Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting...
详细信息
ISBN:
(纸本)9781467388528
Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Recent work has pursued this approach by exploring various ways of connecting the visual and text domains. In this paper, we revisit this idea by going further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This observation motivates us to design a simple yet effective zero-shot learning method that is capable of suppressing noise in the text. Specifically, we propose an l_(2,1)-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms those competing methods which rely on online information sources but with no explicit noise suppression. Furthermore, we make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning.
This paper introduces an optimization framework aimed at providing a theoretical foundation for a class of composite optimization problems, particularly those encountered in deep learning. In this framework, we introd...
详细信息
In this paper, we describe the challenges involved in designing a family of highly-efficient Breadth-First Search (BFS) algorithms and in optimizing these algorithms on the latest two generations of Blue Gene machines...
详细信息
ISBN:
(纸本)9781467308052
In this paper, we describe the challenges involved in designing a family of highly-efficient Breadth-First Search (BFS) algorithms and in optimizing these algorithms on the latest two generations of Blue Gene machines, Blue Gene/P and Blue Gene/Q. With our recent winning Graph 500 submissions in November 2010, June 2011, and November 2011, we have achieved unprecedented scalability results in both space and size. On Blue Gene/P, we have been able to parallelize a scale 38 problem with 2~(38) vertices and 2~(42) edges on 131,072 processing cores. Using only four racks of an experimental configuration of Blue Gene/Q, we have achieved a processing rate of 254 billion edges per second on 65,536 processing cores. This paper describes the algorithmic design and the main classes of optimizations that we have used to achieve these results.
Dense local trajectories have been successfully used in action recognition. However, for most actions only a few local motion features (e.g., critical movement of hand, arm, leg etc.) are responsible for the action la...
详细信息
ISBN:
(纸本)9781467369657
Dense local trajectories have been successfully used in action recognition. However, for most actions only a few local motion features (e.g., critical movement of hand, arm, leg etc.) are responsible for the action label. Therefore, highlighting the local features which are associated with important motion parts will lead to a more discriminative action representation. Inspired by recent advances in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mine for discriminative groups of dense trajectories which form important motion parts. First, motion part candidates are generated by spatio-temporal grouping of densely extracted trajectories. Second, an objective function which encourages sparse selection for these trajectory groups is formulated together with an action class discriminative term. Then, we propose an alternative optimization algorithm to efficiently solve this objective function by introducing a set of auxiliary variables which correspond to the discriminativeness weights of each motion part (trajectory group). These learned motion part weights are further utilized to form a discriminativeness weighted Fisher vector representation for each action sample for final classification. The proposed motion part regularization framework achieves the state-of-the-art performances on several action recognition benchmarks.
Query optimization has become a research area where classical algorithms are being challenged by machine learning algorithms. At the same time, recent trends in learned query optimizers have shown that it is prudent t...
详细信息
In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model...
详细信息
ISBN:
(纸本)9781467369657
In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogenous multi-task learning. The proposed model in an unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to enable the multi-task classifier learning, and 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces. To efficiently train the joint model, a three-step iterative optimization algorithm is proposed, followed by two inference models. Extensive results on three activity datasets have demonstrated the efficacy of the proposed method. In addition, a novel RGB-D activity dataset focusing on human-object interaction is collected for evaluating the proposed method, which will be made available to the community for RGB-D activity benchmarking and analysis.
Nowadays, there is a large number of phasor measurement units (PMU) installed in the power systems, which together form Wide Area Measurement System (WAMS). With a high accuracy, PMU measure complex current and voltag...
详细信息
ISBN:
(纸本)9781728163826
Nowadays, there is a large number of phasor measurement units (PMU) installed in the power systems, which together form Wide Area Measurement System (WAMS). With a high accuracy, PMU measure complex current and voltage values in the installation sites. Previously [1, 2] the possibility of using PMU measurements for determining automatic excitation controller (AEC) parameters of synchronous generator using optimization algorithms was shown. However, the searching for the best optimization method for this issue has not still finished. That is why it would be reasonable to research the capability of neural networks application. At present, we can see a great interest in artificial neural networks. They are implemented in many fields of human life.
Aiming at the problem that traditional bearing fault diagnosis methods rely on artificial feature extraction and expert experience, this paper proposes an adaptive bearing fault diagnosis method based on two-dimension...
详细信息
ISBN:
(数字)9781728144603
ISBN:
(纸本)9781728144610
Aiming at the problem that traditional bearing fault diagnosis methods rely on artificial feature extraction and expert experience, this paper proposes an adaptive bearing fault diagnosis method based on two-dimensional convolutional neural network. In order to retain the features of the original fault data to the greatest extent, the original signal is directly used as the input, and the two-dimensional convolutional neural network fault diagnosis model is used to perform adaptive hierarchical feature extraction, and optimization algorithms are used to improve the performance of the test set. The experimental results show that this method can achieve a fault recognition rate of more than 99% on the bearing data set, and shows good generalization performance under different loads, which is feasible for practical applications.
We study the convex hull membership (CHM) problem in the pure exploration setting where one aims to efficiently and accurately determine if a given point lies in the convex hull of means of a finite set of distributio...
详细信息
We consider stochastic optimization problems with non-convex functional constraints, such as those arising in trajectory generation, sparse approximation, and robust classification. To this end, we put forth a recursi...
详细信息
暂无评论