Paper Group ANR 399
Velocity variations at Columbia Glacier captured by particle filtering of oblique time-lapse images. Asymmetric Deep Supervised Hashing. Disentangled Representations for Manipulation of Sentiment in Text. PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks. Single Reference Image based Scene Relighting …
Velocity variations at Columbia Glacier captured by particle filtering of oblique time-lapse images
| Title | Velocity variations at Columbia Glacier captured by particle filtering of oblique time-lapse images |
| Authors | Douglas Brinkerhoff, Shad O’Neel |
| Abstract | We develop a probabilistic method for tracking glacier surface motion based on time-lapse imagery, which works by sequentially resampling a stochastic state-space model according to a likelihood determined through correlation between reference and test images. The method is robust due to its natural handling of periodic occlusion and its capacity to follow multiple hypothesis displacements between images, and can improve estimates of velocity magnitude and direction through the inclusion of observations from an arbitrary number of cameras. We apply the method to an annual record of images from two cameras near the terminus of Columbia Glacier. While the method produces velocities at daily resolution, we verify our results by comparing eleven-day means to TerraSar-X. We find that Columbia Glacier transitions between a winter state characterized by moderate velocities and little temporal variability, to an early summer speed-up in which velocities are sensitive to increases in melt- and rainwater, to a fall slowdown, where velocities drop to below their winter mean and become insensitive to external forcing, a pattern consistent with the development and collapse of efficient and inefficient subglacial hydrologic networks throughout the year. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05366v1 |
| http://arxiv.org/pdf/1711.05366v1.pdf | |
| PWC | https://paperswithcode.com/paper/velocity-variations-at-columbia-glacier |
| Repo | |
| Framework | |
Asymmetric Deep Supervised Hashing
| Title | Asymmetric Deep Supervised Hashing |
| Authors | Qing-Yuan Jiang, Wu-Jun Li |
| Abstract | Hashing has been widely used for large-scale approximate nearest neighbor search because of its storage and search efficiency. Recent work has found that deep supervised hashing can significantly outperform non-deep supervised hashing in many applications. However, most existing deep supervised hashing methods adopt a symmetric strategy to learn one deep hash function for both query points and database (retrieval) points. The training of these symmetric deep supervised hashing methods is typically time-consuming, which makes them hard to effectively utilize the supervised information for cases with large-scale database. In this paper, we propose a novel deep supervised hashing method, called asymmetric deep supervised hashing (ADSH), for large-scale nearest neighbor search. ADSH treats the query points and database points in an asymmetric way. More specifically, ADSH learns a deep hash function only for query points, while the hash codes for database points are directly learned. The training of ADSH is much more efficient than that of traditional symmetric deep supervised hashing methods. Experiments show that ADSH can achieve state-of-the-art performance in real applications. |
| Tasks | |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08325v1 |
| http://arxiv.org/pdf/1707.08325v1.pdf | |
| PWC | https://paperswithcode.com/paper/asymmetric-deep-supervised-hashing |
| Repo | |
| Framework | |
Disentangled Representations for Manipulation of Sentiment in Text
| Title | Disentangled Representations for Manipulation of Sentiment in Text |
| Authors | Maria Larsson, Amanda Nilsson, Mikael Kågebäck |
| Abstract | The ability to change arbitrary aspects of a text while leaving the core message intact could have a strong impact in fields like marketing and politics by enabling e.g. automatic optimization of message impact and personalized language adapted to the receiver’s profile. In this paper we take a first step towards such a system by presenting an algorithm that can manipulate the sentiment of a text while preserving its semantics using disentangled representations. Validation is performed by examining trajectories in embedding space and analyzing transformed sentences for semantic preservation while expression of desired sentiment shift. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.10066v1 |
| http://arxiv.org/pdf/1712.10066v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangled-representations-for-manipulation |
| Repo | |
| Framework | |
PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks
| Title | PReP: Path-Based Relevance from a Probabilistic Perspective in Heterogeneous Information Networks |
| Authors | Yu Shi, Po-Wei Chan, Honglei Zhuang, Huan Gui, Jiawei Han |
| Abstract | As a powerful representation paradigm for networked and multi-typed data, the heterogeneous information network (HIN) is ubiquitous. Meanwhile, defining proper relevance measures has always been a fundamental problem and of great pragmatic importance for network mining tasks. Inspired by our probabilistic interpretation of existing path-based relevance measures, we propose to study HIN relevance from a probabilistic perspective. We also identify, from real-world data, and propose to model cross-meta-path synergy, which is a characteristic important for defining path-based HIN relevance and has not been modeled by existing methods. A generative model is established to derive a novel path-based relevance measure, which is data-driven and tailored for each HIN. We develop an inference algorithm to find the maximum a posteriori (MAP) estimate of the model parameters, which entails non-trivial tricks. Experiments on two real-world datasets demonstrate the effectiveness of the proposed model and relevance measure. |
