Paper Group ANR 511
Kernel-Based Structural Equation Models for Topology Identification of Directed Networks. Extending DLR with Labelled Tuples, Projections, Functional Dependencies and Objectification (full version). “Knowing value” logic as a normal modal logic. On the uniform one-dimensional fragment. Baseline CNN structure analysis for facial expression recogniti …
Kernel-Based Structural Equation Models for Topology Identification of Directed Networks
| Title | Kernel-Based Structural Equation Models for Topology Identification of Directed Networks |
| Authors | Yanning Shen, Brian Baingana, Georgios B. Giannakis |
| Abstract | Structural equation models (SEMs) have been widely adopted for inference of causal interactions in complex networks. Recent examples include unveiling topologies of hidden causal networks over which processes such as spreading diseases, or rumors propagate. The appeal of SEMs in these settings stems from their simplicity and tractability, since they typically assume linear dependencies among observable variables. Acknowledging the limitations inherent to adopting linear models, the present paper advocates nonlinear SEMs, which account for (possible) nonlinear dependencies among network nodes. The advocated approach leverages kernels as a powerful encompassing framework for nonlinear modeling, and an efficient estimator with affordable tradeoffs is put forth. Interestingly, pursuit of the novel kernel-based approach yields a convex regularized estimator that promotes edge sparsity, and is amenable to proximal-splitting optimization methods. To this end, solvers with complementary merits are developed by leveraging the alternating direction method of multipliers, and proximal gradient iterations. Experiments conducted on simulated data demonstrate that the novel approach outperforms linear SEMs with respect to edge detection errors. Furthermore, tests on a real gene expression dataset unveil interesting new edges that were not revealed by linear SEMs, which could shed more light on regulatory behavior of human genes. |
| Tasks | Edge Detection |
| Published | 2016-05-10 |
| URL | http://arxiv.org/abs/1605.03122v1 |
| http://arxiv.org/pdf/1605.03122v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-based-structural-equation-models-for |
| Repo | |
| Framework | |
Extending DLR with Labelled Tuples, Projections, Functional Dependencies and Objectification (full version)
| Title | Extending DLR with Labelled Tuples, Projections, Functional Dependencies and Objectification (full version) |
| Authors | Alessandro Artale, Enrico Franconi |
| Abstract | We introduce an extension of the n-ary description logic DLR to deal with attribute-labelled tuples (generalising the positional notation), with arbitrary projections of relations (inclusion dependencies), generic functional dependencies and with global and local objectification (reifying relations or their projections). We show how a simple syntactic condition on the appearance of projections and functional dependencies in a knowledge base makes the language decidable without increasing the computational complexity of the basic DLR language. |
| Tasks | |
| Published | 2016-04-04 |
| URL | http://arxiv.org/abs/1604.00799v1 |
| http://arxiv.org/pdf/1604.00799v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-dlr-with-labelled-tuples |
| Repo | |
| Framework | |
“Knowing value” logic as a normal modal logic
| Title | “Knowing value” logic as a normal modal logic |
| Authors | Tao Gu, Yanjing Wang |
| Abstract | Recent years witness a growing interest in nonstandard epistemic logics of “knowing whether”, “knowing what”, “knowing how”, and so on. These logics are usually not normal, i.e., the standard axioms and reasoning rules for modal logic may be invalid. In this paper, we show that the conditional “knowing value” logic proposed by Wang and Fan \cite{WF13} can be viewed as a disguised normal modal logic by treating the negation of the Kv operator as a special diamond. Under this perspective, it turns out that the original first-order Kripke semantics can be greatly simplified by introducing a ternary relation $R_i^c$ in standard Kripke models, which associates one world with two $i$-accessible worlds that do not agree on the value of constant $c$. Under intuitive constraints, the modal logic based on such Kripke models is exactly the one studied by Wang and Fan (2013,2014}. Moreover, there is a very natural binary generalization of the “knowing value” diamond, which, surprisingly, does not increase the expressive power of the logic. The resulting logic with the binary diamond has a transparent normal modal system, which sharpens our understanding of the “knowing value” logic and simplifies some previously hard problems. |
| Tasks | |
| Published | 2016-04-29 |
| URL | http://arxiv.org/abs/1604.08709v3 |
| http://arxiv.org/pdf/1604.08709v3.pdf | |
| PWC | https://paperswithcode.com/paper/knowing-value-logic-as-a-normal-modal-logic |
| Repo | |
| Framework | |
On the uniform one-dimensional fragment
| Title | On the uniform one-dimensional fragment |
| Authors | Antti Kuusisto |
| Abstract | The uniform one-dimensional fragment of first-order logic, U1, is a recently introduced formalism that extends two-variable logic in a natural way to contexts with relations of all arities. We survey properties of U1 and investigate its relationship to description logics designed to accommodate higher arity relations, with particular attention given to DLR_reg. We also define a description logic version of a variant of U1 and prove a range of new results concerning the expressivity of U1 and related logics. |
