July 27, 2019

3330 words 16 mins read

Paper Group ANR 544

Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution. Robustness, Evolvability and Phenotypic Complexity: Insights from Evolving Digital Circuits. Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices. Assessing User Expertise in Spoken Dialo …

Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution


Title	Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution
Authors	Adam Żychowski, Abhishek Gupta, Jacek Mańdziuk, Yew Soon Ong
Abstract	This paper presents algorithmic and empirical contributions demonstrating that the convergence characteristics of a co-evolutionary approach to tackle Multi-Objective Games (MOGs) with postponed preference articulation can often be hampered due to the possible emergence of the so-called Red Queen effect. Accordingly, it is hypothesized that the convergence characteristics can be significantly improved through the incorporation of memetics (local solution refinements as a form of lifelong learning), as a promising means of mitigating (or at least suppressing) the Red Queen phenomenon by providing a guiding hand to the purely genetic mechanisms of co-evolution. Our practical motivation is to address MOGs of a time-sensitive nature that are characterized by computationally expensive evaluations, wherein there is a natural need to reduce the total number of true function evaluations consumed in achieving good quality solutions. To this end, we propose novel enhancements to co-evolutionary approaches for tackling MOGs, such that memetic local refinements can be efficiently applied on evolved candidate strategies by searching on computationally cheap surrogate payoff landscapes (that preserve postponed preference conditions). The efficacy of the proposal is demonstrated on a suite of test MOGs that have been designed.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06763v1
PDF	http://arxiv.org/pdf/1711.06763v1.pdf
PWC	https://paperswithcode.com/paper/addressing-expensive-multi-objective-games
Repo
Framework

Robustness, Evolvability and Phenotypic Complexity: Insights from Evolving Digital Circuits


Title	Robustness, Evolvability and Phenotypic Complexity: Insights from Evolving Digital Circuits
Authors	Nicola Milano, Paolo Pagliuca, Stefano Nolfi
Abstract	We show how the characteristics of the evolutionary algorithm influence the evolvability of candidate solutions, i.e. the propensity of evolving individuals to generate better solutions as a result of genetic variation. More specifically, (1+{\lambda}) evolutionary strategies largely outperform ({\mu}+1) evolutionary strategies in the context of the evolution of digital circuits — a domain characterized by a high level of neutrality. This difference is due to the fact that the competition for robustness to mutations among the circuits evolved with ({\mu}+1) evolutionary strategies leads to the selection of phenotypically simple but low evolvable circuits. These circuits achieve robustness by minimizing the number of functional genes rather than by relying on redundancy or degeneracy to buffer the effects of mutations. The analysis of these factors enabled us to design a new evolutionary algorithm, named Parallel Stochastic Hill Climber (PSHC), which outperforms the other two methods considered.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04254v1
PDF	http://arxiv.org/pdf/1712.04254v1.pdf
PWC	https://paperswithcode.com/paper/robustness-evolvability-and-phenotypic
Repo
Framework

Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices


Title	Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices
Authors	Mohamed Daoudi, Stefano Berretti, Pietro Pala, Yvonne Delevoye, Alberto Del Bimbo
Abstract	Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations. Much of the Computer Vision research in this field has focused on relating emotions to facial expressions, with investigations rarely including more than upper body. In this work, we propose a new scenario, for which emotional states are related to 3D dynamics of the whole body motion. To address the complexity of human body movement, we used covariance descriptors of the sequence of the 3D skeleton joints, and represented them in the non-linear Riemannian manifold of Symmetric Positive Definite matrices. In doing so, we exploited geodesic distances and geometric means on the manifold to perform emotion classification. Using sequences of spontaneous walking under the five primary emotional states, we report a method that succeeded in classifying the different emotions, with comparable performance to those observed in a human-based force-choice classification task.
Tasks	Emotion Classification, Emotion Recognition
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07180v1
PDF	http://arxiv.org/pdf/1707.07180v1.pdf
PWC	https://paperswithcode.com/paper/emotion-recognition-by-body-movement
Repo
Framework

