May 6, 2019

3052 words 15 mins read

Paper Group ANR 222

Tracking Tensor Subspaces with Informative Random Sampling for Real-Time MR Imaging. KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge. Saliency Driven Object recognition in egocentric videos with deep CNN. Fast Predictive Image Registration. Hierarchical Latent Word Clustering. Generalized Entropies and the Simi …

Tracking Tensor Subspaces with Informative Random Sampling for Real-Time MR Imaging


Title	Tracking Tensor Subspaces with Informative Random Sampling for Real-Time MR Imaging
Authors	Morteza Mardani, Georgios B. Giannakis, Kamil Ugurbil
Abstract	Magnetic resonance imaging (MRI) nowadays serves as an important modality for diagnostic and therapeutic guidance in clinics. However, the {\it slow acquisition} process, the dynamic deformation of organs, as well as the need for {\it real-time} reconstruction, pose major challenges toward obtaining artifact-free images. To cope with these challenges, the present paper advocates a novel subspace learning framework that permeates benefits from parallel factor (PARAFAC) decomposition of tensors (multiway data) to low-rank modeling of temporal sequence of images. Treating images as multiway data arrays, the novel method preserves spatial structures and unravels the latent correlations across various dimensions by means of the tensor subspace. Leveraging the spatio-temporal correlation of images, Tykhonov regularization is adopted as a rank surrogate for a least-squares optimization program. Alteranating majorization minimization is adopted to develop online algorithms that recursively procure the reconstruction upon arrival of a new undersampled $k$-space frame. The developed algorithms are {\it provably convergent} and highly {\it parallelizable} with lightweight FFT tasks per iteration. To further accelerate the acquisition process, randomized subsampling policies are devised that leverage intermediate estimates of the tensor subspace, offered by the online scheme, to {\it randomly} acquire {\it informative} $k$-space samples. In a nutshell, the novel approach enables tracking motion dynamics under low acquisition rates `on the fly.’ GPU-based tests with real {\it in vivo} MRI datasets of cardiac cine images corroborate the merits of the novel approach relative to state-of-the-art alternatives. \|
Tasks
Published	2016-09-14
URL	http://arxiv.org/abs/1609.04104v1
PDF	http://arxiv.org/pdf/1609.04104v1.pdf
PWC	https://paperswithcode.com/paper/tracking-tensor-subspaces-with-informative
Repo
Framework

KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge


Title	KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge
Authors	Suwon Shon, Seongkyu Mun, John H. L. Hansen, Hanseok Ko
Abstract	In language recognition, the task of rejecting/differentiating closely spaced versus acoustically far spaced languages remains a major challenge. For confusable closely spaced languages, the system needs longer input test duration material to obtain sufficient information to distinguish between languages. Alternatively, if languages are distinct and not acoustically/linguistically similar to others, duration is not a sufficient remedy. The solution proposed here is to explore duration distribution analysis for near/far languages based on the Language Recognition i-Vector Machine Learning Challenge 2015 (LRiMLC15) database. Using this knowledge, we propose a likelihood ratio based fusion approach that leveraged both score and duration information. The experimental results show that the use of duration and score fusion improves language recognition performance by 5% relative in LRiMLC15 cost.
Tasks
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06404v1
PDF	http://arxiv.org/pdf/1609.06404v1.pdf
PWC	https://paperswithcode.com/paper/ku-ispl-language-recognition-system-for-nist
Repo
Framework

