Paper Group ANR 335
On Multiplicative Multitask Feature Learning. High-Performance Computing for Scheduling Decision Support: A Parallel Depth-First Search Heuristic. Caveats on Bayesian and hidden-Markov models (v2.8). Analyzing the Affect of a Group of People Using Multi-modal Framework. Non-linear Dimensionality Regularizer for Solving Inverse Problems. Incremental …
On Multiplicative Multitask Feature Learning
| Title | On Multiplicative Multitask Feature Learning |
| Authors | Xin Wang, Jinbo Bi, Shipeng Yu, Jiangwen Sun |
| Abstract | We investigate a general framework of multiplicative multitask feature learning which decomposes each task’s model parameters into a multiplication of two components. One of the components is used across all tasks and the other component is task-specific. Several previous methods have been proposed as special cases of our framework. We study the theoretical properties of this framework when different regularization conditions are applied to the two decomposed components. We prove that this framework is mathematically equivalent to the widely used multitask feature learning methods that are based on a joint regularization of all model parameters, but with a more general form of regularizers. Further, an analytical formula is derived for the across-task component as related to the task-specific component for all these regularizers, leading to a better understanding of the shrinkage effect. Study of this framework motivates new multitask learning algorithms. We propose two new learning formulations by varying the parameters in the proposed framework. Empirical studies have revealed the relative advantages of the two new formulations by comparing with the state of the art, which provides instructive insights into the feature learning problem with multiple tasks. |
| Tasks | |
| Published | 2016-10-24 |
| URL | http://arxiv.org/abs/1610.07563v1 |
| http://arxiv.org/pdf/1610.07563v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-multiplicative-multitask-feature-learning |
| Repo | |
| Framework | |
High-Performance Computing for Scheduling Decision Support: A Parallel Depth-First Search Heuristic
| Title | High-Performance Computing for Scheduling Decision Support: A Parallel Depth-First Search Heuristic |
| Authors | Gerhard Rauchecker, Guido Schryen |
| Abstract | Many academic disciplines - including information systems, computer science, and operations management - face scheduling problems as important decision making tasks. Since many scheduling problems are NP-hard in the strong sense, there is a need for developing solution heuristics. For scheduling problems with setup times on unrelated parallel machines, there is limited research on solution methods and to the best of our knowledge, parallel computer architectures have not yet been taken advantage of. We address this gap by proposing and implementing a new solution heuristic and by testing different parallelization strategies. In our computational experiments, we show that our heuristic calculates near-optimal solutions even for large instances and that computing time can be reduced substantially by our parallelization approach. |
| Tasks | Decision Making |
| Published | 2016-05-16 |
| URL | http://arxiv.org/abs/1605.04682v1 |
| http://arxiv.org/pdf/1605.04682v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-performance-computing-for-scheduling |
| Repo | |
| Framework | |
Caveats on Bayesian and hidden-Markov models (v2.8)
| Title | Caveats on Bayesian and hidden-Markov models (v2.8) |
| Authors | Lambert Schomaker |
| Abstract | This paper describes a number of fundamental and practical problems in the application of hidden-Markov models and Bayes when applied to cursive-script recognition. Several problems, however, will have an effect in other application areas. The most fundamental problem is the propagation of error in the product of probabilities. This is a common and pervasive problem which deserves more attention. On the basis of Monte Carlo modeling, tables for the expected relative error are given. It seems that it is distributed according to a continuous Poisson distribution over log probabilities. A second essential problem is related to the appropriateness of the Markov assumption. Basic tests will reveal whether a problem requires modeling of the stochastics of seriality, at all. Examples are given of lexical encodings which cover 95-99% classification accuracy of a lexicon, with removed sequence information, for several European languages. Finally, a summary of results on a non- Bayes, non-Markov method in handwriting recognition are presented, with very acceptable results and minimal modeling or training requirements using nearest-mean classification. |
| Tasks | |
| Published | 2016-08-18 |
| URL | http://arxiv.org/abs/1608.05277v3 |
| http://arxiv.org/pdf/1608.05277v3.pdf | |
| PWC | https://paperswithcode.com/paper/caveats-on-bayesian-and-hidden-markov-models |
| Repo | |
| Framework | |
Analyzing the Affect of a Group of People Using Multi-modal Framework
| Title | Analyzing the Affect of a Group of People Using Multi-modal Framework |
| Authors | Xiaohua Huang, Abhinav Dhall, Xin Liu, Guoying Zhao, Jingang Shi, Roland Goecke, Matti Pietikainen |