| Tasks | |
| Published | 2016-04-06 |
| URL | http://arxiv.org/abs/1604.01673v2 |
| http://arxiv.org/pdf/1604.01673v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-uniform-one-dimensional-fragment |
| Repo | |
| Framework | |
Baseline CNN structure analysis for facial expression recognition
| Title | Baseline CNN structure analysis for facial expression recognition |
| Authors | Minchul Shin, Munsang Kim, Dong-Soo Kwon |
| Abstract | We present a baseline convolutional neural network (CNN) structure and image preprocessing methodology to improve facial expression recognition algorithm using CNN. To analyze the most efficient network structure, we investigated four network structures that are known to show good performance in facial expression recognition. Moreover, we also investigated the effect of input image preprocessing methods. Five types of data input (raw, histogram equalization, isotropic smoothing, diffusion-based normalization, difference of Gaussian) were tested, and the accuracy was compared. We trained 20 different CNN models (4 networks x 5 data input types) and verified the performance of each network with test images from five different databases. The experiment result showed that a three-layer structure consisting of a simple convolutional and a max pooling layer with histogram equalization image input was the most efficient. We describe the detailed training procedure and analyze the result of the test accuracy based on considerable observation. |
| Tasks | Facial Expression Recognition |
| Published | 2016-11-14 |
| URL | http://arxiv.org/abs/1611.04251v1 |
| http://arxiv.org/pdf/1611.04251v1.pdf | |
| PWC | https://paperswithcode.com/paper/baseline-cnn-structure-analysis-for-facial |
| Repo | |
| Framework | |
Globally Optimal Object Tracking with Fully Convolutional Networks
| Title | Globally Optimal Object Tracking with Fully Convolutional Networks |
| Authors | Jinho Lee, Brian Kenji Iwana, Shouta Ide, Seiichi Uchida |
| Abstract | Tracking is one of the most important but still difficult tasks in computer vision and pattern recognition. The main difficulties in the tracking field are appearance variation and occlusion. Most traditional tracking methods set the parameters or templates to track target objects in advance and should be modified accordingly. Thus, we propose a new and robust tracking method using a Fully Convolutional Network (FCN) to obtain an object probability map and Dynamic Programming (DP) to seek the globally optimal path through all frames of video. Our proposed method solves the object appearance variation problem with the use of a FCN and deals with occlusion by DP. We show that our method is effective in tracking various single objects through video frames. |
| Tasks | Object Tracking |
| Published | 2016-12-25 |
| URL | http://arxiv.org/abs/1612.08274v1 |
| http://arxiv.org/pdf/1612.08274v1.pdf | |
| PWC | https://paperswithcode.com/paper/globally-optimal-object-tracking-with-fully |
| Repo | |
| Framework | |
Beyond Brightness Constancy: Learning Noise Models for Optical Flow
| Title | Beyond Brightness Constancy: Learning Noise Models for Optical Flow |
| Authors | Dan Rosenbaum, Yair Weiss |
| Abstract | Optical flow is typically estimated by minimizing a “data cost” and an optional regularizer. While there has been much work on different regularizers many modern algorithms still use a data cost that is not very different from the ones used over 30 years ago: a robust version of brightness constancy or gradient constancy. In this paper we leverage the recent availability of ground-truth optical flow databases in order to learn a data cost. Specifically we take a generative approach in which the data cost models the distribution of noise after warping an image according to the flow and we measure the “goodness” of a data cost by how well it matches the true distribution of flow warp error. Consistent with current practice, we find that robust versions of gradient constancy are better models than simple brightness constancy but a learned GMM that models the density of patches of warp error gives a much better fit than any existing assumption of constancy. This significant advantage of the GMM is due to an explicit modeling of the spatial structure of warp errors, a feature which is missing from almost all existing data costs in optical flow. Finally, we show how a good density model of warp error patches can be used for optical flow estimation on whole images. We replace the data cost by the expected patch log-likelihood (EPLL), and show how this cost can be optimized iteratively using an additional step of denoising the warp error image. The results of our experiments are promising and show that patch models with higher likelihood lead to better optical flow estimation. |
| Tasks | Denoising, Optical Flow Estimation |
| Published | 2016-04-11 |
| URL | http://arxiv.org/abs/1604.02815v1 |
| http://arxiv.org/pdf/1604.02815v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-brightness-constancy-learning-noise |
| Repo | |
| Framework | |
Improving variational methods via pairwise linear response identities
| Title | Improving variational methods via pairwise linear response identities |
| Authors | Jack Raymond, Federico Ricci-Tersenghi |
