May 7, 2019

3199 words 16 mins read

Paper Group ANR 63

Causes for Query Answers from Databases: Datalog Abduction, View-Updates, and Integrity Constraints. Edge Based Grid Super-Imposition for Crowd Emotion Recognition. Predict or classify: The deceptive role of time-locking in brain signal classification. Semantic Clustering for Robust Fine-Grained Scene Recognition. Semi-supervised knowledge extracti …

Causes for Query Answers from Databases: Datalog Abduction, View-Updates, and Integrity Constraints


Title	Causes for Query Answers from Databases: Datalog Abduction, View-Updates, and Integrity Constraints
Authors	Leopoldo Bertossi, Babak Salimi
Abstract	Causality has been recently introduced in databases, to model, characterize, and possibly compute causes for query answers. Connections between QA-causality and consistency-based diagnosis and database repairs (wrt. integrity constraint violations) have already been established. In this work we establish precise connections between QA-causality and both abductive diagnosis and the view-update problem in databases, allowing us to obtain new algorithmic and complexity results for QA-causality. We also obtain new results on the complexity of view-conditioned causality, and investigate the notion of QA-causality in the presence of integrity constraints, obtaining complexity results from a connection with view-conditioned causality. The abduction connection under integrity constraints allows us to obtain algorithmic tools for QA-causality.
Tasks
Published	2016-11-06
URL	http://arxiv.org/abs/1611.01711v3
PDF	http://arxiv.org/pdf/1611.01711v3.pdf
PWC	https://paperswithcode.com/paper/causes-for-query-answers-from-databases-1
Repo
Framework

Edge Based Grid Super-Imposition for Crowd Emotion Recognition


Title	Edge Based Grid Super-Imposition for Crowd Emotion Recognition
Authors	Amol Patwardhan
Abstract	Numerous automatic continuous emotion detection system studies have examined mostly use of videos and images containing individual person expressing emotions. This study examines the detection of spontaneous emotions in a group and crowd settings. Edge detection was used with a grid of lines superimposition to extract the features. The feature movement in terms of movement from the reference point was used to track across sequences of images from the color channel. Additionally the video data capturing was done on spontaneous emotions invoked by watching sports events from group of participants. The method was view and occlusion independent and the results were not affected by presence of multiple people chaotically expressing various emotions. The edge thresholds of 0.2 and grid thresholds of 20 showed the best accuracy results. The overall accuracy of the group emotion classifier was 70.9%.
Tasks	Edge Detection, Emotion Recognition
Published	2016-08-07
URL	http://arxiv.org/abs/1610.05566v1
PDF	http://arxiv.org/pdf/1610.05566v1.pdf
PWC	https://paperswithcode.com/paper/edge-based-grid-super-imposition-for-crowd
Repo
Framework

Predict or classify: The deceptive role of time-locking in brain signal classification


Title	Predict or classify: The deceptive role of time-locking in brain signal classification
Authors	Marco Rusconi, Angelo Valleriani
Abstract	Several experimental studies claim to be able to predict the outcome of simple decisions from brain signals measured before subjects are aware of their decision. Often, these studies use multivariate pattern recognition methods with the underlying assumption that the ability to classify the brain signal is equivalent to predict the decision itself. Here we show instead that it is possible to correctly classify a signal even if it does not contain any predictive information about the decision. We first define a simple stochastic model that mimics the random decision process between two equivalent alternatives, and generate a large number of independent trials that contain no choice-predictive information. The trials are first time-locked to the time point of the final event and then classified using standard machine-learning techniques. The resulting classification accuracy is above chance level long before the time point of time-locking. We then analyze the same trials using information theory. We demonstrate that the high classification accuracy is a consequence of time-locking and that its time behavior is simply related to the large relaxation time of the process. We conclude that when time-locking is a crucial step in the analysis of neural activity patterns, both the emergence and the timing of the classification accuracy are affected by structural properties of the network that generates the signal.
Tasks
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08228v2
PDF	http://arxiv.org/pdf/1605.08228v2.pdf
PWC	https://paperswithcode.com/paper/predict-or-classify-the-deceptive-role-of
Repo
Framework

