Search

Stock price trend prediction is to seek profit maximum of stock investment by estimating future stock price tendency. Nevertheless, it is still a tough task due to noisy and non-stationary properties of stock market. Thus, it is important how to relieve such negative effects and to improve prediction accuracy. In this paper, we leverage four diverse local descriptors in short durations to alleviate noisy fluctuations of stock price. In detail, piecewise aggregate approximation (PAA) collects relatively stable average values; the derivatives of short-time series reflect the change ratio of stock price; the slope implies the short-time price trend; hog-1D aggregates different oriented gradients into histograms in a statistical fashion. They provide diverse and comprehensive cues about the stock price series across different aspects. Building upon such local descriptors, we propose a multi-scale local cues and hierarchical attention-based LSTM model (MLCA-LSTM) to capture the underlying price trend patterns. It has two advantages: 1) multi-scale information is further enriched by performing different scale sliding windows over stock price series to induce diverse local descriptors, 2) temporal dependency and multi-scale interactions are jointly attended and aggregated through the hierarchical attention mechanism and multi-branch LSTM structure. Experiments on the real stock price data confirm the efficacy of the proposed model as compared to the state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

Local descriptor is an important upstream component in computer vision tasks. Despite considerable advances with deep learning-based descriptors, recent descriptors are not robust enough to handle widespread viewpoint changes in image matching tasks such as localization and 3D reconstruction. In this study, SDNet, a robust descriptor utilizing spatial adversarial perturbations, trained with a novel dynamic probabilistic weighting loss to enhance performance under such challenges. First, to increase the robustness and generalization ability of the network across spatially transformed instances, a innovative module for generating hard negative samples via spatial adversarial perturbations is designed. By maximizing adversarial loss, this module generates more complex patches, significantly enhancing the geometric robustness of the descriptor. Importantly, this module integrates seamlessly with existing patch-based descriptors without necessitating extra training data. Second, to mitigate the imbalance in the matching relationship between generated positive and negative pairs, the label weighted triplet loss is proposed, which markedly improves descriptor performance. Third, a comprehensive theoretical analysis of preceding studies is carried out from a gradient perspective, and a probabilistic dynamic weighting approach that adaptively emphasizes weighting functions with higher likelihoods is proposed to improve training performance of the descriptor. Extensive experiments are carried out on mainstream datasets. These comprehensive experiments demonstrate the effectiveness of SDNet, and the proposed method achieves significant improvements on the UBC, HPatches and ETH datasets, outperforming current state-of-the-art methods. The code is available at https://github.com/webd111/sdnet. [ABSTRACT FROM AUTHOR]

• Strengthen the descriptor by effectively combing features at different levels of CNN. • Capture the spatial information of a local patch with spatial context pyramid. • Comparable performance with state-of-the-art and comprehensive ablation experiments. Despite that efforts have shifted to learning local descriptors with convolutional neural network (CNN) from hand-crafted realm, the inherent feature hierarchy within CNN has been rarely explored. To increase both the invariant and discriminative abilities of the CNN-based local descriptors by making use of the complementary representation powers of the feature maps at different levels of CNN, in this paper, we design a multi-level feature aggregation (MLFA) module to communicate information across pyramid levels effectively. Then, each level extracts a feature vector after feature fusion and the final descriptor concatenates these outputs. Moreover, to leverage the spatial structure within a local patch, we propose a novel spatial context pyramid (SCP) module to capture the spatial information. SCP is devised in a residual manner and only several additional parameters are introduced to the model. We implement our algorithm based on the HardNet framework and carry out comprehensive evaluation on the UBC Phototour, HPatches and ETH datasets. The experimental results demonstrate that the proposed method performs favorably against the state-of-the-art ones. Ablation study is also provided to show the effectiveness of each component. [ABSTRACT FROM AUTHOR]

In recent years, the binary feature descriptor has achieved great success in face recognition (FR) field, such as local binary pattern (LBP). It is well known that the high-dimensional feature representations can contain more discriminative information, therefore, it is natural for us to construct the high-dimensional binary feature for FR task. However, the high-dimensional representations would lead to high computational cost and overfitting. Therefore, an effective sparsity regularizer is necessary. In this paper, we introduce the sparsity constraint into the objective function of general binary codes learning framework, so that the problem of high computational cost and overfitting can be somehow solved. There are three main requirements in our objective function: First, we require that the high-dimensional binary codes have the minimized quantization loss compared with centered original data. Second, we require the projection matrices are sparse, so that the projection process would not take lots of computational resource even faced with high-dimensional original data. Third, for a mapping (hashing) function, the bit-independence and bit-balance are two excellent properties for generating discriminative binary codes. We also empirically show that the high-dimensional binary codes can obtain more discriminative ability by pooling process with an unsupervised clustering method. Therefore, a discriminative and low-cost Sparse Projection Matrix Binary Descriptors (SPMBD) is learned by the data-driven way. Extensive experimental results on four public datasets show that our SPMBD descriptor outperforms other existing face recognition algorithms and demonstrate the effectiveness and robustness of the proposed methods. [ABSTRACT FROM AUTHOR]

