Paper Group ANR 295
User Reviews and Language: How Language Influences Ratings. PerSum: Novel Systems for Document Summarization in Persian. A Fully Convolutional Deep Auditory Model for Musical Chord Recognition. Some Insights into the Geometry and Training of Neural Networks. Deep Neural Networks predict Hierarchical Spatio-temporal Cortical Dynamics of Human Visual …
User Reviews and Language: How Language Influences Ratings
| Title | User Reviews and Language: How Language Influences Ratings |
| Authors | Scott A. Hale |
| Abstract | The number of user reviews of tourist attractions, restaurants, mobile apps, etc. is increasing for all languages; yet, research is lacking on how reviews in multiple languages should be aggregated and displayed. Speakers of different languages may have consistently different experiences, e.g., different information available in different languages at tourist attractions or different user experiences with software due to internationalization/localization choices. This paper assesses the similarity in the ratings given by speakers of different languages to London tourist attractions on TripAdvisor. The correlations between different languages are generally high, but some language pairs are more correlated than others. The results question the common practice of computing average ratings from reviews in many languages. |
| Tasks | |
| Published | 2016-05-06 |
| URL | http://arxiv.org/abs/1605.01919v1 |
| http://arxiv.org/pdf/1605.01919v1.pdf | |
| PWC | https://paperswithcode.com/paper/user-reviews-and-language-how-language |
| Repo | |
| Framework | |
PerSum: Novel Systems for Document Summarization in Persian
| Title | PerSum: Novel Systems for Document Summarization in Persian |
| Authors | Saeid Parvandeh, Shibamouli Lahiri, Fahimeh Boroumand |
| Abstract | In this paper we explore the problem of document summarization in Persian language from two distinct angles. In our first approach, we modify a popular and widely cited Persian document summarization framework to see how it works on a realistic corpus of news articles. Human evaluation on generated summaries shows that graph-based methods perform better than the modified systems. We carry this intuition forward in our second approach, and probe deeper into the nature of graph-based systems by designing several summarizers based on centrality measures. Ad hoc evaluation using ROUGE score on these summarizers suggests that there is a small class of centrality measures that perform better than three strong unsupervised baselines. |
| Tasks | Document Summarization |
| Published | 2016-06-09 |
| URL | http://arxiv.org/abs/1606.03143v1 |
| http://arxiv.org/pdf/1606.03143v1.pdf | |
| PWC | https://paperswithcode.com/paper/persum-novel-systems-for-document |
| Repo | |
| Framework | |
A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
| Title | A Fully Convolutional Deep Auditory Model for Musical Chord Recognition |
| Authors | Filip Korzeniowski, Gerhard Widmer |
| Abstract | Chord recognition systems depend on robust feature extraction pipelines. While these pipelines are traditionally hand-crafted, recent advances in end-to-end machine learning have begun to inspire researchers to explore data-driven methods for such tasks. In this paper, we present a chord recognition system that uses a fully convolutional deep auditory model for feature extraction. The extracted features are processed by a Conditional Random Field that decodes the final chord sequence. Both processing stages are trained automatically and do not require expert knowledge for optimising parameters. We show that the learned auditory system extracts musically interpretable features, and that the proposed chord recognition system achieves results on par or better than state-of-the-art algorithms. |
| Tasks | Chord Recognition |
| Published | 2016-12-15 |
| URL | http://arxiv.org/abs/1612.05082v1 |
| http://arxiv.org/pdf/1612.05082v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fully-convolutional-deep-auditory-model-for |
| Repo | |
| Framework | |
Some Insights into the Geometry and Training of Neural Networks
| Title | Some Insights into the Geometry and Training of Neural Networks |
| Authors | Ewout van den Berg |
| Abstract | Neural networks have been successfully used for classification tasks in a rapidly growing number of practical applications. Despite their popularity and widespread use, there are still many aspects of training and classification that are not well understood. In this paper we aim to provide some new insights into training and classification by analyzing neural networks from a feature-space perspective. We review and explain the formation of decision regions and study some of their combinatorial aspects. We place a particular emphasis on the connections between the neural network weight and bias terms and properties of decision boundaries and other regions that exhibit varying levels of classification confidence. We show how the error backpropagates in these regions and emphasize the important role they have in the formation of gradients. These findings expose the connections between scaling of the weight parameters and the density of the training samples. This sheds more light on the vanishing gradient problem, explains the need for regularization, and suggests an approach for subsampling training data to improve performance. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00329v1 |
| http://arxiv.org/pdf/1605.00329v1.pdf | |
| PWC | https://paperswithcode.com/paper/some-insights-into-the-geometry-and-training |
| Repo | |
| Framework | |
Deep Neural Networks predict Hierarchical Spatio-temporal Cortical Dynamics of Human Visual Object Recognition
| Title | Deep Neural Networks predict Hierarchical Spatio-temporal Cortical Dynamics of Human Visual Object Recognition |
| Authors | Radoslaw M. Cichy, Aditya Khosla, Dimitrios Pantazis, Antonio Torralba, Aude Oliva |
| Abstract | The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain. |
| Tasks | Object Recognition |
| Published | 2016-01-12 |