Assessing User Expertise in Spoken Dialog System Interactions


Title	Assessing User Expertise in Spoken Dialog System Interactions
Authors	Eugénio Ribeiro, Fernando Batista, Isabel Trancoso, José Lopes, Ricardo Ribeiro, David Martins de Matos
Abstract	Identifying the level of expertise of its users is important for a system since it can lead to a better interaction through adaptation techniques. Furthermore, this information can be used in offline processes of root cause analysis. However, not much effort has been put into automatically identifying the level of expertise of an user, especially in dialog-based interactions. In this paper we present an approach based on a specific set of task related features. Based on the distribution of the features among the two classes - Novice and Expert - we used Random Forests as a classification approach. Furthermore, we used a Support Vector Machine classifier, in order to perform a result comparison. By applying these approaches on data from a real system, Let’s Go, we obtained preliminary results that we consider positive, given the difficulty of the task and the lack of competing approaches for comparison.
Tasks
Published	2017-01-18
URL	http://arxiv.org/abs/1701.05011v1
PDF	http://arxiv.org/pdf/1701.05011v1.pdf
PWC	https://paperswithcode.com/paper/assessing-user-expertise-in-spoken-dialog
Repo
Framework

Content Based Document Recommender using Deep Learning


Title	Content Based Document Recommender using Deep Learning
Authors	Nishant Nikhil, Muktabh Mayank Srivastava
Abstract	With the recent advancements in information technology there has been a huge surge in amount of data available. But information retrieval technology has not been able to keep up with this pace of information generation resulting in over spending of time for retrieving relevant information. Even though systems exist for assisting users to search a database along with filtering and recommending relevant information, but recommendation system which uses content of documents for recommendation still have a long way to mature. Here we present a Deep Learning based supervised approach to recommend similar documents based on the similarity of content. We combine the C-DSSM model with Word2Vec distributed representations of words to create a novel model to classify a document pair as relevant/irrelavant by assigning a score to it. Using our model retrieval of documents can be done in O(1) time and the memory complexity is O(n), where n is number of documents.
Tasks	Information Retrieval
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08321v1
PDF	http://arxiv.org/pdf/1710.08321v1.pdf
PWC	https://paperswithcode.com/paper/content-based-document-recommender-using-deep
Repo
Framework

Deep Factorization for Speech Signal


Title	Deep Factorization for Speech Signal
Authors	Dong Wang, Lantian Li, Ying Shi, Yixiang Chen, Zhiyuan Tang
Abstract	Speech signals are complex intermingling of various informative factors, and this information blending makes decoding any of the individual factors extremely difficult. A natural idea is to factorize each speech frame into independent factors, though it turns out to be even more difficult than decoding each individual factor. A major encumbrance is that the speaker trait, a major factor in speech signals, has been suspected to be a long-term distributional pattern and so not identifiable at the frame level. In this paper, we demonstrated that the speaker factor is also a short-time spectral pattern and can be largely identified with just a few frames using a simple deep neural network (DNN). This discovery motivated a cascade deep factorization (CDF) framework that infers speech factors in a sequential way, and factors previously inferred are used as conditional variables when inferring other factors. Our experiment on an automatic emotion recognition (AER) task demonstrated that this approach can effectively factorize speech signals, and using these factors, the original speech spectrum can be recovered with high accuracy. This factorization and reconstruction approach provides a novel tool for many speech processing tasks.
Tasks	Emotion Recognition
Published	2017-06-05
URL	http://arxiv.org/abs/1706.01777v2
PDF	http://arxiv.org/pdf/1706.01777v2.pdf
PWC	https://paperswithcode.com/paper/deep-factorization-for-speech-signal-1
Repo
Framework