| Abstract | Millions of images on the web enable us to explore images from social events such as a family party, thus it is of interest to understand and model the affect exhibited by a group of people in images. But analysis of the affect expressed by multiple people is challenging due to varied indoor and outdoor settings, and interactions taking place between various numbers of people. A few existing works on Group-level Emotion Recognition (GER) have investigated on face-level information. Due to the challenging environments, face may not provide enough information to GER. Relatively few studies have investigated multi-modal GER. Therefore, we propose a novel multi-modal approach based on a new feature description for understanding emotional state of a group of people in an image. In this paper, we firstly exploit three kinds of rich information containing face, upperbody and scene in a group-level image. Furthermore, in order to integrate multiple person’s information in a group-level image, we propose an information aggregation method to generate three features for face, upperbody and scene, respectively. We fuse face, upperbody and scene information for robustness of GER against the challenging environments. Intensive experiments are performed on two challenging group-level emotion databases to investigate the role of face, upperbody and scene as well as multi-modal framework. Experimental results demonstrate that our framework achieves very promising performance for GER. |
| Tasks | Emotion Recognition |
| Published | 2016-10-12 |
| URL | http://arxiv.org/abs/1610.03640v2 |
| http://arxiv.org/pdf/1610.03640v2.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-the-affect-of-a-group-of-people |
| Repo | |
| Framework | |
Non-linear Dimensionality Regularizer for Solving Inverse Problems
| Title | Non-linear Dimensionality Regularizer for Solving Inverse Problems |
| Authors | Ravi Garg, Anders Eriksson, Ian Reid |
| Abstract | Consider an ill-posed inverse problem of estimating causal factors from observations, one of which is known to lie near some (un- known) low-dimensional, non-linear manifold expressed by a predefined Mercer-kernel. Solving this problem requires simultaneous estimation of these factors and learning the low-dimensional representation for them. In this work, we introduce a novel non-linear dimensionality regulariza- tion technique for solving such problems without pre-training. We re-formulate Kernel-PCA as an energy minimization problem in which low dimensionality constraints are introduced as regularization terms in the energy. To the best of our knowledge, ours is the first at- tempt to create a dimensionality regularizer in the KPCA framework. Our approach relies on robustly penalizing the rank of the recovered fac- tors directly in the implicit feature space to create their low-dimensional approximations in closed form. Our approach performs robust KPCA in the presence of missing data and noise. We demonstrate state-of-the-art results on predicting missing entries in the standard oil flow dataset. Additionally, we evaluate our method on the challenging problem of Non-Rigid Structure from Motion and our approach delivers promising results on CMU mocap dataset despite the presence of significant occlusions and noise. |
| Tasks | |
| Published | 2016-03-16 |
| URL | http://arxiv.org/abs/1603.05015v1 |
| http://arxiv.org/pdf/1603.05015v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-linear-dimensionality-regularizer-for |
| Repo | |
| Framework | |
Incremental Spectral Sparsification for Large-Scale Graph-Based Semi-Supervised Learning
| Title | Incremental Spectral Sparsification for Large-Scale Graph-Based Semi-Supervised Learning |
| Authors | Daniele Calandriello, Alessandro Lazaric, Michal Valko, Ioannis Koutis |
| Abstract | While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scalable methods, such as the eigenfunction method focus on efficiently approximating the whole spectrum of the graph Laplacian constructed from the data. This is in contrast to various subsampling and quantization methods proposed in the past, which may fail in preserving the graph spectra. However, the impact of the approximation of the spectrum on the final generalization error is either unknown, or requires strong assumptions on the data. In this paper, we introduce Sparse-HFS, an efficient edge-sparsification algorithm for SSL. By constructing an edge-sparse and spectrally similar graph, we are able to leverage the approximation guarantees of spectral sparsification methods to bound the generalization error of Sparse-HFS. As a result, we obtain a theoretically-grounded approximation scheme for graph-based SSL that also empirically matches the performance of known large-scale methods. |
| Tasks | Quantization |
| Published | 2016-01-21 |
| URL | http://arxiv.org/abs/1601.05675v1 |
| http://arxiv.org/pdf/1601.05675v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-spectral-sparsification-for-large |
| Repo | |
| Framework | |
Upper Bound of Bayesian Generalization Error in Non-negative Matrix Factorization
| Title | Upper Bound of Bayesian Generalization Error in Non-negative Matrix Factorization |
| Authors | Naoki Hayashi, Sumio Watanabe |
| Abstract | Non-negative matrix factorization (NMF) is a new knowledge discovery method that is used for text mining, signal processing, bioinformatics, and consumer analysis. However, its basic property as a learning machine is not yet clarified, as it is not a regular statistical model, resulting that theoretical optimization method of NMF has not yet established. In this paper, we study the real log canonical threshold of NMF and give an upper bound of the generalization error in Bayesian learning. The results show that the generalization error of the matrix factorization can be made smaller than regular statistical models if Bayesian learning is applied. |
