Fast online learning algorithm for landmark recognition based on BoW framework

Cao, Jiuwen; Chen, Tao; Fan, Jianchao

doi:10.1109/iciea.2014.6931341

Cited by 44 publications

(40 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, learning two models simultaneously is quite difficult and inefficient because we need to adjust parameters in two models iteratively, such that it cannot be applied to online and real-time applications. But fortunately, this threelevel (feature-attribute-event) framework can be formulated as an extreme learning machine (ELM) [25,[47][48][49] which is a variant of artificial neural network (ANN), where feature is the input layer, attribute is the hidden layer, and event is the output layer. In the theory of ELM, the parameters between input layer and hidden layer can be totally random; that is, we actually do not need to learn these parameters from the training data.…”

Section: Detection Via Elm-based Visualmentioning

confidence: 99%

Anomaly Detection via Midlevel Visual Attributes

Tan

Zhang

Zha

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Automatically discovering anomalous events and objects from surveillance videos plays an important role in real-world application and has attracted considerable attention in computer vision community. However it is still a challenging issue. In this paper, a novel approach for automatic anomaly detection is proposed. Our approach is highly efficient; thus it can perform real-time detection. Furthermore, it can also handle multiscale detection and can cope with spatial and temporal anomalies. Specifically, local features capturing both appearance and motion characteristics of videos are extracted from spatiotemporal video volume (STV). To bridge the large semantic gap between low-level visual feature and high-level event, we use the middle-level visual attributes as the intermediary. And these three-level framework is modeled as an extreme learning machine (ELM). We propose to use the spatiotemporal pyramid (STP) to capture the spatial and temporal continuity of an anomalous even, enabling our approach to cope with multiscale and complicated events. Furthermore, we propose a method to efficiently update the ELM; thus our approach is self-adaptive to background change which often occurs in real-world application. Experiments on several datasets are carried out and the superior performance of our approach compared to the state-of-the-art approaches verifies its effectiveness.

show abstract

Section: Detection Via Elm-based Visualmentioning

confidence: 99%

Anomaly Detection via Midlevel Visual Attributes

Tan

Zhang

Zha

2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…ELM was originally proposed for classification and regression. It has several salient features: efficient, accurate and can be implemented easily (Butcher, Verstraeten, Schrauwen, Day, & Haycock, 2013;Huang, Huang, Song, & You, 2015;Huang, Zhou, Ding, & Zhang, 2012;Liu, Gao, & Li, 2012), and has been widely used in various applications (Cao, Chen, & Fan, 2014Cao & Xiong, 2014;Shi, Cai, Zhu, Zhong, & Wang, 2013). Extending ELM for clustering has been addressed in several existing works.…”

Section: Introductionmentioning

confidence: 98%

Discriminative clustering via extreme learning machine

et al. 2015

View full text Add to dashboard Cite

“…With the random assignments on the input weights, the output weights of ELMs can be directly determined by solving a linear least square problem, which bears similarities to designing the output weights of a radial basis function (RBF) network [37], [38] or neural networks with other activation functions [39], [40]. Besides, some other typical work on ELMs include using evolutionary strategy to optimize the input weights such that a compact ELM can be obtained [41], ELMs with sparse representation [42], integrating fuzzy logic with ELMs to improve the approximation performance [43], employing an ensemble of classifiers with the ELM as the base for performance improvement [44], applications of ELM for effective recognition of landmarks [45], [46], and insightful interpretation of ELMs from the perspective of random neurons, random features, and kernels [47].…”

Section: Introductionmentioning

confidence: 99%

Inverse-Free Extreme Learning Machine With Optimal Information Updating

You

Guo

et al. 2016

IEEE Trans. Cybern.

118

View full text Add to dashboard Cite

The extreme learning machine (ELM) has drawn insensitive research attentions due to its effectiveness in solving many machine learning problems. However, the matrix inversion operation involved in the algorithm is computational prohibitive and limits the wide applications of ELM in many scenarios. To overcome this problem, in this paper, we propose an inverse-free ELM to incrementally increase the number of hidden nodes, and update the connection weights progressively and optimally. Theoretical analysis proves the monotonic decrease of the training error with the proposed updating procedure and also proves the optimality in every updating step. Extensive numerical experiments show the effectiveness and accuracy of the proposed algorithm.

show abstract

Fast online learning algorithm for landmark recognition based on BoW framework

Cited by 44 publications

References 21 publications

Anomaly Detection via Midlevel Visual Attributes

Anomaly Detection via Midlevel Visual Attributes

Discriminative clustering via extreme learning machine

Inverse-Free Extreme Learning Machine With Optimal Information Updating

Contact Info

Product

Resources

About