Semantic Clustering for Robust Fine-Grained Scene Recognition


Title	Semantic Clustering for Robust Fine-Grained Scene Recognition
Authors	Marian George, Mandar Dixit, Gábor Zogg, Nuno Vasconcelos
Abstract	In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first propose a semantic scene descriptor that jointly captures the subtle differences between fine-grained scenes, while being robust to varying object configurations across domains. We model the occurrence patterns of objects in scenes, capturing the informativeness and discriminability of each object for each scene. We then transform such occurrences into scene probabilities for each scene image. Second, we argue that scene images belong to hidden semantic topics that can be discovered by clustering our semantic descriptors. To evaluate the proposed method, we propose a new fine-grained scene dataset in cross-domain settings. Extensive experiments on the proposed dataset and three benchmark scene datasets show the effectiveness of the proposed approach for fine-grained scene transfer, where we outperform state-of-the-art scene recognition and domain generalization methods.
Tasks	Domain Generalization, Scene Recognition
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07614v1
PDF	http://arxiv.org/pdf/1607.07614v1.pdf
PWC	https://paperswithcode.com/paper/semantic-clustering-for-robust-fine-grained
Repo
Framework

Semi-supervised knowledge extraction for detection of drugs and their effects


Title	Semi-supervised knowledge extraction for detection of drugs and their effects
Authors	Fabio Del Vigna, Marinella Petrocchi, Alessandro Tommasi, Cesare Zavattari, Maurizio Tesconi
Abstract	New Psychoactive Substances (NPS) are drugs that lay in a grey area of legislation, since they are not internationally and officially banned, possibly leading to their not prosecutable trade. The exacerbation of the phenomenon is that NPS can be easily sold and bought online. Here, we consider large corpora of textual posts, published on online forums specialized on drug discussions, plus a small set of known substances and associated effects, which we call seeds. We propose a semi-supervised approach to knowledge extraction, applied to the detection of drugs (comprising NPS) and effects from the corpora under investigation. Based on the very small set of initial seeds, the work highlights how a contrastive approach and context deduction are effective in detecting substances and effects from the corpora. Our promising results, which feature a F1 score close to 0.9, pave the way for shortening the detection time of new psychoactive substances, once these are discussed and advertised on the Internet.
Tasks
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06577v1
PDF	http://arxiv.org/pdf/1609.06577v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-knowledge-extraction-for
Repo
Framework

An Empirical Comparison of Sampling Quality Metrics: A Case Study for Bayesian Nonnegative Matrix Factorization


Title	An Empirical Comparison of Sampling Quality Metrics: A Case Study for Bayesian Nonnegative Matrix Factorization
Authors	Arjumand Masood, Weiwei Pan, Finale Doshi-Velez
Abstract	In this work, we empirically explore the question: how can we assess the quality of samples from some target distribution? We assume that the samples are provided by some valid Monte Carlo procedure, so we are guaranteed that the collection of samples will asymptotically approximate the true distribution. Most current evaluation approaches focus on two questions: (1) Has the chain mixed, that is, is it sampling from the distribution? and (2) How independent are the samples (as MCMC procedures produce correlated samples)? Focusing on the case of Bayesian nonnegative matrix factorization, we empirically evaluate standard metrics of sampler quality as well as propose new metrics to capture aspects that these measures fail to expose. The aspect of sampling that is of particular interest to us is the ability (or inability) of sampling methods to move between multiple optima in NMF problems. As a proxy, we propose and study a number of metrics that might quantify the diversity of a set of NMF factorizations obtained by a sampler through quantifying the coverage of the posterior distribution. We compare the performance of a number of standard sampling methods for NMF in terms of these new metrics.
Tasks
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06250v1
PDF	http://arxiv.org/pdf/1606.06250v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-comparison-of-sampling-quality
Repo
Framework

Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition


Title	Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition
Authors	Panqu Wang, Garrison Cottrell
Abstract	It is commonly believed that the central visual field is important for recognizing objects and faces, and the peripheral region is useful for scene recognition. However, the relative importance of central versus peripheral information for object, scene, and face recognition is unclear. In a behavioral study, Larson and Loschky (2009) investigated this question by measuring the scene recognition accuracy as a function of visual angle, and demonstrated that peripheral vision was indeed more useful in recognizing scenes than central vision. In this work, we modeled and replicated the result of Larson and Loschky (2009), using deep convolutional neural networks. Having fit the data for scenes, we used the model to predict future data for large-scale scene recognition as well as for objects and faces. Our results suggest that the relative order of importance of using central visual field information is face recognition>object recognition>scene recognition, and vice-versa for peripheral information.
Tasks	Face Recognition, Object Recognition, Scene Recognition
Published	2016-04-25
URL	http://arxiv.org/abs/1604.07457v1
PDF	http://arxiv.org/pdf/1604.07457v1.pdf
PWC	https://paperswithcode.com/paper/modeling-the-contribution-of-central-versus
Repo
Framework

Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation


Title	Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
Authors	Guo-Sen Xie, Xu-Yao Zhang, Shuicheng Yan, Cheng-Lin Liu
Abstract	Convolutional neural network (CNN) has achieved state-of-the-art performance in many different visual tasks. Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features. Moreover, CNN features are also transferable among different domains. On the other hand, traditional dictionarybased features (such as BoW and SPM) contain much more local discriminative and structural information, which is implicitly embedded in the images. To further improve the performance, in this paper, we propose to combine CNN with dictionarybased models for scene recognition and visual domain adaptation. Specifically, based on the well-tuned CNN models (e.g., AlexNet and VGG Net), two dictionary-based representations are further constructed, namely mid-level local representation (MLR) and convolutional Fisher vector representation (CFV). In MLR, an efficient two-stage clustering method, i.e., weighted spatial and feature space spectral clustering on the parts of a single image followed by clustering all representative parts of all images, is used to generate a class-mixture or a classspecific part dictionary. After that, the part dictionary is used to operate with the multi-scale image inputs for generating midlevel representation. In CFV, a multi-scale and scale-proportional GMM training strategy is utilized to generate Fisher vectors based on the last convolutional layer of CNN. By integrating the complementary information of MLR, CFV and the CNN features of the fully connected layer, the state-of-the-art performance can be achieved on scene recognition and domain adaptation problems. An interested finding is that our proposed hybrid representation (from VGG net trained on ImageNet) is also complementary with GoogLeNet and/or VGG-11 (trained on Place205) greatly.
Tasks	Domain Adaptation, Scene Recognition
Published	2016-01-29
URL	http://arxiv.org/abs/1601.07977v1
PDF	http://arxiv.org/pdf/1601.07977v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-cnn-and-dictionary-based-models-for
Repo
Framework

Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve


Title	Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve
Authors	Harikrishna Narasimhan, Shivani Agarwal
Abstract	The area under the ROC curve (AUC) is a widely used performance measure in machine learning. Increasingly, however, in several applications, ranging from ranking to biometric screening to medicine, performance is measured not in terms of the full area under the ROC curve, but in terms of the \emph{partial} area under the ROC curve between two false positive rates. In this paper, we develop support vector algorithms for directly optimizing the partial AUC between any two false positive rates. Our methods are based on minimizing a suitable proxy or surrogate objective for the partial AUC error. In the case of the full AUC, one can readily construct and optimize convex surrogates by expressing the performance measure as a summation of pairwise terms. The partial AUC, on the other hand, does not admit such a simple decomposable structure, making it more challenging to design and optimize (tight) convex surrogates for this measure. Our approach builds on the structural SVM framework of Joachims (2005) to design convex surrogates for partial AUC, and solves the resulting optimization problem using a cutting plane solver. Unlike the full AUC, where the combinatorial optimization needed in each iteration of the cutting plane solver can be decomposed and solved efficiently, the corresponding problem for the partial AUC is harder to decompose. One of our main contributions is a polynomial time algorithm for solving the combinatorial optimization problem associated with partial AUC. We also develop an approach for optimizing a tighter non-convex hinge loss based surrogate for the partial AUC using difference-of-convex programming. Our experiments on a variety of real-world and benchmark tasks confirm the efficacy of the proposed methods.
Tasks	Combinatorial Optimization
Published	2016-05-13
URL	http://arxiv.org/abs/1605.04337v1
PDF	http://arxiv.org/pdf/1605.04337v1.pdf
PWC	https://paperswithcode.com/paper/support-vector-algorithms-for-optimizing-the
Repo
Framework

