Paper Group ANR 38
Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets. Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures. Facial expression recognition based on local region specific features and support vector machines. LIA-RAG: a system based on graphs and divergence of probabilities applie …
Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets
| Title | Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets |
| Authors | Vishwajeet Singh, Killamsetti Ravi Kumar, K Eswaran |
| Abstract | As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. In this paper, we present a novel way of learning discriminative features by training Deep Neural Nets which have Encoder or Decoder type architecture similar to an Autoencoder. We demonstrate that our approach can learn discriminative features which can perform better at pattern classification tasks when the number of training samples is relatively small in size. |
| Tasks | |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1607.01354v1 |
| http://arxiv.org/pdf/1607.01354v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-discriminative-features-using |
| Repo | |
| Framework | |
Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures
| Title | Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures |
| Authors | Raffaella Bernardi, Ruket Cakici, Desmond Elliott, Aykut Erdem, Erkut Erdem, Nazli Ikizler-Cinbis, Frank Keller, Adrian Muscat, Barbara Plank |
| Abstract | Automatic description generation from natural images is a challenging problem that has recently received a large amount of interest from the computer vision and natural language processing communities. In this survey, we classify the existing approaches based on how they conceptualize this problem, viz., models that cast description as either generation problem or as a retrieval problem over a visual or multimodal representational space. We provide a detailed review of existing models, highlighting their advantages and disadvantages. Moreover, we give an overview of the benchmark image datasets and the evaluation measures that have been developed to assess the quality of machine-generated image descriptions. Finally we extrapolate future directions in the area of automatic image description generation. |
| Tasks | |
| Published | 2016-01-15 |
| URL | http://arxiv.org/abs/1601.03896v2 |
| http://arxiv.org/pdf/1601.03896v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-description-generation-from-images |
| Repo | |
| Framework | |
Facial expression recognition based on local region specific features and support vector machines
| Title | Facial expression recognition based on local region specific features and support vector machines |
| Authors | Deepak Ghimire, Sunghwan Jeong, Joonwhoan Lee, Sang Hyun Park |
| Abstract | Facial expressions are one of the most powerful, natural and immediate means for human being to communicate their emotions and intensions. Recognition of facial expression has many applications including human-computer interaction, cognitive science, human emotion analysis, personality development etc. In this paper, we propose a new method for the recognition of facial expressions from single image frame that uses combination of appearance and geometric features with support vector machines classification. In general, appearance features for the recognition of facial expressions are computed by dividing face region into regular grid (holistic representation). But, in this paper we extracted region specific appearance features by dividing the whole face region into domain specific local regions. Geometric features are also extracted from corresponding domain specific regions. In addition, important local regions are determined by using incremental search approach which results in the reduction of feature dimension and improvement in recognition accuracy. The results of facial expressions recognition using features from domain specific regions are also compared with the results obtained using holistic representation. The performance of the proposed facial expression recognition system has been validated on publicly available extended Cohn-Kanade (CK+) facial expression data sets. |
| Tasks | Emotion Recognition, Facial Expression Recognition |
| Published | 2016-04-15 |
| URL | http://arxiv.org/abs/1604.04337v1 |
| http://arxiv.org/pdf/1604.04337v1.pdf | |
| PWC | https://paperswithcode.com/paper/facial-expression-recognition-based-on-local |
| Repo | |
| Framework | |
LIA-RAG: a system based on graphs and divergence of probabilities applied to Speech-To-Text Summarization
| Title | LIA-RAG: a system based on graphs and divergence of probabilities applied to Speech-To-Text Summarization |
| Authors | Elvys Linhares Pontes, Juan-Manuel Torres-Moreno, Andréa Carneiro Linhares |
| Abstract | This paper aims to introduces a new algorithm for automatic speech-to-text summarization based on statistical divergences of probabilities and graphs. The input is a text from speech conversations with noise, and the output a compact text summary. Our results, on the pilot task CCCS Multiling 2015 French corpus are very encouraging |
| Tasks | Text Summarization |
| Published | 2016-01-26 |
| URL | http://arxiv.org/abs/1601.07124v1 |
| http://arxiv.org/pdf/1601.07124v1.pdf | |
| PWC | https://paperswithcode.com/paper/lia-rag-a-system-based-on-graphs-and |
| Repo | |
| Framework | |
Boolean kernels for collaborative filtering in top-N item recommendation
| Title | Boolean kernels for collaborative filtering in top-N item recommendation |
| Authors | Mirko Polato, Fabio Aiolli |
| Abstract | In many personalized recommendation problems available data consists only of positive interactions (implicit feedback) between users and items. This problem is also known as One-Class Collaborative Filtering (OC-CF). Linear models usually achieve state-of-the-art performances on OC-CF problems and many efforts have been devoted to build more expressive and complex representations able to improve the recommendations. Recent analysis show that collaborative filtering (CF) datasets have peculiar characteristics such as high sparsity and a long tailed distribution of the ratings. In this paper we propose a boolean kernel, called Disjunctive kernel, which is less expressive than the linear one but it is able to alleviate the sparsity issue in CF contexts. The embedding of this kernel is composed by all the combinations of a certain arity d of the input variables, and these combined features are semantically interpreted as disjunctions of the input variables. Experiments on several CF datasets show the effectiveness and the efficiency of the proposed kernel. |
