May 6, 2019

2875 words 14 mins read

Paper Group ANR 411

Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization. A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization. Automatic Techniques for Gridding cDNA Microarray Images. Adaptive Graph-based Total Variation for Tomographic Reconstructions. Learning Online Alig …

Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization


Title	Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
Authors	Jun Suzuki, Masaaki Nagata
Abstract	This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and achieved its best results on an abstractive summarization benchmark.
Tasks	Abstractive Text Summarization
Published	2016-12-31
URL	http://arxiv.org/abs/1701.00138v2
PDF	http://arxiv.org/pdf/1701.00138v2.pdf
PWC	https://paperswithcode.com/paper/cutting-off-redundant-repeating-generations
Repo
Framework

A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization


Title	A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization
Authors	Renbo Zhao, Vincent Y. F. Tan
Abstract	The multiplicative update (MU) algorithm has been extensively used to estimate the basis and coefficient matrices in nonnegative matrix factorization (NMF) problems under a wide range of divergences and regularizers. However, theoretical convergence guarantees have only been derived for a few special divergences without regularization. In this work, we provide a conceptually simple, self-contained, and unified proof for the convergence of the MU algorithm applied on NMF with a wide range of divergences and regularizers. Our main result shows the sequence of iterates (i.e., pairs of basis and coefficient matrices) produced by the MU algorithm converges to the set of stationary points of the non-convex NMF optimization problem. Our proof strategy has the potential to open up new avenues for analyzing similar problems in machine learning and signal processing.
Tasks
Published	2016-09-04
URL	http://arxiv.org/abs/1609.00951v3
PDF	http://arxiv.org/pdf/1609.00951v3.pdf
PWC	https://paperswithcode.com/paper/a-unified-convergence-analysis-of-the
Repo
Framework

Automatic Techniques for Gridding cDNA Microarray Images


Title	Automatic Techniques for Gridding cDNA Microarray Images
Authors	Naima Kaabouch, Hamid Shahbazkia
Abstract	Microarray is considered an important instrument and powerful new technology for large-scale gene sequence and gene expression analysis. One of the major challenges of this technique is the image processing phase. The accuracy of this phase has an important impact on the accuracy and effectiveness of the subsequent gene expression and identification analysis. The processing can be organized mainly into four steps: gridding, spot isolation, segmentation, and quantification. Although several commercial software packages are now available, microarray image analysis still requires some intervention by the user, and thus a certain level of image processing expertise. This paper describes and compares four techniques that perform automatic gridding and spot isolation. The proposed techniques are based on template matching technique, standard deviation, sum, and derivative of these profiles. Experimental results show that the accuracy of the derivative of the sum profile is highly accurate compared to other techniques for good and poor quality microarray images.
Tasks
Published	2016-07-03
URL	http://arxiv.org/abs/1607.00592v1
PDF	http://arxiv.org/pdf/1607.00592v1.pdf
PWC	https://paperswithcode.com/paper/automatic-techniques-for-gridding-cdna
Repo
Framework

Adaptive Graph-based Total Variation for Tomographic Reconstructions


Title	Adaptive Graph-based Total Variation for Tomographic Reconstructions
Authors	Faisal Mahmood, Nauman Shahid, Ulf Skoglund, Pierre Vandergheynst
Abstract	Sparsity exploiting image reconstruction (SER) methods have been extensively used with Total Variation (TV) regularization for tomographic reconstructions. Local TV methods fail to preserve texture details and often create additional artefacts due to over-smoothing. Non-Local TV (NLTV) methods have been proposed as a solution to this but they either lack continuous updates due to computational constraints or limit the locality to a small region. In this paper, we propose Adaptive Graph-based TV (AGTV). The proposed method goes beyond spatial similarity between different regions of an image being reconstructed by establishing a connection between similar regions in the entire image regardless of spatial distance. As compared to NLTV the proposed method is computationally efficient and involves updating the graph prior during every iteration making the connection between similar regions stronger. Moreover, it promotes sparsity in the wavelet and graph gradient domains. Since TV is a special case of graph TV the proposed method can also be seen as a generalization of SER and TV methods.
Tasks	Image Reconstruction, Tomographic Reconstructions
Published	2016-10-04
URL	http://arxiv.org/abs/1610.00893v3
PDF	http://arxiv.org/pdf/1610.00893v3.pdf
PWC	https://paperswithcode.com/paper/adaptive-graph-based-total-variation-for
Repo
Framework