Efficient Robust Proper Learning of Log-concave Distributions


Title	Efficient Robust Proper Learning of Log-concave Distributions
Authors	Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
Abstract	We study the {\em robust proper learning} of univariate log-concave distributions (over continuous and discrete domains). Given a set of samples drawn from an unknown target distribution, we want to compute a log-concave hypothesis distribution that is as close as possible to the target, in total variation distance. In this work, we give the first computationally efficient algorithm for this learning problem. Our algorithm achieves the information-theoretically optimal sample size (up to a constant factor), runs in polynomial time, and is robust to model misspecification with nearly-optimal error guarantees. Specifically, we give an algorithm that, on input $n=O(1/\eps^{5/2})$ samples from an unknown distribution $f$, runs in time $\widetilde{O}(n^{8/5})$, and outputs a log-concave hypothesis $h$ that (with high probability) satisfies $\dtv(h, f) = O(\opt)+\eps$, where $\opt$ is the minimum total variation distance between $f$ and the class of log-concave distributions. Our approach to the robust proper learning problem is quite flexible and may be applicable to many other univariate distribution families.
Tasks
Published	2016-06-09
URL	http://arxiv.org/abs/1606.03077v1
PDF	http://arxiv.org/pdf/1606.03077v1.pdf
PWC	https://paperswithcode.com/paper/efficient-robust-proper-learning-of-log
Repo
Framework

Predicting litigation likelihood and time to litigation for patents


Title	Predicting litigation likelihood and time to litigation for patents
Authors	Papis Wongchaisuwat, Diego Klabjan, John O. McGinnis
Abstract	Patent lawsuits are costly and time-consuming. An ability to forecast a patent litigation and time to litigation allows companies to better allocate budget and time in managing their patent portfolios. We develop predictive models for estimating the likelihood of litigation for patents and the expected time to litigation based on both textual and non-textual features. Our work focuses on improving the state-of-the-art by relying on a different set of features and employing more sophisticated algorithms with more realistic data. The rate of patent litigations is very low, which consequently makes the problem difficult. The initial model for predicting the likelihood is further modified to capture a time-to-litigation perspective.
Tasks
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07394v1
PDF	http://arxiv.org/pdf/1603.07394v1.pdf
PWC	https://paperswithcode.com/paper/predicting-litigation-likelihood-and-time-to
Repo
Framework

Quantifying and Reducing Stereotypes in Word Embeddings


Title	Quantifying and Reducing Stereotypes in Word Embeddings
Authors	Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai
Abstract	Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in {\em word embedding}, a popular framework to represent text data. As their use becomes increasingly common, applications can inadvertently amplify unwanted stereotypes. We show across multiple datasets that the embeddings contain significant gender stereotypes, especially with regard to professions. We created a novel gender analogy task and combined it with crowdsourcing to systematically quantify the gender bias in a given embedding. We developed an efficient algorithm that reduces gender stereotype using just a handful of training examples while preserving the useful geometric properties of the embedding. We evaluated our algorithm on several metrics. While we focus on male/female stereotypes, our framework may be applicable to other types of embedding biases.
Tasks	Word Embeddings
Published	2016-06-20
URL	http://arxiv.org/abs/1606.06121v1
PDF	http://arxiv.org/pdf/1606.06121v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-and-reducing-stereotypes-in-word
Repo
Framework