| Abstract | Inference methods are often formulated as variational approximations: these approximations allow easy evaluation of statistics by marginalization or linear response, but these estimates can be inconsistent. We show that by introducing constraints on covariance, one can ensure consistency of linear response with the variational parameters, and in so doing inference of marginal probability distributions is improved. For the Bethe approximation and its generalizations, improvements are achieved with simple choices of the constraints. The approximations are presented as variational frameworks; iterative procedures related to message passing are provided for finding the minima. |
| Tasks | |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00683v1 |
| http://arxiv.org/pdf/1611.00683v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-variational-methods-via-pairwise |
| Repo | |
| Framework | |
The Evolution of Sex through the Baldwin Effect
| Title | The Evolution of Sex through the Baldwin Effect |
| Authors | Larry Bull |
| Abstract | This paper suggests that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect. With this explanation for the basic cycle, the other associated phenomena can be explained as evolution tuning the amount and frequency of learning experienced by an organism. Using the well-known NK model of fitness landscapes it is shown that varying landscape ruggedness varies the benefit of the haploid-diploid cycle, whether based upon endomitosis or syngamy. The utility of pre-meiotic doubling and recombination during the cycle are also shown to vary with landscape ruggedness. This view is suggested as underpinning, rather than contradicting, many existing explanations for sex. |
| Tasks | |
| Published | 2016-07-01 |
| URL | http://arxiv.org/abs/1607.00318v15 |
| http://arxiv.org/pdf/1607.00318v15.pdf | |
| PWC | https://paperswithcode.com/paper/the-evolution-of-sex-through-the-baldwin |
| Repo | |
| Framework | |
A combined Approach Based on Fuzzy Classification and Contextual Region Growing to Image Segmentation
| Title | A combined Approach Based on Fuzzy Classification and Contextual Region Growing to Image Segmentation |
| Authors | Mahaman Sani Chaibou, Karim Kalti, Bassel Soulaiman, Mohamed Ali Mahjoub |
| Abstract | We present in this paper an image segmentation approach that combines a fuzzy semantic region classification and a context based region-growing. Input image is first over-segmented. Then, prior domain knowledge is used to perform a fuzzy classification of these regions to provide a fuzzy semantic labeling. This allows the proposed approach to operate at high level instead of using low-level features and consequently to remedy to the problem of the semantic gap. Each over-segmented region is represented by a vector giving its corresponding membership degrees to the different thematic labels and the whole image is therefore represented by a Regions Partition Matrix. The segmentation is achieved on this matrix instead of the image pixels through two main phases: focusing and propagation. The focusing aims at selecting seeds regions from which information propagation will be performed. Thepropagation phase allows to spread toward others regions and using fuzzy contextual information the needed knowledge ensuring the semantic segmentation. An application of the proposed approach on mammograms shows promising results |
| Tasks | Semantic Segmentation |
| Published | 2016-08-08 |
| URL | http://arxiv.org/abs/1608.02373v1 |
| http://arxiv.org/pdf/1608.02373v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-combined-approach-based-on-fuzzy |
| Repo | |
| Framework | |
On the Complexity of One-class SVM for Multiple Instance Learning
| Title | On the Complexity of One-class SVM for Multiple Instance Learning |
| Authors | Zhen Hu, Zhuyin Xue |
| Abstract | In traditional multiple instance learning (MIL), both positive and negative bags are required to learn a prediction function. However, a high human cost is needed to know the label of each bag—positive or negative. Only positive bags contain our focus (positive instances) while negative bags consist of noise or background (negative instances). So we do not expect to spend too much to label the negative bags. Contrary to our expectation, nearly all existing MIL methods require enough negative bags besides positive ones. In this paper we propose an algorithm called “Positive Multiple Instance” (PMI), which learns a classifier given only a set of positive bags. So the annotation of negative bags becomes unnecessary in our method. PMI is constructed based on the assumption that the unknown positive instances in positive bags be similar each other and constitute one compact cluster in feature space and the negative instances locate outside this cluster. The experimental results demonstrate that PMI achieves the performances close to or a little worse than those of the traditional MIL algorithms on benchmark and real data sets. However, the number of training bags in PMI is reduced significantly compared with traditional MIL algorithms. |
| Tasks | Multiple Instance Learning |
| Published | 2016-03-16 |
| URL | http://arxiv.org/abs/1603.04947v1 |
| http://arxiv.org/pdf/1603.04947v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-complexity-of-one-class-svm-for |
| Repo | |
| Framework | |
Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach
| Title | Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach |
