Paper Group ANR 321
Wearable Vision Detection of Environmental Fall Risks using Convolutional Neural Networks. Flows Generating Nonlinear Eigenfunctions. Simultaneous Food Localization and Recognition. Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics. Can Boosting with SVM as Week Learners Help?. Linearized GMM Kernels and Norma …
Wearable Vision Detection of Environmental Fall Risks using Convolutional Neural Networks
| Title | Wearable Vision Detection of Environmental Fall Risks using Convolutional Neural Networks |
| Authors | Mina Nouredanesh, Andrew McCormick, Sunil L. Kukreja, James Tung |
| Abstract | In this paper, a method to detect environmental hazards related to a fall risk using a mobile vision system is proposed. First-person perspective videos are proposed to provide objective evidence on cause and circumstances of perturbed balance during activities of daily living, targeted to seniors. A classification problem was defined with 12 total classes of potential fall risks, including slope changes (e.g., stairs, curbs, ramps) and surfaces (e.g., gravel, grass, concrete). Data was collected using a chest-mounted GoPro camera. We developed a convolutional neural network for automatic feature extraction, reduction, and classification of frames. Initial results, with a mean square error of 8%, are promising. |
| Tasks | |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00684v1 |
| http://arxiv.org/pdf/1611.00684v1.pdf | |
| PWC | https://paperswithcode.com/paper/wearable-vision-detection-of-environmental |
| Repo | |
| Framework | |
Flows Generating Nonlinear Eigenfunctions
| Title | Flows Generating Nonlinear Eigenfunctions |
| Authors | Raz Z. Nossek, Guy Gilboa |
| Abstract | Nonlinear variational methods have become very powerful tools for many image processing tasks. Recently a new line of research has emerged, dealing with nonlinear eigenfunctions induced by convex functionals. This has provided new insights and better theoretical understanding of convex regularization and introduced new processing methods. However, the theory of nonlinear eigenvalue problems is still at its infancy. We present a new flow that can generate nonlinear eigenfunctions of the form $T(u)=\lambda u$, where $T(u)$ is a nonlinear operator and $\lambda \in \mathbb{R} $ is the eigenvalue. We develop the theory where $T(u)$ is a subgradient element of a regularizing one-homogeneous functional, such as total-variation (TV) or total-generalized-variation (TGV). We introduce two flows: a forward flow and an inverse flow; for which the steady state solution is a nonlinear eigenfunction. The forward flow monotonically smooths the solution (with respect to the regularizer) and simultaneously increases the $L^2$ norm. The inverse flow has the opposite characteristics. For both flows, the steady state depends on the initial condition, thus different initial conditions yield different eigenfunctions. This enables a deeper investigation into the space of nonlinear eigenfunctions, allowing to produce numerically diverse examples, which may be unknown yet. In addition we suggest an indicator to measure the affinity of a function to an eigenfunction and relate it to pseudo-eigenfunctions in the linear case. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08438v1 |
| http://arxiv.org/pdf/1609.08438v1.pdf | |
| PWC | https://paperswithcode.com/paper/flows-generating-nonlinear-eigenfunctions |
| Repo | |
| Framework | |
Simultaneous Food Localization and Recognition
| Title | Simultaneous Food Localization and Recognition |
| Authors | Marc Bolaños, Petia Radeva |
| Abstract | The development of automatic nutrition diaries, which would allow to keep track objectively of everything we eat, could enable a whole new world of possibilities for people concerned about their nutrition patterns. With this purpose, in this paper we propose the first method for simultaneous food localization and recognition. Our method is based on two main steps, which consist in, first, produce a food activation map on the input image (i.e. heat map of probabilities) for generating bounding boxes proposals and, second, recognize each of the food types or food-related objects present in each bounding box. We demonstrate that our proposal, compared to the most similar problem nowadays - object localization, is able to obtain high precision and reasonable recall levels with only a few bounding boxes. Furthermore, we show that it is applicable to both conventional and egocentric images. |