Leveraging Structural Context Models and Ranking Score Fusion for Human Interaction Prediction


Title	Leveraging Structural Context Models and Ranking Score Fusion for Human Interaction Prediction
Authors	Qiuhong Ke, Mohammed Bennamoun, Senjian An, Farid Bossaid, Ferdous Sohel
Abstract	Predicting an interaction before it is fully executed is very important in applications such as human-robot interaction and video surveillance. In a two-human interaction scenario, there often contextual dependency structure between the global interaction context of the two humans and the local context of the different body parts of each human. In this paper, we propose to learn the structure of the interaction contexts, and combine it with the spatial and temporal information of a video sequence for a better prediction of the interaction class. The structural models, including the spatial and the temporal models, are learned with Long Short Term Memory (LSTM) networks to capture the dependency of the global and local contexts of each RGB frame and each optical flow image, respectively. LSTM networks are also capable of detecting the key information from the global and local interaction contexts. Moreover, to effectively combine the structural models with the spatial and temporal models for interaction prediction, a ranking score fusion method is also introduced to automatically compute the optimal weight of each model for score fusion. Experimental results on the BIT Interaction and the UT-Interaction datasets clearly demonstrate the benefits of the proposed method.
Tasks	Optical Flow Estimation
Published	2016-08-18
URL	http://arxiv.org/abs/1608.05267v3
PDF	http://arxiv.org/pdf/1608.05267v3.pdf
PWC	https://paperswithcode.com/paper/leveraging-structural-context-models-and
Repo
Framework

Observation of dynamics inside an unlabeled live cell using bright-field photon microscopy: Evaluation of organelles’ trajectories


Title	Observation of dynamics inside an unlabeled live cell using bright-field photon microscopy: Evaluation of organelles’ trajectories
Authors	Renata Rychtarikova, Dalibor Stys
Abstract	This article presents an algorithm for the evaluation of organelles’ movements inside of an unmodified live cell. We used a time-lapse image series obtained using wide-field bright-field photon transmission microscopy as an algorithm input. The benefit of the algorithm is the application of the R'enyi information entropy, namely a variable called a point information gain, which enables to highlight the borders of the intracellular organelles and to localize the organelles’ centers of mass with the precision of one pixel.
Tasks
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04110v1
PDF	http://arxiv.org/pdf/1612.04110v1.pdf
PWC	https://paperswithcode.com/paper/observation-of-dynamics-inside-an-unlabeled
Repo
Framework

Automated quantification of one-dimensional nanostructure alignment on surfaces


Title	Automated quantification of one-dimensional nanostructure alignment on surfaces
Authors	Jianjin Dong, Irene A. Goldthorpe, Nasser Mohieddin Abukhdeir
Abstract	A method for automated quantification of the alignment of one-dimensional nanostructures from microscopy imaging is presented. Nanostructure alignment metrics are formulated and shown to able to rigorously quantify the orientational order of nanostructures within a two-dimensional domain (surface). A complementary image processing method is also presented which enables robust processing of microscopy images where overlapping nanostructures might be present. Scanning electron microscopy (SEM) images of nanowire-covered surfaces are analyzed using the presented methods and it is shown that past single parameter alignment metrics are insufficient for highly aligned domains. Through the use of multiple parameter alignment metrics, automated quantitative analysis of SEM images is shown to be possible and the alignment characteristics of different samples are able to be rigorously compared using a similarity metric. The results of this work provide researchers in nanoscience and nanotechnology with a rigorous method for the determination of structure/property relationships where alignment of one-dimensional nanostructures is significant.
Tasks
Published	2016-03-03
URL	http://arxiv.org/abs/1607.07297v1
PDF	http://arxiv.org/pdf/1607.07297v1.pdf
PWC	https://paperswithcode.com/paper/automated-quantification-of-one-dimensional
Repo
Framework