| Tasks | |
| Published | 2017-06-05 |
| URL | http://arxiv.org/abs/1706.01177v2 |
| http://arxiv.org/pdf/1706.01177v2.pdf | |
| PWC | https://paperswithcode.com/paper/prep-path-based-relevance-from-a |
| Repo | |
| Framework | |
Single Reference Image based Scene Relighting via Material Guided Filtering
| Title | Single Reference Image based Scene Relighting via Material Guided Filtering |
| Authors | Xin Jin, Yannan Li, Ningning Liu, Xiaodong Li, Xianggang Jiang, Chaoen Xiao, Shiming Ge |
| Abstract | Image relighting is to change the illumination of an image to a target illumination effect without known the original scene geometry, material information and illumination condition. We propose a novel outdoor scene relighting method, which needs only a single reference image and is based on material constrained layer decomposition. Firstly, the material map is extracted from the input image. Then, the reference image is warped to the input image through patch match based image warping. Lastly, the input image is relit using material constrained layer decomposition. The experimental results reveal that our method can produce similar illumination effect as that of the reference image on the input image using only a single reference image. |
| Tasks | |
| Published | 2017-08-23 |
| URL | http://arxiv.org/abs/1708.07066v1 |
| http://arxiv.org/pdf/1708.07066v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-reference-image-based-scene-relighting |
| Repo | |
| Framework | |
Visual Search at eBay
| Title | Visual Search at eBay |
| Authors | Fan Yang, Ajinkya Kale, Yury Bubnov, Leon Stein, Qiaosong Wang, Hadi Kiapour, Robinson Piramuthu |
| Abstract | In this paper, we propose a novel end-to-end approach for scalable visual search infrastructure. We discuss the challenges we faced for a massive volatile inventory like at eBay and present our solution to overcome those. We harness the availability of large image collection of eBay listings and state-of-the-art deep learning techniques to perform visual search at scale. Supervised approach for optimized search limited to top predicted categories and also for compact binary signature are key to scale up without compromising accuracy and precision. Both use a common deep neural network requiring only a single forward inference. The system architecture is presented with in-depth discussions of its basic components and optimizations for a trade-off between search relevance and latency. This solution is currently deployed in a distributed cloud infrastructure and fuels visual search in eBay ShopBot and Close5. We show benchmark on ImageNet dataset on which our approach is faster and more accurate than several unsupervised baselines. We share our learnings with the hope that visual search becomes a first class citizen for all large scale search engines rather than an afterthought. |
| Tasks | |
| Published | 2017-06-10 |
| URL | http://arxiv.org/abs/1706.03154v2 |
| http://arxiv.org/pdf/1706.03154v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-search-at-ebay |
| Repo | |
| Framework | |
A Deep Learning Framework using Passive WiFi Sensing for Respiration Monitoring
| Title | A Deep Learning Framework using Passive WiFi Sensing for Respiration Monitoring |
| Authors | U. M. Khan, Z. Kabir, S. A. Hassan, S. H. Ahmed |
| Abstract | This paper presents an end-to-end deep learning framework using passive WiFi sensing to classify and estimate human respiration activity. A passive radar test-bed is used with two channels where the first channel provides the reference WiFi signal, whereas the other channel provides a surveillance signal that contains reflections from the human target. Adaptive filtering is performed to make the surveillance signal source-data invariant by eliminating the echoes of the direct transmitted signal. We propose a novel convolutional neural network to classify the complex time series data and determine if it corresponds to a breathing activity, followed by a random forest estimator to determine breathing rate. We collect an extensive dataset to train the learning models and develop reference benchmarks for the future studies in the field. Based on the results, we conclude that deep learning techniques coupled with passive radars offer great potential for end-to-end human activity recognition. |
| Tasks | Activity Recognition, Human Activity Recognition, Time Series |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05708v1 |
| http://arxiv.org/pdf/1704.05708v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-framework-using-passive-wifi |
| Repo | |
| Framework | |
Transfer Learning in CNNs Using Filter-Trees
| Title | Transfer Learning in CNNs Using Filter-Trees |
| Authors | Suresh Kirthi Kumaraswamy, PS Sastry, KR Ramakrishnan |