| Tasks | Object Localization |
| Published | 2016-04-27 |
| URL | http://arxiv.org/abs/1604.07953v2 |
| http://arxiv.org/pdf/1604.07953v2.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-food-localization-and |
| Repo | |
| Framework | |
Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics
| Title | Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics |
| Authors | Nannan Wang, Jie Li, Leiyu Sun, Bin Song, Xinbo Gao |
| Abstract | Face sketch synthesis has wide applications ranging from digital entertainments to law enforcements. Objective image quality assessment scores and face recognition accuracy are two mainly used tools to evaluate the synthesis performance. In this paper, we proposed a synthesized face sketch recognition framework based on full-reference image quality assessment metrics. Synthesized sketches generated from four state-of-the-art methods are utilized to test the performance of the proposed recognition framework. For the image quality assessment metrics, we employed the classical structured similarity index metric and other three prevalent metrics: visual information fidelity, feature similarity index metric and gradient magnitude similarity deviation. Extensive experiments compared with baseline methods illustrate the effectiveness of the proposed synthesized face sketch recognition framework. Data and implementation code in this paper are available online at www.ihitworld.com/WNN/IQA_Sketch.zip. |
| Tasks | Face Recognition, Face Sketch Synthesis, Image Quality Assessment, Sketch Recognition |
| Published | 2016-03-25 |
| URL | http://arxiv.org/abs/1603.07823v1 |
| http://arxiv.org/pdf/1603.07823v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-free-synthesized-face-sketch |
| Repo | |
| Framework | |
Can Boosting with SVM as Week Learners Help?
| Title | Can Boosting with SVM as Week Learners Help? |
| Authors | Dinesh Govindaraj |
| Abstract | Object recognition in images involves identifying objects with partial occlusions, viewpoint changes, varying illumination, cluttered backgrounds. Recent work in object recognition uses machine learning techniques SVM-KNN, Local Ensemble Kernel Learning, Multiple Kernel Learning. In this paper, we want to utilize SVM as week learners in AdaBoost. Experiments are done with classifiers like near- est neighbor, k-nearest neighbor, Support vector machines, Local learning(SVM- KNN) and AdaBoost. Models use Scale-Invariant descriptors and Pyramid his- togram of gradient descriptors. AdaBoost is trained with set of week classifier as SVMs, each with kernel distance function on different descriptors. Results shows AdaBoost with SVM outperform other methods for Object Categorization dataset. |
| Tasks | Object Recognition |
| Published | 2016-04-18 |
| URL | http://arxiv.org/abs/1604.05242v2 |
| http://arxiv.org/pdf/1604.05242v2.pdf | |
| PWC | https://paperswithcode.com/paper/can-boosting-with-svm-as-week-learners-help |
| Repo | |
| Framework | |
Linearized GMM Kernels and Normalized Random Fourier Features
| Title | Linearized GMM Kernels and Normalized Random Fourier Features |
| Authors | Ping Li |
| Abstract | The method of “random Fourier features (RFF)” has become a popular tool for approximating the “radial basis function (RBF)” kernel. The variance of RFF is actually large. Interestingly, the variance can be substantially reduced by a simple normalization step as we theoretically demonstrate. We name the improved scheme as the “normalized RFF (NRFF)". We also propose the “generalized min-max (GMM)” kernel as a measure of data similarity. GMM is positive definite as there is an associated hashing method named “generalized consistent weighted sampling (GCWS)” which linearizes this nonlinear kernel. We provide an extensive empirical evaluation of the RBF kernel and the GMM kernel on more than 50 publicly available datasets. For a majority of the datasets, the (tuning-free) GMM kernel outperforms the best-tuned RBF kernel. We conduct extensive experiments for comparing the linearized RBF kernel using NRFF with the linearized GMM kernel using GCWS. We observe that, to reach a comparable classification accuracy, GCWS typically requires substantially fewer samples than NRFF, even on datasets where the original RBF kernel outperforms the original GMM kernel. The empirical success of GCWS (compared to NRFF) can also be explained from a theoretical perspective. Firstly, the relative variance (normalized by the squared expectation) of GCWS is substantially smaller than that of NRFF, except for the very high similarity region (where the variances of both methods are close to zero). Secondly, if we make a model assumption on the data, we can show analytically that GCWS exhibits much smaller variance than NRFF for estimating the same object (e.g., the RBF kernel), except for the very high similarity region. |
