Abstract ：

Organizing webpages into hot topics is one of the key steps to understand the trends from multi-modal web data. To handle this pressing problem, Poisson Deconvolution (PD), a state-of-the-art method, recently is proposed to rank the interestingness of web topics on a similarity graph. Nevertheless, in terms of scalability, PD optimized by expectation-maximization is not sufficiently efficient for a large-scale data set. In this paper, we develop a Stochastic Poisson Deconvolution (SPD) to deal with the large-scale web data sets. Experiments demonstrate the efficacy of the proposed approach in comparison with the state-of-the-art methods on two public data sets and one large-scale synthetic data set. © 2019, Springer Nature Switzerland AG.

Keyword ：

Maximum principle Maximum principle Stochastic systems Stochastic systems

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Organizing webpages into interesting topics is one of the key steps to understand the trends from multimodal Web data. The sparse, noisy, and less-constrained user-generated content results in inefficient feature representations. These descriptors unavoidably cause that a detected topic still contains a certain number of the false detected webpages, which further make a topic be less coherent, less interpretable, and less useful. In this paper, we address this problem from a viewpoint interpreting a topic by its prototypes, and present a two-step approach to achieve this goal. Following the detection-by-ranking approach, a sparse Poisson deconvolution is proposed to learn the intratopic similarities between webpages. To find the prototypes, leveraging the intratopic similarities, top-k diverse yet representative prototype webpages are identified from a submodularity function. Experimental results not only show the improved accuracies for the Web topic detection task, but also increase the interpretation of a topic by its prototypes on two public datasets.

Keyword ：

Poisson deconvolution Poisson deconvolution sparsity sparsity Web topic detection Web topic detection submodularity submodularity prototype learning (PL) prototype learning (PL) topic interpretation topic interpretation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Bus arrival time prediction intends to improve the level of the services provided by transportation agencies. Intuitively, many stochastic factors affect the predictability of the arrival time, e.g., weather and local events. Moreover, the arrival time prediction for a current station is closely correlated with that of multiple passed stations. Motivated by the observations above, this paper proposes to exploit the long-range dependencies among the multiple time steps for bus arrival prediction via recurrent neural network (RNN). Concretely, RNN with long short-term memory block is used to "correct" the prediction for a station by the correlated multiple passed stations. During the correlation among multiple stations, one-hot coding is introduced to fuse heterogeneous information into a unified vector space. Therefore, the proposed framework leverages the dynamic measurements (i.e., historical trajectory data) and the static observations (i.e., statistics of the infrastructure) for bus arrival time prediction. In order to fairly compare with the state-of-the-art methods, to the best of our knowledge, we have released the largest data set for this task. The experimental results demonstrate the superior performances of our approach on this data set.

Keyword ：

multi-step-ahead prediction multi-step-ahead prediction long-range dependencies long-range dependencies recurrent neural network recurrent neural network heterogenous measurement heterogenous measurement Bus arriving time prediction Bus arriving time prediction

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Organizing multimodal Web pages into hot topics is the core step to grasp trends on the Web. However, the less-constrained social media generate noisy user-generated content, which makes a detected topic be less coherent and less interpretable. In this paper, we address this problem by proposing a coupled Poisson deconvolution to jointly handle topic detection and topic description. For the topic detection, the interestingness of a topic is estimated from the similarities refined by the description of topics; for the topic description, the interestingness of topics is leveraged to describe topics. Two processes cyclically detect interesting topics and generate the multimodal description of topics. This is the innovation of this paper, which just likes killing two birds with one stone. Experiments not only show the significantly improved accuracies for the topic detection but also demonstrate the interpretable descriptions for the topic description on two public data sets.

Keyword ：

Multimodal description Multimodal description Poisson deconvolution (PD) Poisson deconvolution (PD) topic coherent topic coherent topic detection on Web topic detection on Web topic description topic description

Cite：

Copy from the list or Export to your reference management。

Abstract ：

As increasing volumes of urban data are being available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based policies. In particular, taxi trip is an important urban sensor that provides unprecedented insights into many aspects of a city, from economic activity, human mobility to land development. However, analyzing these data presents many challenges, e.g., sparse data for fine-grained patterns, and the regularity submerged by seemingly random data. Inspired by above challenges, we focus on Pick-Up (PU)/Drop-Off (DO) points from taxi trips, and propose a fine-grained approach to unveil a set of low spatio-temporal patterns from the regularity-discovered intensity. The proposed method is conceptually simple yet efficient, by leveraging point process to handle sparsity of points, and by decomposing point intensities into the low-rank regularity and the factorized basis patterns, our approach enables domain experts to discover patterns that are previously unattainable for them, from a case study motivated by traffic engineers.

