Paper Group ANR 1376
Accurate Entrance Position Detection Based on Wi-Fi and GPS Signals Using Machine Learning. Ensemble Neural Networks (ENN): A gradient-free stochastic method. Learning to generate new indoor scenes. Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks. SDFDiff: Differentiable Rendering of Signed Distance Fiel …
Accurate Entrance Position Detection Based on Wi-Fi and GPS Signals Using Machine Learning
| Title | Accurate Entrance Position Detection Based on Wi-Fi and GPS Signals Using Machine Learning |
| Authors | Ahmad Abadleh |
| Abstract | This paper aims at detecting an accurate position of the main entrance of the buildings. The proposed approach relies on the fact that the GPS signals drop significantly when the user enters a building. Moreover, as most of the public buildings provide Wi-Fi services, the Wi-Fi received signal strength (RSS) can be utilized in order to detect the entrance of the buildings. The rationale behind this paper is that the GPS signals decrease as the user gets close to the main entrance and the Wi-Fi signal increases as the user approaches the main entrance. Several real experiments have been conducted in order to guarantee the feasibility of the proposed approach. The experiment results have shown an interesting result and the accuracy of the whole system was one meter |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04556v1 |
| https://arxiv.org/pdf/1912.04556v1.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-entrance-position-detection-based-on |
| Repo | |
| Framework | |
Ensemble Neural Networks (ENN): A gradient-free stochastic method
| Title | Ensemble Neural Networks (ENN): A gradient-free stochastic method |
| Authors | Yuntian Chena, Haibin Changa, Meng Jina, Dongxiao Zhanga |
| Abstract | In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are calculated by the ensemble randomized maximum likelihood algorithm (EnRML), which is an inverse modeling method. The ENN is able to simultaneously provide estimations and perform uncertainty quantification since it is built under the Bayesian framework. The ENN is also robust to small training data size because the ensemble of stochastic realizations essentially enlarges the training dataset. This constitutes a desirable characteristic, especially for real-world engineering applications. In addition, the ENN does not require the calculation of gradients, which enables the use of complicated neuron models and loss functions in neural networks. We experimentally demonstrate benefits of the proposed model, in particular showing that the ENN performs much better than the traditional Bayesian neural networks (BNN). The EnRML in ENN is a substitution of gradient-based optimization algorithms, which means that it can be directly combined with the feed-forward process in other existing (deep) neural networks, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), broadening future applications of the ENN. |
| Tasks | |
| Published | 2019-08-03 |
| URL | https://arxiv.org/abs/1908.01113v1 |
| https://arxiv.org/pdf/1908.01113v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-neural-networks-enn-a-gradient-free |
| Repo | |
| Framework | |
Learning to generate new indoor scenes
| Title | Learning to generate new indoor scenes |
| Authors | Pulak Purkait, Christopher Zach, Ian Reid |
| Abstract | Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high quality images. In this work we propose a neural network to learn a generative model for sampling consistent indoor scene layouts. Our method learns the co-occurrences, and appearance parameters such as shape and pose, for different objects categories through a grammar-based auto-encoder, resulting in a compact and accurate representation for scene layouts. In contrast to existing grammar-based methods with a user-specified grammar, we construct the grammar automatically by extracting a set of production rules on reasoning about object co-occurrences in training data. The extracted grammar is able to represent a scene by an augmented parse tree. The proposed auto-encoder encodes these parse trees to a latent code, and decodes the latent code to a parse-tree, thereby ensuring the generated scene is always valid. We experimentally demonstrate that the proposed auto-encoder learns not only to generate valid scenes (i.e. the arrangements and appearances of objects), but it also learns coherent latent representations where nearby latent samples decode to similar scene outputs. The obtained generative model is applicable to several computer vision tasks such as 3D pose and layout estimation from RGB-D data. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04554v1 |
| https://arxiv.org/pdf/1912.04554v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-generate-new-indoor-scenes |
| Repo | |
| Framework | |
Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
| Title | Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks |
| Authors | Ziyun Wang, Volkan Isler, Daniel D. Lee |