In recent years, local image descriptors based on histograms of oriented gradients (e.g., SIFT, DAISY) and intensity orders (e.g., LBP, LIOP) have been popular for the keypoint matching. However, by relying on the dominant orientation estimation or several pixels based interaction to achieve rotation invariance, these descriptors tend to be error-prone or noise-sensitive. Moreover, they represent features as histograms which are restricted to the low-order statistics. In this paper, we propose to use local second-order statistics with soft-pooling (L2SSP) for robust keypoint description. To this end, a feature set is first designed by modeling each pixel as local spatial-frequency patterns and local extremum patterns. Such a feature set is rotationally invariant, highly discriminative and also robust to noise. Then, a soft spatial binning is introduced to encode the gradient information in a rotation invariant way. Finally, the descriptor is constructed by concatenating all sub-descriptors which are obtained by pooling local features within each spatial bin via the second-order statistics (covariance matrix). The proposed local descriptor, i.e., L2SSP, has been extensively evaluated on the Oxford dataset and some synthesized image pairs. Experimental results demonstrate the superior performance of L2SSP over state-of-the-art methods under a variety of image transformations. The source code of L2SSP is publicly available at https://pan.baidu.com/s/1pLIVwLH#path=/%252Fl2ssp . [ABSTRACT FROM AUTHOR]

Binary feature descriptors have been widely used in computer vision field due to their excellent discriminative power and strong robustness, and local binary patterns (LBP) and its variations have proven that they are effective face descriptors. However, the forms of such binary feature descriptors are predefined in the hand-crafted way, which requires strong domain knowledge to design them. In this paper, we propose a simple and efficient iterative quantization binary codes (IQBC) feature learning method to learn a discriminative binary face descriptor in the data-driven way. Firstly, similar to traditional LBP method, we extract patch-wise pixel difference vectors (PDVs) by computing and concatenating the difference between center patch and its neighboring patches. Then, inspired by multi-class spectral clustering and the orthogonal Procrustes problem, which both are widely used in image retrieval field, we learn an optimized rotation to minimize the quantization error of mapping data to the vertices of a zero-centered binary hypercube by using iterative quantization scheme. In other words, we learn a feature mapping to project these pixel difference vectors into low-dimensional binary vectors. And our IQBC can be used with unsupervised data embedding method such as principle component analysis (PCA) and supervised data embedding method such as canonical correlation analysis (CCA), namely IQBC-PCA and IQBC-CCA. Lastly, we cluster and pool these projected binary codes into a histogram-based feature that describes the co-occurrence of binary codes. And we consider the histogram-based feature as our final feature representation for each face image. We investigate the performance of our IQBC-PCA and IQBC-CCA on FERET, CAS-PEAL-R1, LFW and PaSC databases. Extensive experimental results demonstrate that our IQBC descriptor outperforms other state-of-the-art face descriptors. [ABSTRACT FROM AUTHOR]

Action recognition (AR) is one of the most important tasks in video analysis and computer vision. Recently a large number of related methods have been proposed. While most of these methods are investigated on AR datasets collected from the visible spectrum, the AR problem under infrared scenarios still has not attracted much attention. There is even few public infrared datasets available for supporting the fundamental evaluation requirements of this research. To this issue, this work aims to emphasize the importance of the infrared AR problem in applications and arouse researchers' attention on this task. Specifically, we construct a new Inf rared A ction R ecognition ( InfAR ) dataset captured at different times, including in summer and winter, and explore how discriminable actions in our InfAR dataset are with the state-of-the-art pipelines based on low-level features and deep convolutional neural network (CNN), respectively. Our results reveal: (1) In all, dense trajectory feature can achieve the best performance while the appearance features, e.g., HOG, have relatively poorer performance; (2) the encoding method of vector of locally aggregated descriptors is evidently better than that of the widely-used Fisher Vector; (3) the late fusion facilitates a better performance than early fusion; (4) action videos captured in winter is more discriminable than in summer; (5) compared to appearance information, the motion information is more essential for infrared action recognition and utilizing this information through deep CNN can improve greatly the performance. The best performance achieved on our dataset is 76.66% (Average Precision), leaving a reasonable space for further exploring the insights underlying such type of infrared AR problem and accordingly designing proper techniques to further promote the performance on this specifically constructed InfAR dataset. [ABSTRACT FROM AUTHOR]

