• Publicationsclose
• Research dataclose
• Other research productsclose
• 2017-2021close
• Preprint close
• Article close
• AE close
• arXiv.org e-Print Archive close

Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for many computer vision applications. In this paper, we propose an end-to-end multi-context collaborative deep network for removing distortions from single fisheye images. In contrast to conventional approaches, which focus on extracting hand-crafted features from input images, our method learns high-level semantics and low-level appearance features simultaneously to estimate the distortion parameters. To facilitate training, we construct a synthesized dataset that covers various scenes and distortion parameter settings. Experiments on both synthesized and real-world datasets show that the proposed model significantly outperforms current state of the art methods. Our code and synthesized dataset will be made publicly available. Comment: 16 pages, 5 figures

Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets. To appear in CVPR 2019

We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of the features that requires more memory, or select only a subset of features by pruning entire filter channels. We propose the Cascaded Projection (CaP) compression method that projects the output and input filter channels of successive layers to a unified low dimensional space based on a low-rank projection. We optimize the projection to minimize classification loss and the difference between the next layer's features in the compressed and uncompressed networks. To solve this non-convex optimization problem we propose a new optimization method of a proxy matrix using backpropagation and Stochastic Gradient Descent (SGD) with geometric constraints. Our cascaded projection approach leads to improvements in all critical areas of network compression: high accuracy, low memory consumption, low parameter count and high processing speed. The proposed CaP method demonstrates state-of-the-art results compressing VGG16 and ResNet networks with over 4x reduction in the number of computations and excellent performance in top-5 accuracy on the ImageNet dataset before and after fine-tuning.

A characteristic feature of the 3d plaquette Ising model is its planar subsystem symmetry. The quantum version of this model has been shown to be related via a duality to the X-Cube model, which has been paradigmatic in the new and rapidly developing field of fractons. The relation between the 3d plaquette Ising and the X-Cube model is similar to that between the 2d quantum transverse spin Ising model and the Toric Code. Gauging the global symmetry in the case of the 2d Ising model and considering the gauge invariant sector of the high temperature phase leads to the Toric Code, whereas gauging the subsystem symmetry of the 3d quantum transverse spin plaquette Ising model leads to the X-Cube model. A non-standard dual formulation of the 3d plaquette Ising model which utilises three flavours of spins has recently been discussed in the context of dualising the fracton-free sector of the X-Cube model. In this paper we investigate the classical spin version of this non-standard dual Hamiltonian and discuss its properties in relation to the more familiar Ashkin-Teller-like dual and further related dual formulations involving both link and vertex spins and non-Ising spins. Reviews results in arXiv:1106.0325 and arXiv:1106.4664 in light of more recent simulations and fracton literature. Published in special issue of Entropy dedicated to the memory of Professor Ian Campbell

This paper shows that pinched hysteresis can be observed in simple nonlinear resonance circuits containing a single diode that behaves as a voltage-controlled switch. Mathematical models are derived and numerically validated for both series and parallel resonator circuits. The lobe area of the pinched loop is found to increase with increased frequency and multiple pinch-points are possible with an odd symmetrical nonlinearity such as a cubic nonlinearity. Experiments have been performed to prove the existence of pinched hysteresis with a single diode and with two anti-parallel diodes. The formation of a pinched loop in these circuits confirms that: 1) pinched hysteresis is not a finger-print of memristors and that 2) the existence of a nonlinearity is essential for generating this behavior. Finally, an application in a digital logic circuit is validated. 9 pages, 9 figures

Scenario Analysis is a risk assessment tool that aims to evaluate the impact of a small number of distinct plausible future scenarios. In this paper, we provide an overview of important aspects of Scenario Analysis including when it is appropriate, the design of scenarios, uncertainty and encouraging creativity. Each of these issues is discussed in the context of climate, energy and legal scenarios.

We complement this with lower bounds on the bit complexity of any compression scheme that (1 + epsilon)-approximates all the cuts in a given hypergraph, and hence also on the bit complexity of every epsilon-cut/spectral sparsifier. These lower bounds are based on Ruzsa-Szemeredi graphs, and a particular instantiation yields an Omega(nr) lower bound on the bit complexity even for fixed constant epsilon. In the case of hypergraph cut sparsifiers, this is tight up to polylogarithmic factors in n, due to recent result of [Chen, Khanna and Nagda, FOCS'20]. For spectral sparsifiers it narrows the gap to O*(r). Our first result is a polynomial-time algorithm that, given a hypergraph on n vertices with maximum hyperedge size r, outputs an epsilon-spectral sparsifier with O* (nr) hyperedges, where O* suppresses (epsilon(-1) log n)(O(1) )factors. This size bound improves the two previous bounds: O*(n(3)) [Soma and Yoshida, SODA'19] and O* (nr(3)) [Bansal, Svensson and Trevisan, FOCS'19]. Our main technical tool is a new method for proving concentration of the nonlinear analogue of the quadratic form of the Laplacians for hypergraph expanders. Cut and spectral sparsification of graphs have numerous applications, including e.g. speeding up algorithms for cuts and Laplacian solvers. These powerful notions have recently been extended to hypergraphs, which are much richer and may offer new applications. However, the current bounds on the size of hypergraph sparsifiers are not as tight as the corresponding bounds for graphs. Finally, for directed hypergraphs, we present an algorithm that computes an c-spectral sparsifier with O*(n(2)r(3)) hyperarcs, where r is the maximum size of a hyperarc. For small r, this improves over O*(n(3)) known from [Soma and Yoshida, SODA'19], and is getting close to the trivial lower bound of Omega(n(2)) hyperarcs.

This research aims at identifying the unknown emotion using speaker cues. In this study, we identify the unknown emotion using a two-stage framework. The first stage focuses on identifying the speaker who uttered the unknown emotion, while the next stage focuses on identifying the unknown emotion uttered by the recognized speaker in the prior stage. This proposed framework has been evaluated on an Arabic Emirati-accented speech database uttered by fifteen speakers per gender. Mel-Frequency Cepstral Coefficients (MFCCs) have been used as the extracted features and Hidden Markov Model (HMM) has been utilized as the classifier in this work. Our findings demonstrate that emotion recognition accuracy based on the two-stage framework is greater than that based on the one-stage approach and the state-of-the-art classifiers and models such as Gaussian Mixture Model (GMM), Support Vector Machine (SVM), and Vector Quantization (VQ). The average emotion recognition accuracy based on the two-stage approach is 67.5%, while the accuracy reaches to 61.4%, 63.3%, 64.5%, and 61.5%, based on the one-stage approach, GMM, SVM, and VQ, respectively. The achieved results based on the two-stage framework are very close to those attained in subjective assessment by human listeners. Comment: 5 pages