Peng, HongWang, HaiyanHu, YuZhou, Weiwei...
10页查看更多>>摘要：Clustering objects with heterogeneous attributes captured from different dimensions remains challenging in integrating the multiple dimensional information. Most of the current multi-dimensional clustering models pin on direct sample-wised similarity and fail to exploit hidden mutual affinity among different sampling spaces. Thus, it is hard to capture a legible cluster structure. To tackle this issue, we propose a High-order multi-dimensional Spectral Clustering method (HSC). The proposed HSC aims to learn a high order similarity to characterize the intrinsic relationship among different dimensional spaces instead of the ordinary similarity. It then performs a clustering task within a latent space by jointly learning the high-order similarity and ordinary similarity. Extensive experiments over synthetic and real-world data sets show that the proposed HSC outperforms benchmark multi-dimensional methods in most scenarios and is capable of revealing a reliable structure concealed across multi-dimensional spaces. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:
NSTL
Elsevier
V'yugin, VladimirTrunov, Vladimir
12页查看更多>>摘要：The paper presents numerical experiments and some theoretical developments in prediction with expert advice (PEA). One experiment deals with predicting electricity consumption depending on temperature and uses real data. As the pattern of dependence can change with season and time of the day, the domain naturally admits PEA formulation with experts having different "areas of expertise". We consider the case where several competing methods produce online predictions in the form of probability distribution functions. The dissimilarity between a probability forecast and an outcome is measured by a loss function (scoring rule). A popular example of scoring rule for continuous outcomes is Continuous Ranked Probability Score ( CRPS ). In this paper the problem of combining probabilistic forecasts is considered in the PEA framework. We show that CRPS is a mixable loss function and then the time-independent upper bound for the regret of the Vovk aggregating algorithm using CRPS as a loss function can be obtained. Also, we incorporate a "smooth" version of the method of specialized experts in this scheme which allows us to combine the probabilistic predictions of the specialized experts with overlapping domains of their competence. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Xiao, JiangLi, HuichuwuJin, Hai
12页查看更多>>摘要：Individual diversity poses a cross-user performance variance challenge that stumbles the practicality, especially for the wireless gesture tracking systems. Since the difficulty of annotating low-semantic wireless data limits constructing a big dataset, the recognizer should quickly adjust to different individuals via small datasets. To this end, we present TransTrack, an accurate wireless indoor gesture tracking system that can adjust to different users quickly. The key insight is that each unlabeled gesture contains learnable individual features that can help the gesture tracking model learning how to adapt to different users. Specifically, TransTrack uses recursive Otsu segmentation to separate gesture-induced signals with the background noise inspired by image segmentation. It then augments training data to learn the transferable features by leveraging the redundant information. A datum-based alignment method is proposed to unlock the limitation of classifier selection without distortion. Finally, TransTrack proposes an online meta-transfer learning method that collects unlabeled data transparently to train the tracking model for different tasks. Extensive experiments show that TransTrack can quickly adapt to different users and conditions. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Vaquero, LorenzoBrea, Victor M.Mucientes, Manuel
12页查看更多>>摘要：Most video analytics applications rely on object detectors to localize objects in frames. However, when real-time is a requirement, running the detector at all the frames is usually not possible. This is somewhat circumvented by instantiating visual object trackers between detector calls, but this does not scale with the number of objects. To tackle this problem, we present SiamMT, a new deep learning multiple visual object tracking solution that applies single-object tracking principles to multiple arbitrary objects in real -time. To achieve this, SiamMT reuses feature computations, implements a novel crop-and-resize operator, and defines a new and efficient pairwise similarity operator. SiamMT naturally scales up to several dozens of targets, reaching 25 fps with 122 simultaneous objects for VGA videos, or up to 100 simultaneous objects in HD720 video. SiamMT has been validated on five large real-time benchmarks, achieving leading performance against current state-of-the-art trackers. (c) 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
原文链接:- NSTL
- Elsevier
Wang, JieLiang, JiyeYao, KaixuanLiang, Jianqing...