Saliency Driven Object recognition in egocentric videos with deep CNN


Title	Saliency Driven Object recognition in egocentric videos with deep CNN
Authors	Philippe Pérez de San Roman, Jenny Benois-Pineau, Jean-Philippe Domenger, Florent Paclet, Daniel Cataert, Aymar de Rugy
Abstract	The problem of object recognition in natural scenes has been recently successfully addressed with Deep Convolutional Neuronal Networks giving a significant break-through in recognition scores. The computational efficiency of Deep CNNs as a function of their depth, allows for their use in real-time applications. One of the key issues here is to reduce the number of windows selected from images to be submitted to a Deep CNN. This is usually solved by preliminary segmentation and selection of specific windows, having outstanding “objectiveness” or other value of indicators of possible location of objects. In this paper we propose a Deep CNN approach and the general framework for recognition of objects in a real-time scenario and in an egocentric perspective. Here the window of interest is built on the basis of visual attention map computed over gaze fixations measured by a glass-worn eye-tracker. The application of this set-up is an interactive user-friendly environment for upper-limb amputees. Vision has to help the subject to control his worn neuro-prosthesis in case of a small amount of remaining muscles when the EMG control becomes unefficient. The recognition results on a specifically recorded corpus of 151 videos with simple geometrical objects show the mAP of 64,6% and the computational time at the generalization lower than a time of a visual fixation on the object-of-interest.
Tasks	Object Recognition
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07256v1
PDF	http://arxiv.org/pdf/1606.07256v1.pdf
PWC	https://paperswithcode.com/paper/saliency-driven-object-recognition-in
Repo
Framework

Fast Predictive Image Registration


Title	Fast Predictive Image Registration
Authors	Xiao Yang, Roland Kwitt, Marc Niethammer
Abstract	We present a method to predict image deformations based on patch-wise image appearance. Specifically, we design a patch-based deep encoder-decoder network which learns the pixel/voxel-wise mapping between image appearance and registration parameters. Our approach can predict general deformation parameterizations, however, we focus on the large deformation diffeomorphic metric mapping (LDDMM) registration model. By predicting the LDDMM momentum-parameterization we retain the desirable theoretical properties of LDDMM, while reducing computation time by orders of magnitude: combined with patch pruning, we achieve a 1500x/66x speed up compared to GPU-based optimization for 2D/3D image registration. Our approach has better prediction accuracy than predicting deformation or velocity fields and results in diffeomorphic transformations. Additionally, we create a Bayesian probabilistic version of our network, which allows evaluation of deformation field uncertainty through Monte Carlo sampling using dropout at test time. We show that deformation uncertainty highlights areas of ambiguous deformations. We test our method on the OASIS brain image dataset in 2D and 3D.
Tasks	Image Registration
Published	2016-07-08
URL	http://arxiv.org/abs/1607.02504v1
PDF	http://arxiv.org/pdf/1607.02504v1.pdf
PWC	https://paperswithcode.com/paper/fast-predictive-image-registration
Repo
Framework

Hierarchical Latent Word Clustering


Title	Hierarchical Latent Word Clustering
Authors	Halid Ziya Yerebakan, Fitsum Reda, Yiqiang Zhan, Yoshihisa Shinagawa
Abstract	This paper presents a new Bayesian non-parametric model by extending the usage of Hierarchical Dirichlet Allocation to extract tree structured word clusters from text data. The inference algorithm of the model collects words in a cluster if they share similar distribution over documents. In our experiments, we observed meaningful hierarchical structures on NIPS corpus and radiology reports collected from public repositories.
Tasks
Published	2016-01-20
URL	http://arxiv.org/abs/1601.05472v1
PDF	http://arxiv.org/pdf/1601.05472v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-latent-word-clustering
Repo
Framework

Generalized Entropies and the Similarity of Texts


Title	Generalized Entropies and the Similarity of Texts
Authors	Eduardo G. Altmann, Laercio Dias, Martin Gerlach
Abstract	We show how generalized Gibbs-Shannon entropies can provide new insights on the statistical properties of texts. The universal distribution of word frequencies (Zipf’s law) implies that the generalized entropies, computed at the word level, are dominated by words in a specific range of frequencies. Here we show that this is the case not only for the generalized entropies but also for the generalized (Jensen-Shannon) divergences, used to compute the similarity between different texts. This finding allows us to identify the contribution of specific words (and word frequencies) for the different generalized entropies and also to estimate the size of the databases needed to obtain a reliable estimation of the divergences. We test our results in large databases of books (from the Google n-gram database) and scientific papers (indexed by Web of Science).
Tasks
Published	2016-11-11
URL	http://arxiv.org/abs/1611.03596v1
PDF	http://arxiv.org/pdf/1611.03596v1.pdf
PWC	https://paperswithcode.com/paper/generalized-entropies-and-the-similarity-of
Repo
Framework