| Tasks | |
| Published | 2016-12-13 |
| URL | http://arxiv.org/abs/1612.04112v5 |
| http://arxiv.org/pdf/1612.04112v5.pdf | |
| PWC | https://paperswithcode.com/paper/upper-bound-of-bayesian-generalization-error |
| Repo | |
| Framework | |
Data-driven Rank Breaking for Efficient Rank Aggregation
| Title | Data-driven Rank Breaking for Efficient Rank Aggregation |
| Authors | Ashish Khetan, Sewoong Oh |
| Abstract | Rank aggregation systems collect ordinal preferences from individuals to produce a global ranking that represents the social preference. Rank-breaking is a common practice to reduce the computational complexity of learning the global ranking. The individual preferences are broken into pairwise comparisons and applied to efficient algorithms tailored for independent paired comparisons. However, due to the ignored dependencies in the data, naive rank-breaking approaches can result in inconsistent estimates. The key idea to produce accurate and consistent estimates is to treat the pairwise comparisons unequally, depending on the topology of the collected data. In this paper, we provide the optimal rank-breaking estimator, which not only achieves consistency but also achieves the best error bound. This allows us to characterize the fundamental tradeoff between accuracy and complexity. Further, the analysis identifies how the accuracy depends on the spectral gap of a corresponding comparison graph. |
| Tasks | |
| Published | 2016-01-21 |
| URL | http://arxiv.org/abs/1601.05495v2 |
| http://arxiv.org/pdf/1601.05495v2.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-rank-breaking-for-efficient-rank |
| Repo | |
| Framework | |
Vision-based Engagement Detection in Virtual Reality
| Title | Vision-based Engagement Detection in Virtual Reality |
| Authors | Ghassem Tofighi, Kaamraan Raahemifar, Maria Frank, Haisong Gu |
| Abstract | User engagement modeling for manipulating actions in vision-based interfaces is one of the most important case studies of user mental state detection. In a Virtual Reality environment that employs camera sensors to recognize human activities, we have to know when user intends to perform an action and when not. Without a proper algorithm for recognizing engagement status, any kind of activities could be interpreted as manipulating actions, called “Midas Touch” problem. Baseline approach for solving this problem is activating gesture recognition system using some focus gestures such as waiving or raising hand. However, a desirable natural user interface should be able to understand user’s mental status automatically. In this paper, a novel multi-modal model for engagement detection, DAIA, is presented. using DAIA, the spectrum of mental status for performing an action is quantized in a finite number of engagement states. For this purpose, a Finite State Transducer (FST) is designed. This engagement framework shows how to integrate multi-modal information from user biometric data streams such as 2D and 3D imaging. FST is employed to make the state transition smoothly using combination of several boolean expressions. Our FST true detection rate is 92.3% in total for four different states. Results also show FST can segment user hand gestures more robustly. |
| Tasks | Gesture Recognition |
| Published | 2016-09-05 |
| URL | http://arxiv.org/abs/1609.01344v1 |
| http://arxiv.org/pdf/1609.01344v1.pdf | |
| PWC | https://paperswithcode.com/paper/vision-based-engagement-detection-in-virtual |
| Repo | |
| Framework | |
Trajectory Aligned Features For First Person Action Recognition
| Title | Trajectory Aligned Features For First Person Action Recognition |
| Authors | Suriya Singh, Chetan Arora, C. V. Jawahar |
| Abstract | Egocentric videos are characterised by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. Recognizing action of the wearer from egocentric videos is an important problem. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video. We propose a novel representation of the first person actions derived from feature trajectories. The features are simple to compute using standard point tracking and does not assume segmentation of hand/objects or recognizing object or hand pose unlike in many previous approaches. We train a bag of words classifier with the proposed features and report a performance improvement of more than 11% on publicly available datasets. Although not designed for the particular case, we show that our technique can also recognize wearer’s actions when hands or objects are not visible. |
| Tasks | Temporal Action Localization |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.02115v1 |
| http://arxiv.org/pdf/1604.02115v1.pdf | |
| PWC | https://paperswithcode.com/paper/trajectory-aligned-features-for-first-person |
| Repo | |
| Framework | |
Online and Differentially-Private Tensor Decomposition
| Title | Online and Differentially-Private Tensor Decomposition |
| Authors | Yining Wang, Animashree Anandkumar |
| Abstract | In this paper, we resolve many of the key algorithmic questions regarding robustness, memory efficiency, and differential privacy of tensor decomposition. We propose simple variants of the tensor power method which enjoy these strong properties. We present the first guarantees for online tensor power method which has a linear memory requirement. Moreover, we present a noise calibrated tensor power method with efficient privacy guarantees. At the heart of all these guarantees lies a careful perturbation analysis derived in this paper which improves up on the existing results significantly. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06237v4 |