12页查看更多>>摘要：Recently, graph representation learning based on autoencoders has received much attention. However, these methods suffer from two limitations. First, most graph autoencoders ignore the reconstruction of either the graph structure or the node attributes, which often leads to a poor latent representation of the graph-structured data. Second, for existing graph autoencoders models, the encoder and decoder are mainly composed of an initial graph convolutional network (GCN) or its variants. These traditional GCN-based graph autoencoders more or less encounter the problem of incomplete filtering, which causes these models to be unstable in practical applications. To address the above issues, this paper proposes the Graph convolutional Autoencoders with co-learning of graph Structure and Node attributes (GASN) based on variational autoencoders. Specifically, the proposed GASN encodes and decodes the node attributes and graph structure comprehensively in the graph-structured data. Furthermore, we design a completely low-pass graph encoder and a high-pass graph decoder. The experimental results on real-world datasets demonstrate that the proposed GASN achieves state-of-the-art performance on node clustering, link prediction, and visualization tasks. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Mokoena, TshepisoCelik, TurgayMarivate, Vukosi
14页查看更多>>摘要：In most applications, anomaly detection operates in an unsupervised mode by looking for outliers hoping that they are anomalies. Unfortunately, most anomaly detectors do not come with explanations about which features make a detected outlier point anomalous. Therefore, it requires human analysts to manually browse through each detected outlier point's feature space to obtain the subset of features that will help them determine whether they are genuinely anomalous or not. This paper introduces sequential explanation (SE) methods that sequentially explain to the analyst which features make the detected outlier anomalous. We present two methods for computing SEs called the outlier and sample-based SE that will work alongside any anomaly detector. The outlier-based SE methods use an anomaly detector's outlier scoring measure guided by a search algorithm to compute the SEs. Meanwhile, the sample-based SE methods employ sampling to turn the problem into a classical feature selection problem. In our experiments, we compare the performances of the different outlier-and sample-based SEs. Our results show that both the outlier and sample-based methods compute SEs that perform well and outperform sequential feature explanations. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Feng, ShiboXu, ChenZuo, YuChen, Guo...
12页查看更多>>摘要：The inherent properties of the graph structure of the financial market and the correlation attributes that actually exist in the system inspire us to introduce the concept of the graph to solve the problem of prediction and recommendation in the financial sector. In this paper, we are adhering to the idea of recommending high return ratio stocks and put forward an attributed graph attention network model based on the correlation information, with encoded timing characteristics derived from time series module and global information originating from the stacked graph neural network(GNN) based models, which we called Relation-aware Dynamic Attributed Graph Attention Network (RA-AGAT). On this basis, we have verified the practicality and applicability of the application of graph models in finance. Our innovative structure first captures the local correlation topology information and then introduce a stacked graph neural network structure to recommend Top-N return ratio of stock items. Experiments on the real China A-share market demonstrate that the RA-AGAT architecture is capable of surpassing the previously applicable methods in the prediction and recommendation of stock return ratio. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Tavakkol, BehnamChoi, JeongsubJeong, Myong KeeAlbin, L. Susan...
14页查看更多>>摘要：Clustering validity indices are typically used as tools to find the correct number of clusters in a data set and/or to evaluate the quality of the clusters formed by clustering algorithms. Clustering validity in-dices measure separation and compactness of clusters. Typically, when applying a clustering algorithm, the input includes the number of clusters. After applying the algorithm with several different numbers of clusters, we determine the number of clusters to be the one with the best validity index. There are two types of clustering validity indices: external indices that are supervised, and internal indices that are un-supervised. The focus of this paper is on internal validity indices. Some existing internal validity indices capture the properties of the clusters by using representative statistics such as mean, variance, diameter, etc., however, these do not perform well when clusters have arbitrary shapes. One approach to overcome this issue is to use the density of the data objects in each cluster. That provides the advantage of captur-ing the full characteristics of the cluster which is most beneficial when there are clusters with arbitrary shapes. In the literature, a few density-based clustering validity indices have been proposed. However, some of them show poor performance when the clusters are not perfectly separated. Some others per-form poorly because they use only representative objects from each cluster instead of all objects. The contribution of this paper is an internal validity index named the object-based clustering validity index with densities (OCVD). OCVD is a single number that averages the density-based contribution of individ-ual data objects to both separation and compactness of clusters. The methodology behind calculating the density-based contributions of the objects is kernel density estimation. We show through several exper-iments that OCVD performs well in detecting the correct number of clusters in data sets with different cluster shapes including arbitrary shapes. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
Peng, YifanHe, ZijianWen, ChengluCheng, Ming...
12页查看更多>>摘要：To recover relative camera motion accurately and robustly, establishing a set of point-to-point correspon-dences in the pixel space is an essential yet challenging task in computer vision. Even though multi-scale design philosophy has been used with significant success in computer vision tasks, such as object de-tection and semantic segmentation, learning-based image matching has not been fully exploited. In this work, we explore a scale awareness learning approach in finding pixel-level correspondences based on the intuition that keypoints need to be extracted and described on an appropriate scale. With that in -sight, we propose a novel scale-aware network and then develop a new fusion scheme that derives high-consistency response maps and high-precision descriptions. We also revise the Second Order Similarity Regularization (SOSR) to make it more effective for the end-to-end image matching network, which leads to significant improvement in local feature descriptions. Experimental results run on multiple datasets demonstrate that our approach performs better than state-of-the-art methods under multiple criteria. (c) 2021 Elsevier Ltd. All rights reserved.
原文链接:- NSTL
- Elsevier