Learning Online Alignments with Continuous Rewards Policy Gradient


Title	Learning Online Alignments with Continuous Rewards Policy Gradient
Authors	Yuping Luo, Chung-Cheng Chiu, Navdeep Jaitly, Ilya Sutskever
Abstract	Sequence-to-sequence models with soft attention had significant success in machine translation, speech recognition, and question answering. Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition. To address this problem, we present a new method for solving sequence-to-sequence problems using hard online alignments instead of soft offline alignments. The online alignments model is able to start producing outputs without the need to first process the entire input sequence. A highly accurate online sequence-to-sequence model is useful because it can be used to build an accurate voice-based instantaneous translator. Our model uses hard binary stochastic decisions to select the timesteps at which outputs will be produced. The model is trained to produce these stochastic decisions using a standard policy gradient method. In our experiments, we show that this model achieves encouraging performance on TIMIT and Wall Street Journal (WSJ) speech recognition datasets.
Tasks	Machine Translation, Question Answering, Speech Recognition
Published	2016-08-03
URL	http://arxiv.org/abs/1608.01281v1
PDF	http://arxiv.org/pdf/1608.01281v1.pdf
PWC	https://paperswithcode.com/paper/learning-online-alignments-with-continuous
Repo
Framework

A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation


Title	A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation
Authors	Qiang Liu, Jason D. Lee, Michael I. Jordan
Abstract	We derive a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein’s identity with the reproducing kernel Hilbert space theory. We apply our result to test how well a probabilistic model fits a set of observations, and derive a new class of powerful goodness-of-fit tests that are widely applicable for complex and high dimensional distributions, even for those with computationally intractable normalization constants. Both theoretical and empirical properties of our methods are studied thoroughly.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03253v2
PDF	http://arxiv.org/pdf/1602.03253v2.pdf
PWC	https://paperswithcode.com/paper/a-kernelized-stein-discrepancy-for-goodness
Repo
Framework

A Survey on Artificial Intelligence and Data Mining for MOOCs


Title	A Survey on Artificial Intelligence and Data Mining for MOOCs
Authors	Simon Fauvel, Han Yu
Abstract	Massive Open Online Courses (MOOCs) have gained tremendous popularity in the last few years. Thanks to MOOCs, millions of learners from all over the world have taken thousands of high-quality courses for free. Putting together an excellent MOOC ecosystem is a multidisciplinary endeavour that requires contributions from many different fields. Artificial intelligence (AI) and data mining (DM) are two such fields that have played a significant role in making MOOCs what they are today. By exploiting the vast amount of data generated by learners engaging in MOOCs, DM improves our understanding of the MOOC ecosystem and enables MOOC practitioners to deliver better courses. Similarly, AI, supported by DM, can greatly improve student experience and learning outcomes. In this survey paper, we first review the state-of-the-art artificial intelligence and data mining research applied to MOOCs, emphasising the use of AI and DM tools and techniques to improve student engagement, learning outcomes, and our understanding of the MOOC ecosystem. We then offer an overview of key trends and important research to carry out in the fields of AI and DM so that MOOCs can reach their full potential.
Tasks
Published	2016-01-26
URL	http://arxiv.org/abs/1601.06862v1
PDF	http://arxiv.org/pdf/1601.06862v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-artificial-intelligence-and-data
Repo
Framework

Improving Accuracy and Scalability of the PC Algorithm by Maximizing P-value


Title	Improving Accuracy and Scalability of the PC Algorithm by Maximizing P-value
Authors	Joseph Ramsey
Abstract	A number of attempts have been made to improve accuracy and/or scalability of the PC (Peter and Clark) algorithm, some well known (Buhlmann, et al., 2010; Kalisch and Buhlmann, 2007; 2008; Zhang, 2012, to give some examples). We add here one more tool to the toolbox: the simple observation that if one is forced to choose between a variety of possible conditioning sets for a pair of variables, one should choose the one with the highest p-value. One can use the CPC (Conservative PC, Ramsey et al., 2012) algorithm as a guide to possible sepsets for a pair of variables. However, whereas CPC uses a voting rule to classify colliders versus noncolliders, our proposed algorithm, PC-Max, picks the conditioning set with the highest p-value, so that there are no ambiguities. We combine this with two other optimizations: (a) avoiding bidirected edges in the orientation of colliders, and (b) parallelization. For (b) we borrow ideas from the PC-Stable algorithm (Colombo and Maathuis, 2014). The result is an algorithm that scales quite well both in terms of accuracy and time, with no risk of bidirected edges.
Tasks
Published	2016-10-03
URL	http://arxiv.org/abs/1610.00378v2
PDF	http://arxiv.org/pdf/1610.00378v2.pdf
PWC	https://paperswithcode.com/paper/improving-accuracy-and-scalability-of-the-pc
Repo
Framework