| http://arxiv.org/pdf/1606.06237v4.pdf | |
| PWC | https://paperswithcode.com/paper/online-and-differentially-private-tensor |
| Repo | |
| Framework | |
Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation
| Title | Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiation |
| Authors | James Townsend, Niklas Koep, Sebastian Weichwald |
| Abstract | Optimization on manifolds is a class of methods for optimization of an objective function, subject to constraints which are smooth, in the sense that the set of points which satisfy the constraints admits the structure of a differentiable manifold. While many optimization problems are of the described form, technicalities of differential geometry and the laborious calculation of derivatives pose a significant barrier for experimenting with these methods. We introduce Pymanopt (available at https://pymanopt.github.io), a toolbox for optimization on manifolds, implemented in Python, that—similarly to the Manopt Matlab toolbox—implements several manifold geometries and optimization algorithms. Moreover, we lower the barriers to users further by using automated differentiation for calculating derivative information, saving users time and saving them from potential calculation and implementation errors. |
| Tasks | |
| Published | 2016-03-10 |
| URL | http://arxiv.org/abs/1603.03236v4 |
| http://arxiv.org/pdf/1603.03236v4.pdf | |
| PWC | https://paperswithcode.com/paper/pymanopt-a-python-toolbox-for-optimization-on |
| Repo | |
| Framework | |
A MAP-MRF filter for phase-sensitive coil combination in autocalibrating partially parallel susceptibility weighted MRI
| Title | A MAP-MRF filter for phase-sensitive coil combination in autocalibrating partially parallel susceptibility weighted MRI |
| Authors | Sreekanth Madhusoodhanan, Joseph Suresh Paul |
| Abstract | A statistical approach for combination of channel phases is developed for optimizing the Contrast-to-Noise Ratio (CNR) in Susceptibility Weighted Images (SWI) acquired using autocalibrating partially parallel techniques. The unwrapped phase images of each coil are filtered using local random field based probabilistic weights, derived using energy functions representative of noisy sensitivity and tissue information pertaining to venous structure in the individual channel phase images. The channel energy functions are obtained as functions of local image intensities, first or second order clique phase difference and a threshold scaling parameter dependent on the input noise level. Whereas the expectation of the individual energy functions with respect to the noise distribution in clique phase differences is to be maximized for optimal filtering, the expectation of tissue energy function decreases and noise energy function increases with increase in threshold scale parameter. The optimum scaling parameter is shown to occur at the point where expectations of both energy functions contribute to the largest possible extent. It is shown that implementation of the filter in the same lines as that of Iterated Conditional Modes (ICM) algorithm provides structural enhancement in the coil combined phase, with reduced noise amplification. Application to simulated and in vivo multi-channel SWI shows that CNR of combined phase obtained using MAP-MRF filter is higher as compared to that of coil combination using weighted average. |
| Tasks | |
| Published | 2016-10-29 |
| URL | http://arxiv.org/abs/1610.09498v1 |
| http://arxiv.org/pdf/1610.09498v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-map-mrf-filter-for-phase-sensitive-coil |
| Repo | |
| Framework | |
Towards automatic pulmonary nodule management in lung cancer screening with deep learning
| Title | Towards automatic pulmonary nodule management in lung cancer screening with deep learning |
| Authors | Francesco Ciompi, Kaman Chung, Sarah J. van Riel, Arnaud Arindra Adiyoso Setio, Paul K. Gerke, Colin Jacobs, Ernst Th. Scholten, Cornelia Schaefer-Prokop, Mathilde M. W. Wille, Alfonso Marchiano, Ugo Pastorino, Mathias Prokop, Bram van Ginneken |
| Abstract | The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers. |
| Tasks | |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09157v2 |
| http://arxiv.org/pdf/1610.09157v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automatic-pulmonary-nodule-management |
| Repo | |
| Framework | |
One Sentence One Model for Neural Machine Translation
| Title | One Sentence One Model for Neural Machine Translation |
| Authors | Xiaoqing Li, Jiajun Zhang, Chengqing Zong |
| Abstract | Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is used to translate all the test sentences. We argue that the general fixed network cannot best fit the specific test sentences. In this paper, we propose the dynamic NMT which learns a general network as usual, and then fine-tunes the network for each test sentence. The fine-tune work is done on a small set of the bilingual training data that is obtained through similarity search according to the test sentence. Extensive experiments demonstrate that this method can significantly improve the translation performance, especially when highly similar sentences are available. |
| Tasks | Machine Translation |
| Published | 2016-09-21 |
| URL | http://arxiv.org/abs/1609.06490v1 |
| http://arxiv.org/pdf/1609.06490v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-sentence-one-model-for-neural-machine |
| Repo | |
| Framework | |