| Authors | Saurav Ghosh, Prithwish Chakraborty, Emily Cohn, John S. Brownstein, Naren Ramakrishnan |
| Abstract | Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper, we motivate a disease vocabulary driven word2vec model (Dis2Vec) to model diseases and constituent attributes as word embeddings from the HealthMap news corpus. We use these word embeddings to automatically create disease taxonomies and evaluate our model against corresponding human annotated taxonomies. We compare our model accuracies against several state-of-the art word2vec methods. Our results demonstrate that Dis2Vec outperforms traditional distributed vector representations in its ability to faithfully capture taxonomical attributes across different class of diseases such as endemic, emerging and rare. |
| Tasks | Word Embeddings |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00106v2 |
| http://arxiv.org/pdf/1603.00106v2.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-diseases-from-unstructured |
| Repo | |
| Framework | |
Zero-Shot Visual Question Answering
| Title | Zero-Shot Visual Question Answering |
| Authors | Damien Teney, Anton van den Hengel |
| Abstract | Part of the appeal of Visual Question Answering (VQA) is its promise to answer new questions about previously unseen images. Most current methods demand training questions that illustrate every possible concept, and will therefore never achieve this capability, since the volume of required training data would be prohibitive. Answering general questions about images requires methods capable of Zero-Shot VQA, that is, methods able to answer questions beyond the scope of the training questions. We propose a new evaluation protocol for VQA methods which measures their ability to perform Zero-Shot VQA, and in doing so highlights significant practical deficiencies of current approaches, some of which are masked by the biases in current datasets. We propose and evaluate several strategies for achieving Zero-Shot VQA, including methods based on pretrained word embeddings, object classifiers with semantic embeddings, and test-time retrieval of example images. Our extensive experiments are intended to serve as baselines for Zero-Shot VQA, and they also achieve state-of-the-art performance in the standard VQA evaluation setting. |
| Tasks | Question Answering, Visual Question Answering, Word Embeddings |
| Published | 2016-11-17 |
| URL | http://arxiv.org/abs/1611.05546v2 |
| http://arxiv.org/pdf/1611.05546v2.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-visual-question-answering |
| Repo | |
| Framework | |
Gaussian Processes for Survival Analysis
| Title | Gaussian Processes for Survival Analysis |
| Authors | Tamara Fernández, Nicolás Rivera, Yee Whye Teh |
| Abstract | We introduce a semi-parametric Bayesian model for survival analysis. The model is centred on a parametric baseline hazard, and uses a Gaussian process to model variations away from it nonparametrically, as well as dependence on covariates. As opposed to many other methods in survival analysis, our framework does not impose unnecessary constraints in the hazard rate or in the survival function. Furthermore, our model handles left, right and interval censoring mechanisms common in survival analysis. We propose a MCMC algorithm to perform inference and an approximation scheme based on random Fourier features to make computations faster. We report experimental results on synthetic and real data, showing that our model performs better than competing models such as Cox proportional hazards, ANOVA-DDP and random survival forests. |
| Tasks | Gaussian Processes, Survival Analysis |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00817v1 |
| http://arxiv.org/pdf/1611.00817v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-processes-for-survival-analysis |
| Repo | |
| Framework | |
Learning Mobile App Usage Routine through Learning Automata
| Title | Learning Mobile App Usage Routine through Learning Automata |
| Authors | Ramin Rahnamoun, Reza Rawassizadeh, Arash Maskooki |
| Abstract | Since its conception, smart app market has grown exponentially. Success in the app market depends on many factors among which the quality of the app is a significant contributor, such as energy use. Nevertheless, smartphones, as a subset of mobile computing devices. inherit the limited power resource constraint. Therefore, there is a challenge of maintaining the resource while increasing the target app quality. This paper introduces Learning Automata (LA) as an online learning method to learn and predict the app usage routines of the users. Such prediction can leverage the app cache functionality of the operating system and thus (i) decreases app launch time and (ii) preserve battery. Our algorithm, which is an online learning approach, temporally updates and improves the internal states of itself. In particular, it learns the transition probabilities between app launching. Each App launching instance updates the transition probabilities related to that App, and this will result in improving the prediction. We benefit from a real-world lifelogging dataset and our experimental results show considerable success with respect to the two baseline methods that are used currently for smartphone app prediction approaches. |
| Tasks | |
| Published | 2016-08-11 |
| URL | http://arxiv.org/abs/1608.03507v2 |
| http://arxiv.org/pdf/1608.03507v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-mobile-app-usage-routine-through |
| Repo | |
| Framework | |