Title	Automated Management of Pothole related Disasters Using Image Processing and Geotagging
Authors	Madhura Katageri, Manisha Mandal, Mansi Gandhi, Navin Koregaonkar, Prof. Sharmila Sengupta
Abstract	Potholes though seem inconsequential, may cause accidents resulting in loss of human life. In this paper, we present an automated system to efficiently manage the potholes in a ward by deploying geotagging and image processing techniques that overcomes the drawbacks associated with the existing survey-oriented systems. Image processing is used for identification of target pothole regions in the 2D images using edge detection and morphological image processing operations. A method is developed to accurately estimate the dimensions of the potholes from their images, analyze their area and depth, estimate the quantity of filling material required and therefore enabling pothole attendance on a priority basis. This will further enable the government official to have a fully automated system for effectively managing pothole related disasters.
Tasks	Edge Detection
Published	2016-01-08
URL	http://arxiv.org/abs/1610.08808v1
PDF	http://arxiv.org/pdf/1610.08808v1.pdf
PWC	https://paperswithcode.com/paper/automated-management-of-pothole-related
Repo
Framework

Optimal Target Assignment and Path Finding for Teams of Agents


Title	Optimal Target Assignment and Path Finding for Teams of Agents
Authors	Hang Ma, Sven Koenig
Abstract	We study the TAPF (combined target-assignment and path-finding) problem for teams of agents in known terrain, which generalizes both the anonymous and non-anonymous multi-agent path-finding problems. Each of the teams is given the same number of targets as there are agents in the team. Each agent has to move to exactly one target given to its team such that all targets are visited. The TAPF problem is to first assign agents to targets and then plan collision-free paths for the agents to their targets in a way such that the makespan is minimized. We present the CBM (Conflict-Based Min-Cost-Flow) algorithm, a hierarchical algorithm that solves TAPF instances optimally by combining ideas from anonymous and non-anonymous multi-agent path-finding algorithms. On the low level, CBM uses a min-cost max-flow algorithm on a time-expanded network to assign all agents in a single team to targets and plan their paths. On the high level, CBM uses conflict-based search to resolve collisions among agents in different teams. Theoretically, we prove that CBM is correct, complete and optimal. Experimentally, we show the scalability of CBM to TAPF instances with dozens of teams and hundreds of agents and adapt it to a simulated warehouse system.
Tasks	Multi-Agent Path Finding
Published	2016-12-17
URL	http://arxiv.org/abs/1612.05693v1
PDF	http://arxiv.org/pdf/1612.05693v1.pdf
PWC	https://paperswithcode.com/paper/optimal-target-assignment-and-path-finding
Repo
Framework

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring


Title	GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
Authors	Wenying Ma, Liangliang Cao, Lei Yu, Guoping Long, Yucheng Li
Abstract	Fisher vector has been widely used in many multimedia retrieval and visual recognition applications with good performance. However, the computation complexity prevents its usage in real-time video monitoring. In this work, we proposed and implemented GPU-FV, a fast Fisher vector extraction method with the help of modern GPUs. The challenge of implementing Fisher vector on GPUs lies in the data dependency in feature extraction and expensive memory access in Fisher vector computing. To handle these challenges, we carefully designed GPU-FV in a way that utilizes the computing power of GPU as much as possible, and applied optimizations such as loop tiling to boost the performance. GPU-FV is about 12 times faster than the CPU version, and 50% faster than a non-optimized GPU implementation. For standard video input (320*240), GPU-FV can process each frame within 34ms on a model GPU. Our experiments show that GPU-FV obtains a similar recognition accuracy as traditional FV on VOC 2007 and Caltech 256 image sets. We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works. Especially, when the number of training examples are small, GPU-FV outperforms the recent popular deep CNN features borrowed from ImageNet. The code can be downloaded from the following link https://bitbucket.org/mawenjing/gpu-fv.
Tasks
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03498v1
PDF	http://arxiv.org/pdf/1604.03498v1.pdf
PWC	https://paperswithcode.com/paper/gpu-fv-realtime-fisher-vector-and-its
Repo
Framework