| Abstract | Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a trans- fer learning mechanism for improving efficiency of learning CNNs. A filter-tree corresponding to a filter in k^{th} convolu- tional layer of a CNN is a subnetwork consisting of the filter along with all its connections to filters in all preceding layers. An ensemble of such filter-trees created from the k^{th} layers of many CNNs learnt on different but related tasks, forms the BFT. To learn a new CNN, we sample from the BFT to select a set of filter trees. This fixes the target net up to the k th layer and only the remaining network would be learnt using train- ing data of new task. Through simulations we demonstrate the effectiveness of this idea of BFT. This method constitutes a novel transfer learning technique where transfer is at a sub- network level; transfer can be effected from multiple source networks; and, with no finetuning of the transferred weights, the performance achieved is on par with networks that are trained from scratch. |
| Tasks | Transfer Learning |
| Published | 2017-11-27 |
| URL | http://arxiv.org/abs/1711.09648v1 |
| http://arxiv.org/pdf/1711.09648v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-in-cnns-using-filter-trees |
| Repo | |
| Framework | |
Backpropagation Training for Fisher Vectors within Neural Networks
| Title | Backpropagation Training for Fisher Vectors within Neural Networks |
| Authors | Patrick Wieschollek, Fabian Groh, Hendrik P. A. Lensch |
| Abstract | Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learning architectures on visual recognitions tasks. Current methods using FV as a feature descriptor in deep architectures assume that all original input features are static. We propose a framework to jointly learn the representation of original features, FV parameters and parameters of the classifier in the style of traditional neural networks. Our proof of concept implementation improves the performance of FV on the Pascal Voc 2007 challenge in a multi-GPU setting in comparison to a default SVM setting. We demonstrate that FV can be embedded into neural networks at arbitrary positions, allowing end-to-end training with back-propagation. |
| Tasks | |
| Published | 2017-02-08 |
| URL | http://arxiv.org/abs/1702.02549v1 |
| http://arxiv.org/pdf/1702.02549v1.pdf | |
| PWC | https://paperswithcode.com/paper/backpropagation-training-for-fisher-vectors |
| Repo | |
| Framework | |
Unsupervised Neural-Symbolic Integration
| Title | Unsupervised Neural-Symbolic Integration |
| Authors | Son N. Tran |
| Abstract | Symbolic has been long considered as a language of human intelligence while neural networks have advantages of robust computation and dealing with noisy data. The integration of neural-symbolic can offer better learning and reasoning while providing a means for interpretability through the representation of symbolic knowledge. Although previous works focus intensively on supervised feedforward neural networks, little has been done for the unsupervised counterparts. In this paper we show how to integrate symbolic knowledge into unsupervised neural networks. We exemplify our approach with knowledge in different forms, including propositional logic for DNA promoter prediction and first-order logic for understanding family relationship. |
| Tasks | |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01991v2 |
| http://arxiv.org/pdf/1706.01991v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-neural-symbolic-integration |
| Repo | |
| Framework | |
Design of a Time Delay Reservoir Using Stochastic Logic: A Feasibility Study
| Title | Design of a Time Delay Reservoir Using Stochastic Logic: A Feasibility Study |
| Authors | Cory Merkel |
| Abstract | This paper presents a stochastic logic time delay reservoir design. The reservoir is analyzed using a number of metrics, such as kernel quality, generalization rank, performance on simple benchmarks, and is also compared to a deterministic design. A novel re-seeding method is introduced to reduce the adverse effects of stochastic noise, which may also be implemented in other stochastic logic reservoir computing designs, such as echo state networks. Benchmark results indicate that the proposed design performs well on noise-tolerant classification problems, but more work needs to be done to improve the stochastic logic time delay reservoir’s robustness for regression problems. |
| Tasks | |
| Published | 2017-02-13 |
| URL | http://arxiv.org/abs/1702.04265v1 |
| http://arxiv.org/pdf/1702.04265v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-of-a-time-delay-reservoir-using |
| Repo | |
| Framework | |
Sparse Regularization in Marketing and Economics
| Title | Sparse Regularization in Marketing and Economics |
| Authors | Guanhao Feng, Nicholas Polson, Yuexi Wang, Jianeng Xu |
| Abstract | Sparse alpha-norm regularization has many data-rich applications in Marketing and Economics. Alpha-norm, in contrast to lasso and ridge regularization, jumps to a sparse solution. This feature is attractive for ultra high-dimensional problems that occur in demand estimation and forecasting. The alpha-norm objective is nonconvex and requires coordinate descent and proximal operators to find the sparse solution. We study a typical marketing demand forecasting problem, grocery store sales for salty snacks, that has many dummy variables as controls. The key predictors of demand include price, equivalized volume, promotion, flavor, scent, and brand effects. By comparing with many commonly used machine learning methods, alpha-norm regularization achieves its goal of providing accurate out-of-sample estimates for the promotion lift effects. Finally, we conclude with directions for future research. |
| Tasks | |
| Published | 2017-09-01 |