WoCE: a framework for clustering ensemble by exploiting the wisdom of Crowds theory


Title	WoCE: a framework for clustering ensemble by exploiting the wisdom of Crowds theory
Authors	Muhammad Yousefnezhad, Sheng-Jun Huang, Daoqiang Zhang
Abstract	The Wisdom of Crowds (WOC), as a theory in the social science, gets a new paradigm in computer science. The WOC theory explains that the aggregate decision made by a group is often better than those of its individual members if specific conditions are satisfied. This paper presents a novel framework for unsupervised and semi-supervised cluster ensemble by exploiting the WOC theory. We employ four conditions in the WOC theory, i.e., diversity, independency, decentralization and aggregation, to guide both the constructing of individual clustering results and the final combination for clustering ensemble. Firstly, independency criterion, as a novel mapping system on the raw data set, removes the correlation between features on our proposed method. Then, decentralization as a novel mechanism generates high-quality individual clustering results. Next, uniformity as a new diversity metric evaluates the generated clustering results. Further, weighted evidence accumulation clustering method is proposed for the final aggregation without using thresholding procedure. Experimental study on varied data sets demonstrates that the proposed approach achieves superior performance to state-of-the-art methods.
Tasks
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06598v1
PDF	http://arxiv.org/pdf/1612.06598v1.pdf
PWC	https://paperswithcode.com/paper/woce-a-framework-for-clustering-ensemble-by
Repo
Framework

Who is Mistaken?


Title	Who is Mistaken?
Authors	Benjamin Eysenbach, Carl Vondrick, Antonio Torralba
Abstract	Recognizing when people have false beliefs is crucial for understanding their actions. We introduce the novel problem of identifying when people in abstract scenes have incorrect beliefs. We present a dataset of scenes, each visually depicting an 8-frame story in which a character has a mistaken belief. We then create a representation of characters’ beliefs for two tasks in human action understanding: predicting who is mistaken, and when they are mistaken. Experiments suggest that our method for identifying mistaken characters performs better on these tasks than simple baselines. Diagnostics on our model suggest it learns important cues for recognizing mistaken beliefs, such as gaze. We believe models of people’s beliefs will have many applications in action understanding, robotics, and healthcare.
Tasks
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01175v2
PDF	http://arxiv.org/pdf/1612.01175v2.pdf
PWC	https://paperswithcode.com/paper/who-is-mistaken
Repo
Framework

An Automaton Learning Approach to Solving Safety Games over Infinite Graphs


Title	An Automaton Learning Approach to Solving Safety Games over Infinite Graphs
Authors	Daniel Neider, Ufuk Topcu
Abstract	We propose a method to construct finite-state reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration two-player games over (possibly) infinite graphs. The proposed method targets safety games with infinitely many states or with such a large number of states that it would be impractical—if not impossible—for conventional synthesis techniques that work on the entire state space. We resort to constructing finite-state controllers for such systems through an automata learning approach, utilizing a symbolic representation of the underlying game that is based on finite automata. Throughout the learning process, the learner maintains an approximation of the winning region (represented as a finite automaton) and refines it using different types of counterexamples provided by the teacher until a satisfactory controller can be derived (if one exists). We present a symbolic representation of safety games (inspired by regular model checking), propose implementations of the learner and teacher, and evaluate their performance on examples motivated by robotic motion planning in dynamic environments.
Tasks	Motion Planning
Published	2016-01-07
URL	http://arxiv.org/abs/1601.01660v1
PDF	http://arxiv.org/pdf/1601.01660v1.pdf
PWC	https://paperswithcode.com/paper/an-automaton-learning-approach-to-solving
Repo
Framework