Analyzing Features for the Detection of Happy Endings in German Novels


Title	Analyzing Features for the Detection of Happy Endings in German Novels
Authors	Fotis Jannidis, Isabella Reger, Albin Zehe, Martin Becker, Lena Hettinger, Andreas Hotho
Abstract	With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels. Its focus lies on the investigation of previously proposed sentiment features in order to gain insight about the relevance of specific features on the one hand and the implications of their performance on the other hand. Therefore, we study various partitionings of novels, considering the highly variable concept of “ending”. We also show that our approach, even though still rather simple, can potentially lead to substantial findings relevant to literary studies.
Tasks	Sentiment Analysis
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09028v1
PDF	http://arxiv.org/pdf/1611.09028v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-features-for-the-detection-of-happy
Repo
Framework

Fast Incremental Method for Nonconvex Optimization


Title	Fast Incremental Method for Nonconvex Optimization
Authors	Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alex Smola
Abstract	We analyze a fast incremental aggregated gradient method for optimizing nonconvex problems of the form $\min_x \sum_i f_i(x)$. Specifically, we analyze the SAGA algorithm within an Incremental First-order Oracle framework, and show that it converges to a stationary point provably faster than both gradient descent and stochastic gradient descent. We also discuss a Polyak’s special class of nonconvex problems for which SAGA converges at a linear rate to the global optimum. Finally, we analyze the practically valuable regularized and minibatch variants of SAGA. To our knowledge, this paper presents the first analysis of fast convergence for an incremental aggregated gradient method for nonconvex problems.
Tasks
Published	2016-03-19
URL	http://arxiv.org/abs/1603.06159v1
PDF	http://arxiv.org/pdf/1603.06159v1.pdf
PWC	https://paperswithcode.com/paper/fast-incremental-method-for-nonconvex
Repo
Framework

Safety-Aware Robot Damage Recovery Using Constrained Bayesian Optimization and Simulated Priors


Title	Safety-Aware Robot Damage Recovery Using Constrained Bayesian Optimization and Simulated Priors
Authors	Vaios Papaspyros, Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Jean-Baptiste Mouret
Abstract	The recently introduced Intelligent Trial-and-Error (IT&E) algorithm showed that robots can adapt to damage in a matter of a few trials. The success of this algorithm relies on two components: prior knowledge acquired through simulation with an intact robot, and Bayesian optimization (BO) that operates on-line, on the damaged robot. While IT&E leads to fast damage recovery, it does not incorporate any safety constraints that prevent the robot from attempting harmful behaviors. In this work, we address this limitation by replacing the BO component with a constrained BO procedure. We evaluate our approach on a simulated damaged humanoid robot that needs to crawl as fast as possible, while performing as few unsafe trials as possible. We compare our new “safety-aware IT&E” algorithm to IT&E and a multi-objective version of IT&E in which the safety constraints are dealt as separate objectives. Our results show that our algorithm outperforms the other approaches, both in crawling speed within the safe regions and number of unsafe trials.
Tasks
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09419v3
PDF	http://arxiv.org/pdf/1611.09419v3.pdf
PWC	https://paperswithcode.com/paper/safety-aware-robot-damage-recovery-using
Repo
Framework

Towards Miss Universe Automatic Prediction: The Evening Gown Competition


Title	Towards Miss Universe Automatic Prediction: The Evening Gown Competition
Authors	Johanna Carvajal, Arnold Wiliem, Conrad Sanderson, Brian Lovell
Abstract	Can we predict the winner of Miss Universe after watching how they stride down the catwalk during the evening gown competition? Fashion gurus say they can! In our work, we study this question from the perspective of computer vision. In particular, we want to understand whether existing computer vision approaches can be used to automatically extract the qualities exhibited by the Miss Universe winners during their catwalk. This study can pave the way towards new vision-based applications for the fashion industry. To this end, we propose a novel video dataset, called the Miss Universe dataset, comprising 10 years of the evening gown competition selected between 1996-2010. We further propose two ranking-related problems: (1) Miss Universe Listwise Ranking and (2) Miss Universe Pairwise Ranking. In addition, we also develop an approach that simultaneously addresses the two proposed problems. To describe the videos we employ the recently proposed Stacked Fisher Vectors in conjunction with robust local spatio-temporal features. From our evaluation we found that although the addressed problems are extremely challenging, the proposed system is able to rank the winner in the top 3 best predicted scores for 5 out of 10 Miss Universe competitions.
Tasks
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07547v2
PDF	http://arxiv.org/pdf/1604.07547v2.pdf
PWC	https://paperswithcode.com/paper/towards-miss-universe-automatic-prediction
Repo
Framework