| Abstract | We address the problem of generating a high-resolution surface reconstruction from a single image. Our approach is to learn a Higher Order Function (HOF) which takes an image of an object as input and generates a mapping function. The mapping function takes samples from a canonical domain (e.g. the unit sphere) and maps each sample to a local tangent plane on the 3D reconstruction of the object. Each tangent plane is represented as an origin point and a normal vector at that point. By efficiently learning a continuous mapping function, the surface can be generated at arbitrary resolution in contrast to other methods which generate fixed resolution outputs. We present the Surface HOF in which both the higher order function and the mapping function are represented as neural networks, and train the networks to generate reconstructions of PointNet objects. Experiments show that Surface HOF is more accurate and uses more efficient representations than other state of the art methods for surface reconstruction. Surface HOF is also easier to train: it requires minimal input pre-processing and output post-processing and generates surface representations that are more parameter efficient. Its accuracy and convenience make Surface HOF an appealing method for single image reconstruction. |
| Tasks | 3D Reconstruction, Image Reconstruction |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08852v1 |
| https://arxiv.org/pdf/1912.08852v1.pdf | |
| PWC | https://paperswithcode.com/paper/surface-hof-surface-reconstruction-from-a |
| Repo | |
| Framework | |
SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
| Title | SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization |
| Authors | Yue Jiang, Dantong Ji, Zhizhong Han, Matthias Zwicker |
| Abstract | We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDF). Compared to other representations, SDFs have the advantage that they can represent shapes with arbitrary topology, and that they guarantee watertight surfaces. We apply our approach to the problem of multi-view 3D reconstruction, where we achieve high reconstruction quality and can capture complex topology of 3D objects. In addition, we employ a multi-resolution strategy to obtain a robust optimization algorithm. We further demonstrate that our SDF-based differentiable renderer can be integrated with deep learning models, which opens up options for learning approaches on 3D objects without 3D supervision. In particular, we apply our method to single-view 3D reconstruction and achieve state-of-the-art results. |
| Tasks | 3D Reconstruction, Single-View 3D Reconstruction |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07109v1 |
| https://arxiv.org/pdf/1912.07109v1.pdf | |
| PWC | https://paperswithcode.com/paper/sdfdiff-differentiable-rendering-of-signed |
| Repo | |
| Framework | |
PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
| Title | PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models |
| Authors | Lin Gao, Ling-Xiao Zhang, Hsien-Yu Meng, Yi-Hui Ren, Yu-Kun Lai, Leif Kobbelt |
| Abstract | In geometry processing, symmetry is the universally high-level structural information of the 3d models and benefits many geometry processing tasks including shape segmentation, alignment, matching, completion, e.g.. Thus it is an important problem to analyze various forms of the symmetry of 3D shapes. The planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time consuming and may not be able to identify all the symmetry planes. In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify isotropic shapes by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network-based method is hundreds of times faster than the state-of-the-art method, which is based on sampling. Our method is also robust even with noisy or incomplete input surfaces. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06511v3 |
| https://arxiv.org/pdf/1910.06511v3.pdf | |
| PWC | https://paperswithcode.com/paper/prs-net-planar-reflective-symmetry-detection |
| Repo | |
| Framework | |
Using Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery
| Title | Using Conditional Generative Adversarial Networks to Generate Ground-Level Views From Overhead Imagery |
| Authors | Xueqing Deng, Yi Zhu, Shawn Newsam |
| Abstract | This paper develops a deep-learning framework to synthesize a ground-level view of a location given an overhead image. We propose a novel conditional generative adversarial network (cGAN) in which the trained generator generates realistic looking and representative ground-level images using overhead imagery as auxiliary information. The generator is an encoder-decoder network which allows us to compare low- and high-level features as well as their concatenation for encoding the overhead imagery. We also demonstrate how our framework can be used to perform land cover classification by modifying the trained cGAN to extract features from overhead imagery. This is interesting because, although we are using this modified cGAN as a feature extractor for overhead imagery, it incorporates knowledge of how locations look from the ground. |
| Tasks | |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.06923v1 |
| http://arxiv.org/pdf/1902.06923v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-conditional-generative-adversarial |
| Repo | |
| Framework | |