| URL | http://arxiv.org/abs/1601.02970v1 |
| http://arxiv.org/pdf/1601.02970v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-predict-hierarchical |
| Repo | |
| Framework | |
Accelerating Stochastic Composition Optimization
| Title | Accelerating Stochastic Composition Optimization |
| Authors | Mengdi Wang, Ji Liu, Ethan X. Fang |
| Abstract | Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using two different timescales. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optimal sample-error complexity in several important special cases. We further demonstrate the application of ASC-PG to reinforcement learning and conduct numerical experiments. |
| Tasks | |
| Published | 2016-07-25 |
| URL | http://arxiv.org/abs/1607.07329v1 |
| http://arxiv.org/pdf/1607.07329v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-stochastic-composition |
| Repo | |
| Framework | |
Application of Multifractal Analysis to Segmentation of Water Bodies in Optical and Synthetic Aperture Radar Satellite Images
| Title | Application of Multifractal Analysis to Segmentation of Water Bodies in Optical and Synthetic Aperture Radar Satellite Images |
| Authors | Victor Manuel San Martin, Alejandra Figliola |
| Abstract | A method for segmenting water bodies in optical and synthetic aperture radar (SAR) satellite images is proposed. It makes use of the textural features of the different regions in the image for segmentation. The method consists in a multiscale analysis of the images, which allows us to study the images regularity both, locally and globally. As results of the analysis, coarse multifractal spectra of studied images and a group of images that associates each position (pixel) with its corresponding value of local regularity (or singularity) spectrum are obtained. Thresholds are then applied to the multifractal spectra of the images for the classification. These thresholds are selected after studying the characteristics of the spectra under the assumption that water bodies have larger local regularity than other soil types. Classifications obtained by the multifractal method are compared quantitatively with those obtained by neural networks trained to classify the pixels of the images in covered against uncovered by water. In optical images, the classifications are also compared with those derived using the so-called Normalized Differential Water Index (NDWI). |
| Tasks | |
| Published | 2016-04-08 |
| URL | http://arxiv.org/abs/1604.02488v1 |
| http://arxiv.org/pdf/1604.02488v1.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-multifractal-analysis-to |
| Repo | |
| Framework | |
Supervised quantum gate “teaching” for quantum hardware design
| Title | Supervised quantum gate “teaching” for quantum hardware design |
| Authors | Leonardo Banchi, Nicola Pancotti, Sougato Bose |
| Abstract | We show how to train a quantum network of pairwise interacting qubits such that its evolution implements a target quantum algorithm into a given network subset. Our strategy is inspired by supervised learning and is designed to help the physical construction of a quantum computer which operates with minimal external classical control. |
| Tasks | |
| Published | 2016-07-20 |
| URL | http://arxiv.org/abs/1607.06146v1 |
| http://arxiv.org/pdf/1607.06146v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-quantum-gate-teaching-for-quantum |
| Repo | |
| Framework | |
Robust training on approximated minimal-entropy set
| Title | Robust training on approximated minimal-entropy set |
| Authors | Tianpei Xie, Nasser. M. Narabadi, Alfred O. Hero |
| Abstract | In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling the false alarm rate associated with anomalous samples. By incorporating a non-parametric regularizer based on an empirical entropy estimator, we propose a Geometric-Entropy-Minimization regularized Maximum Entropy Discrimination (GEM-MED) method to learn to classify and detect anomalies in a joint manner. We demonstrate using simulated data and a real multimodal data set. Our GEM-MED method can yield improved performance over previous robust classification methods in terms of both classification accuracy and anomaly detection rate. |
| Tasks | Anomaly Detection |
| Published | 2016-10-21 |
| URL | http://arxiv.org/abs/1610.06806v1 |
| http://arxiv.org/pdf/1610.06806v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-training-on-approximated-minimal |
| Repo | |
| Framework | |
Selfie Detection by Synergy-Constraint Based Convolutional Neural Network
| Title | Selfie Detection by Synergy-Constraint Based Convolutional Neural Network |
| Authors | Yashas Annadani, Vijayakrishna Naganoor, Akshay Kumar Jagadish, Krishnan Chemmangat |
| Abstract | Categorisation of huge amount of data on the multimedia platform is a crucial task. In this work, we propose a novel approach to address the subtle problem of selfie detection for image database segregation on the web, given rapid rise in number of selfies clicked. A Convolutional Neural Network (CNN) is modeled to learn a synergy feature in the common subspace of head and shoulder orientation, derived from Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) features respectively. This synergy was captured by projecting the aforementioned features using Canonical Correlation Analysis (CCA). We show that the resulting network’s convolutional activations in the neighbourhood of spatial keypoints captured by SIFT are discriminative for selfie-detection. In general, proposed approach aids in capturing intricacies present in the image data and has the potential for usage in other subtle image analysis scenarios apart from just selfie detection. We investigate and analyse the performance of popular CNN architectures (GoogleNet, AlexNet), used for other image classification tasks, when subjected to the task of detecting the selfies on the multimedia platform. The results of the proposed approach are compared with these popular architectures on a dataset of ninety thousand images comprising of roughly equal number of selfies and non-selfies. Experimental results on this dataset shows the effectiveness of the proposed approach. |