| Tasks | |
| Published | 2016-05-18 |
| URL | http://arxiv.org/abs/1605.05721v4 |
| http://arxiv.org/pdf/1605.05721v4.pdf | |
| PWC | https://paperswithcode.com/paper/linearized-gmm-kernels-and-normalized-random |
| Repo | |
| Framework | |
An Online Mechanism for Ridesharing in Autonomous Mobility-on-Demand Systems
| Title | An Online Mechanism for Ridesharing in Autonomous Mobility-on-Demand Systems |
| Authors | Wen Shen, Cristina V. Lopes, Jacob W. Crandall |
| Abstract | With proper management, Autonomous Mobility-on-Demand (AMoD) systems have great potential to satisfy the transport demands of urban populations by providing safe, convenient, and affordable ridesharing services. Meanwhile, such systems can substantially decrease private car ownership and use, and thus significantly reduce traffic congestion, energy consumption, and carbon emissions. To achieve this objective, an AMoD system requires private information about the demand from passengers. However, due to self-interestedness, passengers are unlikely to cooperate with the service providers in this regard. Therefore, an online mechanism is desirable if it incentivizes passengers to truthfully report their actual demand. For the purpose of promoting ridesharing, we hereby introduce a posted-price, integrated online ridesharing mechanism (IORS) that satisfies desirable properties such as ex-post incentive compatibility, individual rationality, and budget-balance. Numerical results indicate the competitiveness of IORS compared with two benchmarks, namely the optimal assignment and an offline, auction-based mechanism. |
| Tasks | |
| Published | 2016-03-07 |
| URL | http://arxiv.org/abs/1603.02208v3 |
| http://arxiv.org/pdf/1603.02208v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-mechanism-for-ridesharing-in |
| Repo | |
| Framework | |
The Upper Bound on Knots in Neural Networks
| Title | The Upper Bound on Knots in Neural Networks |
| Authors | Kevin K. Chen |
| Abstract | Neural networks with rectified linear unit activations are essentially multivariate linear splines. As such, one of many ways to measure the “complexity” or “expressivity” of a neural network is to count the number of knots in the spline model. We study the number of knots in fully-connected feedforward neural networks with rectified linear unit activation functions. We intentionally keep the neural networks very simple, so as to make theoretical analyses more approachable. An induction on the number of layers $l$ reveals a tight upper bound on the number of knots in $\mathbb{R} \to \mathbb{R}^p$ deep neural networks. With $n_i \gg 1$ neurons in layer $i = 1, \dots, l$, the upper bound is approximately $n_1 \dots n_l$. We then show that the exact upper bound is tight, and we demonstrate the upper bound with an example. The purpose of these analyses is to pave a path for understanding the behavior of general $\mathbb{R}^q \to \mathbb{R}^p$ neural networks. |
| Tasks | |
| Published | 2016-11-29 |
| URL | http://arxiv.org/abs/1611.09448v2 |
| http://arxiv.org/pdf/1611.09448v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-upper-bound-on-knots-in-neural-networks |
| Repo | |
| Framework | |
Comparing Apples and Oranges: Two Examples of the Limits of Statistical Inference, With an Application to Google Advertising Markets
| Title | Comparing Apples and Oranges: Two Examples of the Limits of Statistical Inference, With an Application to Google Advertising Markets |
| Authors | John Mount, Nina Zumel |
| Abstract | We show how the classic Cramer-Rao bound limits how accurately one can simultaneously estimate values of a large number of Google Ad campaigns (or similarly limit the measurement rate of many confounding A/B tests). |
| Tasks | |
| Published | 2016-11-30 |
| URL | http://arxiv.org/abs/1611.10331v1 |
| http://arxiv.org/pdf/1611.10331v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-apples-and-oranges-two-examples-of |
| Repo | |
| Framework | |
