-relation’ and a multiplication of the modes of analysis through which cultural geography is performed, including the emergence of reparative and descriptive modes.
Learning discriminative feature representations has shown remarkable importance due to its promising performance for machine learning problems. This paper presents a discriminative data ...representation learning framework by employing a simple yet powerful marginal regression function with probabilistic graphical structure adaptation. A marginally structured representation learning (MSRL) method is proposed by seamlessly incorporating distinguishable regression targets analysis, graph structure adaptation, and robust linear structural learning into a joint framework. Specifically, MSRL learns marginal regression targets from data rather than exploiting the conventional zero-one matrix that greatly hinders the freedom of regression fitness and degrades the performance of regression results. Meanwhile, an optimized graph regularization term with self-improving adaptation is constructed based on probabilistic connection knowledge to improve the compactness of the learned representation. Additionally, the regression targets are further predicted by utilizing the explanatory factors from the latent subspace of data, which can uncover the underlying feature correlations to enhance the reliability. The resulting optimization problem can be elegantly solved by an efficient iterative algorithm. Finally, the proposed method is evaluated by eight diverse but related tasks, including object, face, texture, and scene, categorization data sets. The encouraging experimental results and the explicit theoretical analysis demonstrate the efficacy of the proposed representation learning method in comparison with state-of-the-art algorithms.
This study analyzes the self-representations of Russian-speaking women with anorexia on YouTube. Using multimodal interaction analysis, the research focuses on how the explanatory model of anorexia ...and the representation platform influence the narratives produced by vloggers who have experienced or are experiencing anorexia. It is concluded that anorexia is mainly represented in these videos as a weight-related mental health disorder. Although the explanatory model of anorexia shapes self-representations on YouTube, the platform plays an even greater role in the construction of such narratives. This study’s findings fill gaps in the existing literature by revealing the joint structural influences that shape storytelling regarding the anorexia experience. The theoretical perspective utilized in this article could be further applied in research examining media representations of other mental health conditions.
Graphs naturally appear in numerous application domains, ranging from social analysis, bioinformatics to computer vision. The unique capability of graphs enables capturing the structural relations ...among data, and thus allows to harvest more insights compared to analyzing data in isolation. However, it is often very challenging to solve the learning problems on graphs, because (1) many types of data are not originally structured as graphs, such as images and text data, and (2) for graph-structured data, the underlying connectivity patterns are often complex and diverse. On the other hand, the representation learning has achieved great successes in many areas. Thereby, a potential solution is to learn the representation of graphs in a low-dimensional Euclidean space, such that the graph properties can be preserved. Although tremendous efforts have been made to address the graph representation learning problem, many of them still suffer from their shallow learning mechanisms. Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems. In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models. First, we group the existing graph convolutional network models into two categories based on the types of convolutions and highlight some graph convolutional network models in details. Then, we categorize different graph convolutional networks according to the areas of their applications. Finally, we present several open challenges in this area and discuss potential directions for future research.
We prove a characterization of monomial projective representations of finitely generated nilpotent groups. We also characterize polycyclic groups whose projective representations are finite ...dimensional.
•Study of the impact of the implicit aspects of knowledge graphs for cross-language plagiarism detection.•We present a new weighting scheme for relations between concepts based on distributed ...representations of concepts.•We obtain state-of-the-art performance compared to several state-of-the-art models.
Cross-language plagiarism detection aims to detect plagiarised fragments of text among documents in different languages. In this paper, we perform a systematic examination of Cross-language Knowledge Graph Analysis; an approach that represents text fragments using knowledge graphs as a language independent content model. We analyse the contributions to cross-language plagiarism detection of the different aspects covered by knowledge graphs: word sense disambiguation, vocabulary expansion, and representation by similarities with a collection of concepts. In addition, we study both the relevance of concepts and their relations when detecting plagiarism. Finally, as a key component of the knowledge graph construction, we present a new weighting scheme of relations between concepts based on distributed representations of concepts. Experimental results in Spanish–English and German–English plagiarism detection show state-of-the-art performance and provide interesting insights on the use of knowledge graphs.
With the explosive growth of online information, recommender systems play a key role to alleviate such information overload. Due to the important application value of recommender systems, there have ...always been emerging works in this field. In recommender systems, the main challenge is to learn the effective user/item representations from their interactions and side information (if any). Recently, graph neural network (GNN) techniques have been widely utilized in recommender systems since most of the information in recommender systems essentially has graph structure and GNN has superiority in graph representation learning. This article aims to provide a comprehensive review of recent research efforts on GNN-based recommender systems. Specifically, we provide a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks. Moreover, we systematically analyze the challenges of applying GNN on different types of data and discuss how existing works in this field address these challenges. Furthermore, we state new perspectives pertaining to the development of this field. We collect the representative papers along with their open-source implementations in https://github.com/wusw14/GNN-in-RS.