Unsupervised Action Proposal Ranking through Proposal Recombination


Title	Unsupervised Action Proposal Ranking through Proposal Recombination
Authors	Waqas Sultani, Dong Zhang, Mubarak Shah
Abstract	Recently, action proposal methods have played an important role in action recognition tasks, as they reduce the search space dramatically. Most unsupervised action proposal methods tend to generate hundreds of action proposals which include many noisy, inconsistent, and unranked action proposals, while supervised action proposal methods take advantage of predefined object detectors (e.g., human detector) to refine and score the action proposals, but they require thousands of manual annotations to train. Given the action proposals in a video, the goal of the proposed work is to generate a few better action proposals that are ranked properly. In our approach, we first divide action proposal into sub-proposal and then use Dynamic Programming based graph optimization scheme to select the optimal combinations of sub-proposals from different proposals and assign each new proposal a score. We propose a new unsupervised image-based actioness detector that leverages web images and employs it as one of the node scores in our graph formulation. Moreover, we capture motion information by estimating the number of motion contours within each action proposal patch. The proposed method is an unsupervised method that neither needs bounding box annotations nor video level labels, which is desirable with the current explosion of large-scale action datasets. Our approach is generic and does not depend on a specific action proposal method. We evaluate our approach on several publicly available trimmed and un-trimmed datasets and obtain better performance compared to several proposal ranking methods. In addition, we demonstrate that properly ranked proposals produce significantly better action detection as compared to state-of-the-art proposal based methods.
Tasks	Action Detection, Temporal Action Localization
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00758v1
PDF	http://arxiv.org/pdf/1704.00758v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-action-proposal-ranking-through
Repo
Framework

Block CUR: Decomposing Matrices using Groups of Columns


Title	Block CUR: Decomposing Matrices using Groups of Columns
Authors	Urvashi Oswal, Swayambhoo Jain, Kevin S. Xu, Brian Eriksson
Abstract	A common problem in large-scale data analysis is to approximate a matrix using a combination of specifically sampled rows and columns, known as CUR decomposition. Unfortunately, in many real-world environments, the ability to sample specific individual rows or columns of the matrix is limited by either system constraints or cost. In this paper, we consider matrix approximation by sampling predefined \emph{blocks} of columns (or rows) from the matrix. We present an algorithm for sampling useful column blocks and provide novel guarantees for the quality of the approximation. This algorithm has application in problems as diverse as biometric data analysis to distributed computing. We demonstrate the effectiveness of the proposed algorithms for computing the Block CUR decomposition of large matrices in a distributed setting with multiple nodes in a compute cluster, where such blocks correspond to columns (or rows) of the matrix stored on the same node, which can be retrieved with much less overhead than retrieving individual columns stored across different nodes. In the biometric setting, the rows correspond to different users and columns correspond to users’ biometric reaction to external stimuli, {\em e.g.,}~watching video content, at a particular time instant. There is significant cost in acquiring each user’s reaction to lengthy content so we sample a few important scenes to approximate the biometric response. An individual time sample in this use case cannot be queried in isolation due to the lack of context that caused that biometric reaction. Instead, collections of time segments ({\em i.e.,} blocks) must be presented to the user. The practical application of these algorithms is shown via experimental results using real-world user biometric data from a content testing environment.
Tasks
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06065v2
PDF	http://arxiv.org/pdf/1703.06065v2.pdf
PWC	https://paperswithcode.com/paper/block-cur-decomposing-matrices-using-groups
Repo
Framework

Learning Criticality in an Embodied Boltzmann Machine


Title	Learning Criticality in an Embodied Boltzmann Machine
Authors	Miguel Aguilera, Manuel G. Bedia
Abstract	Many biological and cognitive systems do not operate deep into one or other regime of activity. Instead, they exploit critical surfaces poised at transitions in their parameter space. The pervasiveness of criticality in natural systems suggests that there may be general principles inducing this behaviour. However, there is a lack of conceptual models explaining how embodied agents propel themselves towards these critical points. In this paper, we present a learning model driving an embodied Boltzmann Machine towards critical behaviour by maximizing the heat capacity of the network. We test and corroborate the model implementing an embodied agent in the mountain car benchmark, controlled by a Boltzmann Machine that adjust its weights according to the model. We find that the neural controller reaches a point of criticality, which coincides with a transition point of the behaviour of the agent between two regimes of behaviour, maximizing the synergistic information between its sensors and the hidden and motor neurons. Finally, we discuss the potential of our learning model to study the contribution of criticality to the behaviour of embodied living systems in scenarios not necessarily constrained by biological restrictions of the examples of criticality we find in nature.
Tasks
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00614v1
PDF	http://arxiv.org/pdf/1702.00614v1.pdf
PWC	https://paperswithcode.com/paper/learning-criticality-in-an-embodied-boltzmann
Repo
Framework