Sentiment/Subjectivity Analysis Survey for Languages other than English
| Title | Sentiment/Subjectivity Analysis Survey for Languages other than English |
| Authors | Mohammed Korayem, Khalifeh Aljadda, David Crandall |
| Abstract | Subjective and sentiment analysis have gained considerable attention recently. Most of the resources and systems built so far are done for English. The need for designing systems for other languages is increasing. This paper surveys different ways used for building systems for subjective and sentiment analysis for languages other than English. There are three different types of systems used for building these systems. The first (and the best) one is the language specific systems. The second type of systems involves reusing or transferring sentiment resources from English to the target language. The third type of methods is based on using language independent methods. The paper presents a separate section devoted to Arabic sentiment analysis. |
| Tasks | Arabic Sentiment Analysis, Sentiment Analysis, Subjectivity Analysis |
| Published | 2016-01-01 |
| URL | http://arxiv.org/abs/1601.00087v3 |
| http://arxiv.org/pdf/1601.00087v3.pdf | |
| PWC | https://paperswithcode.com/paper/sentimentsubjectivity-analysis-survey-for |
| Repo | |
| Framework | |
Generalization Properties and Implicit Regularization for Multiple Passes SGM
| Title | Generalization Properties and Implicit Regularization for Multiple Passes SGM |
| Authors | Junhong Lin, Raffaello Camoriano, Lorenzo Rosasco |
| Abstract | We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning either the step-size or the number of passes over the data. In this view, these parameters can be seen to control a form of implicit regularization. Numerical results complement the theoretical findings. |
| Tasks | |
| Published | 2016-05-26 |
| URL | http://arxiv.org/abs/1605.08375v1 |
| http://arxiv.org/pdf/1605.08375v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-properties-and-implicit |
| Repo | |
| Framework | |
Estimation of matrix trace using machine learning
| Title | Estimation of matrix trace using machine learning |
| Authors | Boram Yoon |
| Abstract | We present a new trace estimator of the matrix whose explicit form is not given but its matrix multiplication to a vector is available. The form of the estimator is similar to the Hutchison stochastic trace estimator, but instead of the random noise vectors in Hutchison estimator, we use small number of probing vectors determined by machine learning. Evaluation of the quality of estimates and bias correction are discussed. An unbiased estimator is proposed for the calculation of the expectation value of a function of traces. In the numerical experiments with random matrices, it is shown that the precision of trace estimates with $\mathcal{O}(10)$ probing vectors determined by the machine learning is similar to that with $\mathcal{O}(10000)$ random noise vectors. |
| Tasks | |
| Published | 2016-06-16 |
| URL | http://arxiv.org/abs/1606.05560v1 |
| http://arxiv.org/pdf/1606.05560v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-matrix-trace-using-machine |
| Repo | |
| Framework | |
Determining the best attributes for surveillance video keywords generation
| Title | Determining the best attributes for surveillance video keywords generation |
| Authors | Liangchen Liu, Arnold Wiliem, Shaokang Chen, Kun Zhao, Brian C. Lovell |
| Abstract | Automatic video keyword generation is one of the key ingredients in reducing the burden of security officers in analyzing surveillance videos. Keywords or attributes are generally chosen manually based on expert knowledge of surveillance. Most existing works primarily aim at either supervised learning approaches relying on extensive manual labelling or hierarchical probabilistic models that assume the features are extracted using the bag-of-words approach; thus limiting the utilization of the other features. To address this, we turn our attention to automatic attribute discovery approaches. However, it is not clear which automatic discovery approach can discover the most meaningful attributes. Furthermore, little research has been done on how to compare and choose the best automatic attribute discovery methods. In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches.We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets. The evaluation shows that our approach is able to select the automatic discovery approach that discovers the most meaningful attributes. We then employ the best discovery approach to generate keywords for videos recorded from a surveillance system. This work shows it is possible to massively reduce the amount of manual work in generating video keywords without limiting ourselves to a particular video feature descriptor. |