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices


Title	Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices
Authors	Felix Stahlberg, Adrià de Gispert, Eva Hasler, Bill Byrne
Abstract	We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined with the Bayes-risk of the translation according the SMT lattice. This makes our approach much more flexible than $n$-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space. We show an efficient and simple way to integrate risk estimation into the NMT decoder which is suitable for word-level as well as subword-unit-level NMT. We test our method on English-German and Japanese-English and report significant gains over lattice rescoring on several data sets for both single and ensembled NMT. The MBR decoder produces entirely new hypotheses far beyond simply rescoring the SMT search space or fixing UNKs in the NMT output.
Tasks	Machine Translation
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03791v2
PDF	http://arxiv.org/pdf/1612.03791v2.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-by-minimising-the
Repo
Framework

Universal Dependencies for Learner English


Title	Universal Dependencies for Learner English
Authors	Yevgeni Berzak, Jessica Kenney, Carolyn Spadine, Jing Xian Wang, Lucia Lam, Keiko Sophie Mori, Sebastian Garza, Boris Katz
Abstract	We introduce the Treebank of Learner English (TLE), the first publicly available syntactic treebank for English as a Second Language (ESL). The TLE provides manually annotated POS tags and Universal Dependency (UD) trees for 5,124 sentences from the Cambridge First Certificate in English (FCE) corpus. The UD annotations are tied to a pre-existing error annotation of the FCE, whereby full syntactic analyses are provided for both the original and error corrected versions of each sentence. Further on, we delineate ESL annotation guidelines that allow for consistent syntactic treatment of ungrammatical English. Finally, we benchmark POS tagging and dependency parsing performance on the TLE dataset and measure the effect of grammatical errors on parsing accuracy. We envision the treebank to support a wide range of linguistic and computational research on second language acquisition as well as automatic processing of ungrammatical language. The treebank is available at universaldependencies.org. The annotation manual used in this project and a graphical query engine are available at esltreebank.org.
Tasks	Dependency Parsing, Language Acquisition
Published	2016-05-13
URL	http://arxiv.org/abs/1605.04278v2
PDF	http://arxiv.org/pdf/1605.04278v2.pdf
PWC	https://paperswithcode.com/paper/universal-dependencies-for-learner-english
Repo
Framework

Sensorimotor Input as a Language Generalisation Tool: A Neurorobotics Model for Generation and Generalisation of Noun-Verb Combinations with Sensorimotor Inputs


Title	Sensorimotor Input as a Language Generalisation Tool: A Neurorobotics Model for Generation and Generalisation of Noun-Verb Combinations with Sensorimotor Inputs
Authors	Junpei Zhong, Martin Peniak, Jun Tani, Tetsuya Ogata, Angelo Cangelosi
Abstract	The paper presents a neurorobotics cognitive model to explain the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot. This generalisation process is done via the grounding process: different objects are being interacted, and associated, with different motor behaviours, following a learning approach inspired by developmental language acquisition in infants. This cognitive model is based on Multiple Time-scale Recurrent Neural Networks (MTRNN).With the data obtained from object manipulation tasks with a humanoid robot platform, the robotic agent implemented with this model can ground the primitive embodied structure of verbs through training with verb-noun combination samples. Moreover, we show that a functional hierarchical architecture, based on MTRNN, is able to generalise and produce novel combinations of noun-verb sentences. Further analyses of the learned network dynamics and representations also demonstrate how the generalisation is possible via the exploitation of this functional hierarchical recurrent network.
Tasks	Language Acquisition
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03261v1
PDF	http://arxiv.org/pdf/1605.03261v1.pdf
PWC	https://paperswithcode.com/paper/sensorimotor-input-as-a-language
Repo
Framework

Optimizing Expectation with Guarantees in POMDPs (Technical Report)