Stochastic Approximation for Canonical Correlation Analysis


Title	Stochastic Approximation for Canonical Correlation Analysis
Authors	Raman Arora, Teodor V. Marinov, Poorya Mianjy, Nathan Srebro
Abstract	We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA). Algorithms presented are instances of inexact matrix stochastic gradient (MSG) and inexact matrix exponentiated gradient (MEG), and achieve $\epsilon$-suboptimality in the population objective in $\operatorname{poly}(\frac{1}{\epsilon})$ iterations. We also consider practical variants of the proposed algorithms and compare them with other methods for CCA both theoretically and empirically.
Tasks
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06818v2
PDF	http://arxiv.org/pdf/1702.06818v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-approximation-for-canonical
Repo
Framework

Classification Using Proximity Catch Digraphs (Technical Report)


Title	Classification Using Proximity Catch Digraphs (Technical Report)
Authors	Artür Manukyan, Elvan Ceyhan
Abstract	We employ random geometric digraphs to construct semi-parametric classifiers. These data-random digraphs are from parametrized random digraph families called proximity catch digraphs (PCDs). A related geometric digraph family, class cover catch digraph (CCCD), has been used to solve the class cover problem by using its approximate minimum dominating set. CCCDs showed relatively good performance in the classification of imbalanced data sets, and although CCCDs have a convenient construction in $\mathbb{R}^d$, finding minimum dominating sets is NP-hard and its probabilistic behaviour is not mathematically tractable except for $d=1$. On the other hand, a particular family of PCDs, called \emph{proportional-edge} PCDs (PE-PCDs), has mathematical tractable minimum dominating sets in $\mathbb{R}^d$; however their construction in higher dimensions may be computationally demanding. More specifically, we show that the classifiers based on PE-PCDs are prototype-based classifiers such that the exact minimum number of prototypes (equivalent to minimum dominating sets) are found in polynomial time on the number of observations. We construct two types of classifiers based on PE-PCDs. One is a family of hybrid classifiers depend on the location of the points of the training data set, and another type is a family of classifiers solely based on class covers. We assess the classification performance of our PE-PCD based classifiers by extensive Monte Carlo simulations, and compare them with that of other commonly used classifiers. We also show that, similar to CCCD classifiers, our classifiers are relatively better in classification in the presence of class imbalance.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07600v1
PDF	http://arxiv.org/pdf/1705.07600v1.pdf
PWC	https://paperswithcode.com/paper/classification-using-proximity-catch-digraphs
Repo
Framework

Deep Self-Paced Learning for Person Re-Identification


Title	Deep Self-Paced Learning for Person Re-Identification
Authors	Sanping Zhou, Jinjun Wang, Deyu Meng, Xiaomeng Xin, Yubing Li, Yihong Gong, Nanning Zheng
Abstract	Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different individuals across the disjoint camera views. In this paper, we propose a novel deep self-paced learning (DSPL) algorithm to alleviate this problem, in which we apply a self-paced constraint and symmetric regularization to help the relative distance metric training the deep neural network, so as to learn the stable and discriminative features for person Re-ID. Firstly, we propose a soft polynomial regularizer term which can derive the adaptive weights to samples based on both the training loss and model age. As a result, the high-confidence fidelity samples will be emphasized and the low-confidence noisy samples will be suppressed at early stage of the whole training process. Such a learning regime is naturally implemented under a self-paced learning (SPL) framework, in which samples weights are adaptively updated based on both model age and sample loss using an alternative optimization method. Secondly, we introduce a symmetric regularizer term to revise the asymmetric gradient back-propagation derived by the relative distance metric, so as to simultaneously minimize the intra-class distance and maximize the inter-class distance in each triplet unit. Finally, we build a part-based deep neural network, in which the features of different body parts are first discriminately learned in the lower convolutional layers and then fused in the higher fully connected layers. Experiments on several benchmark datasets have demonstrated the superior performance of our method as compared with the state-of-the-art approaches.
Tasks	Person Re-Identification
Published	2017-10-07
URL	http://arxiv.org/abs/1710.05711v1
PDF	http://arxiv.org/pdf/1710.05711v1.pdf
PWC	https://paperswithcode.com/paper/deep-self-paced-learning-for-person-re
Repo
Framework