| Tasks | Image Classification |
| Published | 2016-11-14 |
| URL | http://arxiv.org/abs/1611.04357v1 |
| http://arxiv.org/pdf/1611.04357v1.pdf | |
| PWC | https://paperswithcode.com/paper/selfie-detection-by-synergy-constraint-based |
| Repo | |
| Framework | |
Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding
| Title | Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding |
| Authors | J. Krishna Murthy, G. V. Sai Krishna, Falak Chhaya, K. Madhava Krishna |
| Abstract | We present an approach for reconstructing vehicles from a single (RGB) image, in the context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to an image can be used to reason about the reverse process, i.e., how shapes (back-)project from 2D to 3D. We encode this knowledge in \emph{shape priors}, which are learnt over a small keypoint-annotated dataset. We then formulate a shape-aware adjustment problem that uses the learnt shape priors to recover the 3D pose and shape of a query object from an image. For shape representation and inference, we leverage recent successes of Convolutional Neural Networks (CNNs) for the task of object and keypoint localization, and train a novel cascaded fully-convolutional architecture to localize vehicle \emph{keypoints} in images. The shape-aware adjustment then robustly recovers shape (3D locations of the detected keypoints) while simultaneously filling in occluded keypoints. To tackle estimation errors incurred due to erroneously detected keypoints, we use an Iteratively Re-weighted Least Squares (IRLS) scheme for robust optimization, and as a by-product characterize noise models for each predicted keypoint. We evaluate our approach on autonomous driving benchmarks, and present superior results to existing monocular, as well as stereo approaches. |
| Tasks | Autonomous Driving, Scene Understanding |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09468v1 |
| http://arxiv.org/pdf/1609.09468v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconstructing-vechicles-from-a-single-image |
| Repo | |
| Framework | |
Relative Natural Gradient for Learning Large Complex Models
| Title | Relative Natural Gradient for Learning Large Complex Models |
| Authors | Ke Sun, Frank Nielsen |
| Abstract | Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks. However related analysis becomes more and more difficult as the learner’s structure turns large and complex. This paper makes a preliminary step towards a new direction. We extract a local component of a large neuron system, and defines its relative Fisher information metric that describes accurately this small component, and is invariant to the other parts of the system. This concept is important because the geometry structure is much simplified and it can be easily applied to guide the learning of neural networks. We provide an analysis on a list of commonly used components, and demonstrate how to use this concept to further improve optimization. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06069v1 |
| http://arxiv.org/pdf/1606.06069v1.pdf | |
| PWC | https://paperswithcode.com/paper/relative-natural-gradient-for-learning-large |
| Repo | |
| Framework | |
Cross-Modal Scene Networks
| Title | Cross-Modal Scene Networks |
| Authors | Yusuf Aytar, Lluis Castrejon, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba |
| Abstract | People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality. |
| Tasks | |
| Published | 2016-10-27 |
| URL | http://arxiv.org/abs/1610.09003v1 |
| http://arxiv.org/pdf/1610.09003v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-scene-networks |
| Repo | |
| Framework | |
Iterative Aggregation Method for Solving Principal Component Analysis Problems
| Title | Iterative Aggregation Method for Solving Principal Component Analysis Problems |
| Authors | Vitaly Bulgakov |
| Abstract | Motivated by the previously developed multilevel aggregation method for solving structural analysis problems a novel two-level aggregation approach for efficient iterative solution of Principal Component Analysis (PCA) problems is proposed. The course aggregation model of the original covariance matrix is used in the iterative solution of the eigenvalue problem by a power iterations method. The method is tested on several data sets consisting of large number of text documents. |
| Tasks | |
| Published | 2016-02-29 |
| URL | http://arxiv.org/abs/1602.08800v1 |
| http://arxiv.org/pdf/1602.08800v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-aggregation-method-for-solving |
| Repo | |
| Framework | |
Geometry-Based Next Frame Prediction from Monocular Video
| Title | Geometry-Based Next Frame Prediction from Monocular Video |
| Authors | Reza Mahjourian, Martin Wicke, Anelia Angelova |
| Abstract | We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocular video input, which, along with the current video image and the camera trajectory, can then be used to compute the next frame. Unlike prior next-frame prediction approaches, we take advantage of the scene geometry and use the predicted depth for generating the next frame prediction. Our approach can produce rich next frame predictions which include depth information attached to each pixel. Another novel aspect of our approach is that it predicts depth from a sequence of images (e.g. in a video), rather than from a single still image. We evaluate the proposed approach on the KITTI dataset, a standard dataset for benchmarking tasks relevant to autonomous driving. The proposed method produces results which are visually and numerically superior to existing methods that directly predict the next frame. We show that the accuracy of depth prediction improves as more prior frames are considered. |
| Tasks | Autonomous Driving, Depth Estimation |
| Published | 2016-09-20 |
| URL | http://arxiv.org/abs/1609.06377v2 |
| http://arxiv.org/pdf/1609.06377v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-based-next-frame-prediction-from |
| Repo | |
| Framework | |