Title	Optimizing Expectation with Guarantees in POMDPs (Technical Report)
Authors	Krishnendu Chatterjee, Petr Novotný, Guillermo A. Pérez, Jean-François Raskin, Đorđe Žikelić
Abstract	A standard objective in partially-observable Markov decision processes (POMDPs) is to find a policy that maximizes the expected discounted-sum payoff. However, such policies may still permit unlikely but highly undesirable outcomes, which is problematic especially in safety-critical applications. Recently, there has been a surge of interest in POMDPs where the goal is to maximize the probability to ensure that the payoff is at least a given threshold, but these approaches do not consider any optimization beyond satisfying this threshold constraint. In this work we go beyond both the “expectation” and “threshold” approaches and consider a “guaranteed payoff optimization (GPO)” problem for POMDPs, where we are given a threshold $t$ and the objective is to find a policy $\sigma$ such that a) each possible outcome of $\sigma$ yields a discounted-sum payoff of at least $t$, and b) the expected discounted-sum payoff of $\sigma$ is optimal (or near-optimal) among all policies satisfying a). We present a practical approach to tackle the GPO problem and evaluate it on standard POMDP benchmarks.
Tasks
Published	2016-11-26
URL	http://arxiv.org/abs/1611.08696v2
PDF	http://arxiv.org/pdf/1611.08696v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-expectation-with-guarantees-in
Repo
Framework

Reactive Multi-Context Systems: Heterogeneous Reasoning in Dynamic Environments


Title	Reactive Multi-Context Systems: Heterogeneous Reasoning in Dynamic Environments
Authors	Gerhard Brewka, Stefan Ellmauthaler, Ricardo Gonçalves, Matthias Knorr, João Leite, Jörg Pührer
Abstract	Managed multi-context systems (mMCSs) allow for the integration of heterogeneous knowledge sources in a modular and very general way. They were, however, mainly designed for static scenarios and are therefore not well-suited for dynamic environments in which continuous reasoning over such heterogeneous knowledge with constantly arriving streams of data is necessary. In this paper, we introduce reactive multi-context systems (rMCSs), a framework for reactive reasoning in the presence of heterogeneous knowledge sources and data streams. We show that rMCSs are indeed well-suited for this purpose by illustrating how several typical problems arising in the context of stream reasoning can be handled using them, by showing how inconsistencies possibly occurring in the integration of multiple knowledge sources can be handled, and by arguing that the potential non-determinism of rMCSs can be avoided if needed using an alternative, more skeptical well-founded semantics instead with beneficial computational properties. We also investigate the computational complexity of various reasoning problems related to rMCSs. Finally, we discuss related work, and show that rMCSs do not only generalize mMCSs to dynamic settings, but also capture/extend relevant approaches w.r.t. dynamics in knowledge representation and stream reasoning.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03438v3
PDF	http://arxiv.org/pdf/1609.03438v3.pdf
PWC	https://paperswithcode.com/paper/reactive-multi-context-systems-heterogeneous
Repo
Framework

Clustering Time Series and the Surprising Robustness of HMMs


Title	Clustering Time Series and the Surprising Robustness of HMMs
Authors	Mark Kozdoba, Shie Mannor
Abstract	Suppose that we are given a time series where consecutive samples are believed to come from a probabilistic source, that the source changes from time to time and that the total number of sources is fixed. Our objective is to estimate the distributions of the sources. A standard approach to this problem is to model the data as a hidden Markov model (HMM). However, since the data often lacks the Markov or the stationarity properties of an HMM, one can ask whether this approach is still suitable or perhaps another approach is required. In this paper we show that a maximum likelihood HMM estimator can be used to approximate the source distributions in a much larger class of models than HMMs. Specifically, we propose a natural and fairly general non-stationary model of the data, where the only restriction is that the sources do not change too often. Our main result shows that for this model, a maximum-likelihood HMM estimator produces the correct second moment of the data, and the results can be extended to higher moments.
Tasks	Time Series
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02531v2
PDF	http://arxiv.org/pdf/1605.02531v2.pdf
PWC	https://paperswithcode.com/paper/clustering-time-series-and-the-surprising
Repo
Framework