An EEG-based Image Annotation System


Title	An EEG-based Image Annotation System
Authors	Viral Parekh, Ramanathan Subramanian, Dipanjan Roy, C. V. Jawahar
Abstract	The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20-200 milliseconds, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.
Tasks	EEG
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02383v1
PDF	http://arxiv.org/pdf/1711.02383v1.pdf
PWC	https://paperswithcode.com/paper/an-eeg-based-image-annotation-system
Repo
Framework

The Cultural Evolution of National Constitutions


Title	The Cultural Evolution of National Constitutions
Authors	Daniel N. Rockmore, Chen Fang, Nicholas J. Foti, Tom Ginsburg, David C. Krakauer
Abstract	We explore how ideas from infectious disease and genetics can be used to uncover patterns of cultural inheritance and innovation in a corpus of 591 national constitutions spanning 1789 - 2008. Legal “Ideas” are encoded as “topics” - words statistically linked in documents - derived from topic modeling the corpus of constitutions. Using these topics we derive a diffusion network for borrowing from ancestral constitutions back to the US Constitution of 1789 and reveal that constitutions are complex cultural recombinants. We find systematic variation in patterns of borrowing from ancestral texts and “biological”-like behavior in patterns of inheritance with the distribution of “offspring” arising through a bounded preferential-attachment process. This process leads to a small number of highly innovative (influential) constitutions some of which have yet to have been identified as so in the current literature. Our findings thus shed new light on the critical nodes of the constitution-making network. The constitutional network structure reflects periods of intense constitution creation, and systematic patterns of variation in constitutional life-span and temporal influence.
Tasks
Published	2017-11-18
URL	http://arxiv.org/abs/1711.06899v1
PDF	http://arxiv.org/pdf/1711.06899v1.pdf
PWC	https://paperswithcode.com/paper/the-cultural-evolution-of-national
Repo
Framework

3D Textured Model Encryption via 3D Lu Chaotic Mapping


Title	3D Textured Model Encryption via 3D Lu Chaotic Mapping
Authors	Xin Jin, Shuyun Zhu, Chaoen Xiao, Hongbo Sun, Xiaodong Li, Geng Zhao, Shiming Ge
Abstract	In the coming Virtual/Augmented Reality (VR/AR) era, 3D contents will be popularized just as images and videos today. The security and privacy of these 3D contents should be taken into consideration. 3D contents contain surface models and solid models. The surface models include point clouds, meshes and textured models. Previous work mainly focus on encryption of solid models, point clouds and meshes. This work focuses on the most complicated 3D textured model. We propose a 3D Lu chaotic mapping based encryption method of 3D textured model. We encrypt the vertexes, the polygons and the textures of 3D models separately using the 3D Lu chaotic mapping. Then the encrypted vertices, edges and texture maps are composited together to form the final encrypted 3D textured model. The experimental results reveal that our method can encrypt and decrypt 3D textured models correctly. In addition, our method can resistant several attacks such as brute-force attack and statistic attack.
Tasks
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08364v1
PDF	http://arxiv.org/pdf/1709.08364v1.pdf
PWC	https://paperswithcode.com/paper/3d-textured-model-encryption-via-3d-lu
Repo
Framework