On Conforming and Conflicting Values
| Title | On Conforming and Conflicting Values |
| Authors | Kinzang Chhogyal, Abhaya Nayak, Aditya Ghose, Mehmet Orgun, Hoa Dam |
| Abstract | Values are things that are important to us. Actions activate values - they either go against our values or they promote our values. Values themselves can either be conforming or conflicting depending on the action that is taken. In this short paper, we argue that values may be classified as one of two types - conflicting and inherently conflicting values. They are distinguished by the fact that the latter in some sense can be thought of as being independent of actions. This allows us to do two things: i) check whether a set of values is consistent and ii) check whether it is in conflict with other sets of values. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01682v2 |
| https://arxiv.org/pdf/1907.01682v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-conflicting-and-conflicting-values |
| Repo | |
| Framework | |
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
| Title | STD: Sparse-to-Dense 3D Object Detector for Point Cloud |
| Authors | Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia |
| Abstract | We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, we implement a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance. We conduct experiments on KITTI dataset, and evaluate our method in terms of 3D object and Bird’s Eye View (BEV) detection. Our method outperforms other state-of-the-arts by a large margin, especially on the hard set, with inference speed more than 10 FPS. |
| Tasks | 3D Object Detection, Object Detection |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.10471v1 |
| https://arxiv.org/pdf/1907.10471v1.pdf | |
| PWC | https://paperswithcode.com/paper/std-sparse-to-dense-3d-object-detector-for |
| Repo | |
| Framework | |
Toward a Dempster-Shafer theory of concepts
| Title | Toward a Dempster-Shafer theory of concepts |
| Authors | Sabine Frittella, Krishna Manoorkar, Alessandra Palmigiano, Apostolos Tzimoulis, Nachoem M. Wijnberg |
| Abstract | In this paper, we generalize the basic notions and results of Dempster-Shafer theory from predicates to formal concepts. Results include the representation of conceptual belief functions as inner measures of suitable probability functions, and a Dempster-Shafer rule of combination on belief functions on formal concepts. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05145v2 |
| https://arxiv.org/pdf/1908.05145v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-a-dempster-shafer-theory-of-concepts |
| Repo | |
| Framework | |
Representation Learning for Words and Entities
| Title | Representation Learning for Words and Entities |
| Authors | Pushpendre Rastogi |
| Abstract | This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning representations of words called Multiview Latent Semantic Analysis (MVLSA). By incorporating up to 46 different types of co-occurrence statistics for the same vocabulary of english words, I show that MVLSA outperforms other state-of-the-art word embedding models. Next, I focus on learning entity representations for search and recommendation and present the second method of this thesis, Neural Variational Set Expansion (NVSE). NVSE is also an unsupervised learning method, but it is based on the Variational Autoencoder framework. Evaluations with human annotators show that NVSE can facilitate better search and recommendation of information gathered from noisy, automatic annotation of unstructured natural language corpora. Finally, I move from unstructured data and focus on structured knowledge graphs. I present novel approaches for learning embeddings of vertices and edges in a knowledge graph that obey logical constraints. |
| Tasks | Knowledge Graphs, Representation Learning |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05651v1 |
| https://arxiv.org/pdf/1906.05651v1.pdf | |
| PWC | https://paperswithcode.com/paper/representation-learning-for-words-and |
| Repo | |
| Framework | |
Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network
| Title | Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network |
| Authors | Yusong Wu, Shengchen Li, Chengzhu Yu, Heng Lu, Chao Weng, Liqiang Zhang, Dong Yu |
| Abstract | This paper presents a method that generates expressive singing voice of Peking opera. The synthesis of expressive opera singing usually requires pitch contours to be extracted as the training data, which relies on techniques and is not able to be manually labeled. With the Duration Informed Attention Network (DurIAN), this paper makes use of musical note instead of pitch contours for expressive opera singing synthesis. The proposed method enables human annotation being combined with automatic extracted features to be used as training data thus the proposed method gives extra flexibility in data collection for Peking opera singing synthesis. Comparing with the expressive singing voice of Peking opera synthesised by pitch contour based system, the proposed musical note based system produces comparable singing voice in Peking opera with expressiveness in various aspects. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12010v1 |