Over the past decades, an increasing number of local feature descriptors have been proposed in the community of computer vision and pattern recognition. Although they have achieved impressive results in many applications, how to find a balance between accuracy and computational efficiency is still an open issue. To address this issue, we present a local feature descriptor using entropy rate (FDER), which is robust to a variety of image transformations. We first employ the nonsubsampled Contourlet transform to produce multiple support regions and design a graph structure to describe the sub-region. We then use the entropy rate of random walks on the designed graph to build the FDER descriptor. Extensive experiments demonstrate the superiority of proposed descriptor dealing with various image transformations in comparison with the existing state-of-the-art descriptors. [ABSTRACT FROM AUTHOR]

This paper presents a new descriptor, multi-sparse descriptor (MSD), for pedestrian detection in static images. Specifically, the proposed descriptor is based on multi-dictionary sparse coding which contains unsupervised dictionary learning and sparse coding. During unsupervised learning phase, a family of dictionaries with different representation abilities is learnt from the pedestrian data. Then the data are encoded by these dictionaries and the histogram of the sparse coefficients is calculated as the descriptor. The benefit of this multi-dictionary sparse encoding is three-fold: firstly, the dictionaries are learnt from the pedestrian data, they are more efficient for encoding local structures of the pedestrian; secondly, multiple dictionaries can enrich the representation by providing different levels of abstractions; thirdly, since the dictionaries based representation is mainly focused on the low frequency, better generalization ability along the scale range is obtained. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Solid protocols to benchmark local feature detectors and descriptors were introduced by Mikolajczyk et al. [1,2] . The detectors and the descriptors are popular tools in object class matching, but the wide baseline setting in the benchmarks does not correspond to class-level matching where appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-of-the-art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best descriptor; (2) dense sampling outperforms interest point detectors with a clear margin; (3) detectors perform moderately well, but descriptors׳ performance collapses; (4) using multiple, even a few, best matches instead of the single best has significant effect on the performance; (5) object pose variation degrades dense sampling performance while the best detector (Hessian-affine) is unaffected. The performance of the best detector-descriptor pair is verified in the application of unsupervised visual class alignment where state-of-the-art results are achieved. The findings help to improve the existing detectors and descriptors for which the framework provides an automatic validation tool. [ABSTRACT FROM AUTHOR]

A new descriptor referred to as local beam descriptor is proposed to figure out the directionally spatial arrangement of the key points in a local region. As a byproduct, a phase value to maximize the periodical correlation of the short time series represented descriptors can be obtained. Consequently, most erroneous matches disagreeing with each other in terms of phase value can be filtered out to reduce the computational load of subsequent matching considerably. Then, the fine matching can be focused on robustness based on the similar triangles formed by every triple of matched point pairs. As confirmed experimentally, the proposed solution augments scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) in terms of both reduced time cost and the ability to match image pairs missed by such classical solution. An ensemble solution incorporating the proposed solution with SIFT based solution outperforms using either individual solution alone since they represent different views of image contents complementary to each other. [ABSTRACT FROM AUTHOR]

Visual descriptor learning seeks a projection to embed local descriptors (e.g., SIFT descriptors) into a new Euclidean space where pairs of matching descriptors (positive pairs) are better separated from pairs of non-matching descriptors (negative pairs). The original descriptors often confuse the positive pairs with the negative pairs, since local points labeled “non-matching” yield descriptors close together (irrelevant-near) or local points labeled “matching” yield descriptors far apart (relevant-far). This is because images differ in terms of viewpoint, resolution, noise, and illumination. In this paper, we formulate an embedding as a regularized discriminant analysis , which emphasizes relevant-far pairs and irrelevant-near pairs to better separate negative pairs from positive pairs. We then extend our method to nonlinear mapping by employing recent work on explicit kernel mapping. Experiments on object retrieval for landmark buildings in Oxford and Paris demonstrate the high performance of our method, compared to existing methods. [ABSTRACT FROM AUTHOR]

A novel Sparsely Encoded Local Descriptor (SELD) is proposed for face verification. Different from traditional hard or soft quantization methods, we exploit linear regression (LR) model with sparsity and non-negativity constraints to extract more discriminative features (i.e. sparse codes) from local image patches sampled pixel-wisely. Sum-pooling is then imposed to integrate all the sparse codes within each block partitioned from the whole face image. Whitened Principal Component Analysis (WPCA) is finally used to suppress noises and reduce the dimensionality of the pooled features, which thus results in the so-called SELD. To validate the proposed method, comprehensive experiments are conducted on face verification task to compare SELD with the existing related methods in terms of three variable component modules: K-means or K-SVD for dictionary learning, hard/soft assignment or regression model for encoding, as well as sum-pooling or max-pooling for pooling. Experimental results show that our method achieves a competitive accuracy compared with the state-of-the-art methods on the challenging Labeled Faces in the Wild (LFW) database. [ABSTRACT FROM AUTHOR]