Keyword ：

taxis trip taxis trip low-rank regularity low-rank regularity matrix factorization matrix factorization fine-grained pattern fine-grained pattern Spatio-temporal pattern Spatio-temporal pattern point process point process

Cite：

Copy from the list or Export to your reference management。

Abstract ：

To quickly grasp what interesting topics are happening on web, it is challenge to discover and describe topics from User-Generated Content (UGC) data. Describing topics by probable keywords and prototype images is an efficient human-machine interaction to help person quickly grasp a topic. However, except for the challenges from web topic detection, mining the multi-media description is a challenge task that the conventional approaches can barely handle: (1) noises from non-informative short texts or images due to less-constrained UGC; and (2) even for these informative images, the gaps between visual concepts and social ones. This paper addresses above challenges from the perspective of background similarity remove, and proposes a two-step approach to mining the multi-media description from noisy data. First, we utilize a devcovolution model to strip the similarities among non-informative words/images during web topic detection. Second, the background-removed similarities are reconstructed to identify the probable keywords and prototype images during topic description. By removing background similarities, we can generate coherent and informative multi-media description for a topic. Experiments show that the proposed method produces a high quality description on two public datasets. (C) 2017 Elsevier B.V. All rights reserved.

Keyword ：

Topic detection Topic detection Poisson deconvolution Poisson deconvolution Multi-modal description Multi-modal description User-Generated Content User-Generated Content Topic description Topic description Background similarity Background similarity

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Inspired by the photometric invariance of color space, this paper proposes a simple yet powerful descriptor for object detection and recognition, called Rotative Maximal Pattern (RMP). The effectiveness of RMP comes from the two components: Rotatable Couple Templates (RCTs) with max pooling, and Normalized Histogram Intersection (NHI) with the theoretical guarantee. More concretely, RCTs are the combination of two templates to code the possible rotations. NHI serves as the similarity between two color histograms. We have conducted extensive experiments on INRIA pedestrian and Pascal VOC2007 data sets for object detection tasks; we also show that our approach leads to a promising performance on Caltech 101, Scene 15, UIUCsport and Stanford 40 action data sets. (C) 2017 Published by Elsevier Inc.

Keyword ：

Max pooling Max pooling Photometric invariance Photometric invariance Object recognition Object recognition Translation invariance Translation invariance Self similarity Self similarity Object detection Object detection

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Recently top performing cross-media topic detection employs Similarity Diffusion Process (SDP) to rank the interestingness of topics from a large number of candidates. SDP models the polysemous phenomenon from short and less-constrained user-generated data by assuming the similarities between two multi-media data should be divided into intersected topics. The noise in SDP plays an important role to explain the generation of the similarity. However, it is unclear what kind of noise is more appropriate for different modalities in cross media: SDP under different noises should has the lower false positives when topics are successfully detected. In this paper, we provide an in depth analysis of two types of noises (Poisson and Gaussian) for this task. In the evaluation, we observe that the combination of Poisson noise and topic sizes performs best while Gaussian noise has a faster optimization speed than that of Poisson one.

Keyword ：

Deconvolution Deconvolution Poisson noise Poisson noise Similarity Diffusion Process Similarity Diffusion Process Gaussian noise Gaussian noise Unsupervised ranking Unsupervised ranking

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Convolutional Neural Networks (CNNs) have delivered impressive state-of-the-art performances for many vision tasks, while the computation costs of these networks during test-time are notorious. Empirical results have discovered that CNNs have learned the redundant representations both within and across different layers. When CNNs are applied for binary classification, we investigate a method to exploit this redundancy across layers, and construct a cascade of classifiers which explicitly balances classification accuracy and hierarchical feature extraction costs. Our method cost-sensitively selects feature points across several layers from trained networks and embeds non-expensive yet discriminative features into a cascade. Experiments on binary classification demonstrate that our framework leads to drastic test-time improvements, e.g., possible 47.2x speedup for TRECVID upper body detection, 2.82x speedup for Pascal VOC2007 People detection, 3.72x for INRIA Person detection with less than 0.5% drop in accuracies of the original networks.

Keyword ：

Convolutional Neural Networks Convolutional Neural Networks cascade cascade binary classification binary classification cost-sensitive cost-sensitive accelerate accelerate feature selection feature selection

Cite：

Copy from the list or Export to your reference management。

Abstract ：

We proposed a novel model to predict human's visual attention when free-viewing webpages. Compared with natural images, webpages are usually full of salient regions such as logos, text, and faces, while few of them attract human's attention in a short sight. Moreover, webpages perform distinct viewing patterns which are quite different from the natural images In this paper, we introduced multi-features according to our observation on webpages characters and related eye-tracking data. Further, in order to achieve a flexible adaptation to various types of webpages, we employed a machine-learning framework based on our proposed features. Experimental results demonstrate that our model outperforms other state-of-the-art methods in webpage saliency prediction.

Keyword ：

Webpages viewing Webpages viewing Support vector machine Support vector machine Multi-features Multi-features Saliency Saliency

Cite：

Copy from the list or Export to your reference management。