| https://arxiv.org/pdf/1912.12010v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthesising-expressiveness-in-peking-opera |
| Repo | |
| Framework | |
Deep progressive multi-scale attention for acoustic event classification
| Title | Deep progressive multi-scale attention for acoustic event classification |
| Authors | Xugang Lu, Peng Shen, Sheng Li, Yu Tsao, Hisashi Kawai |
| Abstract | Convolutional neural network (CNN) is an indispensable building block for designing a state of the art system for acoustic event classification (AEC). By stacking multiple CNN layers, the model could explore long-range dependency of explored features in top layers with increasing of feature abstraction. However it is also possible that the discriminative features with short-range dependency which are distributed locally are smooth out in the final representation. In this paper, we propose a progressive multi-scale attention (MSA) model which explicitly integrates multi-scale features with short- and long-range dependency in feature extraction. Based on mathematic formulations, we revealed that the conventional residual CNN (ResCNN) model could be explained as a special case of the proposed MSA model, and the MSA model could use the ResCNN as a backbone with an attentive feature weighting in consecutive scales. The discriminative features in multi-scales are progressively propagated to top layers for the final representation. Therefore, the final representation encodes multi-scale features with local and global discriminative structures which are expected to improve the performance. We tested the proposed model on two AEC data corpora, one is for urban acoustic event classification task, the other is for acoustic event detection in smart car environments. Our results showed that the proposed MSA model effectively improved the performance on the current state-of-the-art deep learning algorithms. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12011v1 |
| https://arxiv.org/pdf/1912.12011v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-progressive-multi-scale-attention-for |
| Repo | |
| Framework | |
Fast Generalized Matrix Regression with Applications in Machine Learning
| Title | Fast Generalized Matrix Regression with Applications in Machine Learning |
| Authors | Haishan Ye, Shusen Wang, Zhihua Zhang, Tong Zhang |
| Abstract | Fast matrix algorithms have become the fundamental tools of machine learning in big data era. The generalized matrix regression problem is widely used in the matrix approximation such as CUR decomposition, kernel matrix approximation, and stream singular value decomposition (SVD), etc. In this paper, we propose a fast generalized matrix regression algorithm (Fast GMR) which utilizes sketching technique to solve the GMR problem efficiently. Given error parameter $0<\epsilon<1$, the Fast GMR algorithm can achieve a $(1+\epsilon)$ relative error with the sketching sizes being of order $\cO(\epsilon^{-1/2})$ for a large group of GMR problems. We apply the Fast GMR algorithm to the symmetric positive definite matrix approximation and single pass singular value decomposition and they achieve a better performance than conventional algorithms. Our empirical study also validates the effectiveness and efficiency of our proposed algorithms. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12008v1 |
| https://arxiv.org/pdf/1912.12008v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-generalized-matrix-regression-with |
| Repo | |
| Framework | |
Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
| Title | Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss |
| Authors | Eskil Jörgensen, Christopher Zach, Fredrik Kahl |
| Abstract | Three-dimensional object detection from a single view is a challenging task which, if performed with good accuracy, is an important enabler of low-cost mobile robot perception. Previous approaches to this problem suffer either from an overly complex inference engine or from an insufficient detection accuracy. To deal with these issues, we present SS3D, a single-stage monocular 3D object detector. The framework consists of (i) a CNN, which outputs a redundant representation of each relevant object in the image with corresponding uncertainty estimates, and (ii) a 3D bounding box optimizer. We show how modeling heteroscedastic uncertainty improves performance upon our baseline, and furthermore, how back-propagation can be done through the optimizer in order to train the pipeline end-to-end for additional accuracy. Our method achieves SOTA accuracy on monocular 3D object detection, while running at 20 fps in a straightforward implementation. We argue that the SS3D architecture provides a solid framework upon which high performing detection systems can be built, with autonomous driving being the main application in mind. |
| Tasks | 3D Object Detection, Autonomous Driving, Object Detection |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08070v2 |
| https://arxiv.org/pdf/1906.08070v2.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-3d-object-detection-and-box-fitting |
| Repo | |
| Framework | |