| URL | http://arxiv.org/abs/1709.00379v2 |
| http://arxiv.org/pdf/1709.00379v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-regularization-in-marketing-and |
| Repo | |
| Framework | |
Exploiting Modern Hardware for High-Dimensional Nearest Neighbor Search
| Title | Exploiting Modern Hardware for High-Dimensional Nearest Neighbor Search |
| Authors | Fabien André |
| Abstract | Many multimedia information retrieval or machine learning problems require efficient high-dimensional nearest neighbor search techniques. For instance, multimedia objects (images, music or videos) can be represented by high-dimensional feature vectors. Finding two similar multimedia objects then comes down to finding two objects that have similar feature vectors. In the current context of mass use of social networks, large scale multimedia databases or large scale machine learning applications are more and more common, calling for efficient nearest neighbor search approaches. This thesis builds on product quantization, an efficient nearest neighbor search technique that compresses high-dimensional vectors into short codes. This makes it possible to store very large databases entirely in RAM, enabling low response times. We propose several contributions that exploit the capabilities of modern CPUs, especially SIMD and the cache hierarchy, to further decrease response times offered by product quantization. |
| Tasks | Information Retrieval, Quantization |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.02912v1 |
| http://arxiv.org/pdf/1712.02912v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-modern-hardware-for-high |
| Repo | |
| Framework | |
Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations
| Title | Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations |
| Authors | Patrick Glauner, Niklas Dahringer, Oleksandr Puhachov, Jorge Augusto Meira, Petko Valtchev, Radu State, Diogo Duarte |
| Abstract | Power grids are critical infrastructure assets that face non-technical losses (NTL) such as electricity theft or faulty meters. NTL may range up to 40% of the total electricity distributed in emerging countries. Industrial NTL detection systems are still largely based on expert knowledge when deciding whether to carry out costly on-site inspections of customers. Electricity providers are reluctant to move to large-scale deployments of automated systems that learn NTL profiles from data due to the latter’s propensity to suggest a large number of unnecessary inspections. In this paper, we propose a novel system that combines automated statistical decision making with expert knowledge. First, we propose a machine learning framework that classifies customers into NTL or non-NTL using a variety of features derived from the customers’ consumption data. The methodology used is specifically tailored to the level of noise in the data. Second, in order to allow human experts to feed their knowledge in the decision loop, we propose a method for visualizing prediction results at various granularity levels in a spatial hologram. Our approach allows domain experts to put the classification results into the context of the data and to incorporate their knowledge for making the final decisions of which customers to inspect. This work has resulted in appreciable results on a real-world data set of 3.6M customers. Our system is being deployed in a commercial NTL detection software. |
| Tasks | Decision Making |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.03008v1 |
| http://arxiv.org/pdf/1709.03008v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-irregular-power-usage-by-turning |
| Repo | |
| Framework | |
A Novel SDASS Descriptor for Fully Encoding the Information of 3D Local Surface
| Title | A Novel SDASS Descriptor for Fully Encoding the Information of 3D Local Surface |
| Authors | Bao Zhao, Xinyi Le, Juntong Xi |
| Abstract | Local feature description is a fundamental yet challenging task in 3D computer vision. This paper proposes a novel descriptor, named Statistic of Deviation Angles on Subdivided Space (SDASS), of encoding geometrical and spatial information of local surface on Local Reference Axis (LRA). In terms of encoding geometrical information, considering that surface normals, which are usually used for encoding geometrical information of local surface, are vulnerable to various nuisances (e.g., noise, varying mesh resolutions etc.), we propose a robust geometrical attribute, called Local Minimum Axis (LMA), to replace the normals for generating the geometrical feature in our SDASS descriptor. For encoding spatial information, we use two spatial features for fully encoding the spatial information of a local surface based on LRA which usually presents high overall repeatability than Local Reference Axis (LRF). Besides, an improved LRA is proposed for increasing the robustness of our SDASS to noise and varying mesh resolutions. The performance of the SDASS descriptor is rigorously tested on four popular datasets. The results show that our descriptor has a high descriptiveness and strong robustness, and its performance outperform existing algorithms by a large margin. Finally, the proposed descriptor is applied to 3D registration. The accurate result further confirms the effectiveness of our SDASS method. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05368v3 |
| http://arxiv.org/pdf/1711.05368v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-sdass-descriptor-for-fully-encoding |
| Repo | |
| Framework | |