| Tasks | |
| Published | 2016-02-21 |
| URL | http://arxiv.org/abs/1602.06539v1 |
| http://arxiv.org/pdf/1602.06539v1.pdf | |
| PWC | https://paperswithcode.com/paper/determining-the-best-attributes-for |
| Repo | |
| Framework | |
Cluster-Seeking James-Stein Estimators
| Title | Cluster-Seeking James-Stein Estimators |
| Authors | K. Pavan Srinath, Ramji Venkataramanan |
| Abstract | This paper considers the problem of estimating a high-dimensional vector of parameters $\boldsymbol{\theta} \in \mathbb{R}^n$ from a noisy observation. The noise vector is i.i.d. Gaussian with known variance. For a squared-error loss function, the James-Stein (JS) estimator is known to dominate the simple maximum-likelihood (ML) estimator when the dimension $n$ exceeds two. The JS-estimator shrinks the observed vector towards the origin, and the risk reduction over the ML-estimator is greatest for $\boldsymbol{\theta}$ that lie close to the origin. JS-estimators can be generalized to shrink the data towards any target subspace. Such estimators also dominate the ML-estimator, but the risk reduction is significant only when $\boldsymbol{\theta}$ lies close to the subspace. This leads to the question: in the absence of prior information about $\boldsymbol{\theta}$, how do we design estimators that give significant risk reduction over the ML-estimator for a wide range of $\boldsymbol{\theta}$? In this paper, we propose shrinkage estimators that attempt to infer the structure of $\boldsymbol{\theta}$ from the observed data in order to construct a good attracting subspace. In particular, the components of the observed vector are separated into clusters, and the elements in each cluster shrunk towards a common attractor. The number of clusters and the attractor for each cluster are determined from the observed vector. We provide concentration results for the squared-error loss and convergence results for the risk of the proposed estimators. The results show that the estimators give significant risk reduction over the ML-estimator for a wide range of $\boldsymbol{\theta}$, particularly for large $n$. Simulation results are provided to support the theoretical claims. |
| Tasks | |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00542v4 |
| http://arxiv.org/pdf/1602.00542v4.pdf | |
| PWC | https://paperswithcode.com/paper/cluster-seeking-james-stein-estimators |
| Repo | |
| Framework | |
Deep Learning on Lie Groups for Skeleton-based Action Recognition
| Title | Deep Learning on Lie Groups for Skeleton-based Action Recognition |
| Authors | Zhiwu Huang, Chengde Wan, Thomas Probst, Luc Van Gool |
| Abstract | In recent years, skeleton-based action recognition has become a popular 3D classification problem. State-of-the-art methods typically first represent each motion sequence as a high-dimensional trajectory on a Lie group with an additional dynamic time warping, and then shallowly learn favorable Lie group features. In this paper we incorporate the Lie group structure into a deep network architecture to learn more appropriate Lie group features for 3D action recognition. Within the network structure, we design rotation mapping layers to transform the input Lie group features into desirable ones, which are aligned better in the temporal domain. To reduce the high feature dimensionality, the architecture is equipped with rotation pooling layers for the elements on the Lie group. Furthermore, we propose a logarithm mapping layer to map the resulting manifold data into a tangent space that facilitates the application of regular output layers for the final classification. Evaluations of the proposed network for standard 3D human action recognition datasets clearly demonstrate its superiority over existing shallow Lie group feature learning methods as well as most conventional deep learning methods. |
| Tasks | 3D Human Action Recognition, Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2016-12-18 |
| URL | http://arxiv.org/abs/1612.05877v2 |
| http://arxiv.org/pdf/1612.05877v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-on-lie-groups-for-skeleton |
| Repo | |
| Framework | |