| Tasks | |
| Published | 2016-12-21 |
| URL | http://arxiv.org/abs/1612.07025v2 |
| http://arxiv.org/pdf/1612.07025v2.pdf | |
| PWC | https://paperswithcode.com/paper/boolean-kernels-for-collaborative-filtering |
| Repo | |
| Framework | |
Recognition of facial expressions based on salient geometric features and support vector machines
| Title | Recognition of facial expressions based on salient geometric features and support vector machines |
| Authors | Deepak Ghimire, Joonwhoan Lee, Ze-Nian Li, Sunghwan Jeong |
| Abstract | Facial expressions convey nonverbal cues which play an important role in interpersonal relations, and are widely used in behavior interpretation of emotions, cognitive science, and social interactions. In this paper we analyze different ways of representing geometric feature and present a fully automatic facial expression recognition (FER) system using salient geometric features. In geometric feature-based FER approach, the first important step is to initialize and track dense set of facial points as the expression evolves over time in consecutive frames. In the proposed system, facial points are initialized using elastic bunch graph matching (EBGM) algorithm and tracking is performed using Kanade-Lucas-Tomaci (KLT) tracker. We extract geometric features from point, line and triangle composed of tracking results of facial points. The most discriminative line and triangle features are extracted using feature selective multi-class AdaBoost with the help of extreme learning machine (ELM) classification. Finally the geometric features for FER are extracted from the boosted line, and triangles composed of facial points. The recognition accuracy using features from point, line and triangle are analyzed independently. The performance of the proposed FER system is evaluated on three different data sets: namely CK+, MMI and MUG facial expression data sets. |
| Tasks | Facial Expression Recognition, Graph Matching |
| Published | 2016-04-15 |
| URL | http://arxiv.org/abs/1604.04334v1 |
| http://arxiv.org/pdf/1604.04334v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognition-of-facial-expressions-based-on |
| Repo | |
| Framework | |
Geometric Feature-Based Facial Expression Recognition in Image Sequences Using Multi-Class AdaBoost and Support Vector Machines
| Title | Geometric Feature-Based Facial Expression Recognition in Image Sequences Using Multi-Class AdaBoost and Support Vector Machines |
| Authors | Deepak Ghimire, Joonwhoan Lee |
| Abstract | Facial expressions are widely used in the behavioral interpretation of emotions, cognitive science, and social interactions. In this paper, we present a novel method for fully automatic facial expression recognition in facial image sequences. As the facial expression evolves over time facial landmarks are automatically tracked in consecutive video frames, using displacements based on elastic bunch graph matching displacement estimation. Feature vectors from individual landmarks, as well as pairs of landmarks tracking results are extracted, and normalized, with respect to the first frame in the sequence. The prototypical expression sequence for each class of facial expression is formed, by taking the median of the landmark tracking results from the training facial expression sequences. Multi-class AdaBoost with dynamic time warping similarity distance between the feature vector of input facial expression and prototypical facial expression, is used as a weak classifier to select the subset of discriminative feature vectors. Finally, two methods for facial expression recognition are presented, either by using multi-class AdaBoost with dynamic time warping, or by using support vector machine on the boosted feature vectors. The results on the Cohn-Kanade (CK+) facial expression database show a recognition accuracy of 95.17% and 97.35% using multi-class AdaBoost and support vector machines, respectively. |
| Tasks | Facial Expression Recognition, Graph Matching, Landmark Tracking |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03225v1 |
| http://arxiv.org/pdf/1604.03225v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-feature-based-facial-expression |
| Repo | |
| Framework | |
Non-Evolutionary Superintelligences Do Nothing, Eventually
| Title | Non-Evolutionary Superintelligences Do Nothing, Eventually |
| Authors | Telmo Menezes |
| Abstract | There is overwhelming evidence that human intelligence is a product of Darwinian evolution. Investigating the consequences of self-modification, and more precisely, the consequences of utility function self-modification, leads to the stronger claim that not only human, but any form of intelligence is ultimately only possible within evolutionary processes. Human-designed artificial intelligences can only remain stable until they discover how to manipulate their own utility function. By definition, a human designer cannot prevent a superhuman intelligence from modifying itself, even if protection mechanisms against this action are put in place. Without evolutionary pressure, sufficiently advanced artificial intelligences become inert by simplifying their own utility function. Within evolutionary processes, the implicit utility function is always reducible to persistence, and the control of superhuman intelligences embedded in evolutionary processes is not possible. Mechanisms against utility function self-modification are ultimately futile. Instead, scientific effort toward the mitigation of existential risks from the development of superintelligences should be in two directions: understanding consciousness, and the complex dynamics of evolutionary systems. |
| Tasks | |
| Published | 2016-09-07 |
| URL | http://arxiv.org/abs/1609.02009v1 |
| http://arxiv.org/pdf/1609.02009v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-evolutionary-superintelligences-do |
| Repo | |
| Framework | |
A Birth and Death Process for Bayesian Network Structure Inference
| Title | A Birth and Death Process for Bayesian Network Structure Inference |
| Authors | D. Jennings, J. N. Corcoran |
| Abstract | Bayesian networks (BNs) are graphical models that are useful for representing high-dimensional probability distributions. There has been a great deal of interest in recent years in the NP-hard problem of learning the structure of a BN from observed data. Typically, one assigns a score to various structures and the search becomes an optimization problem that can be approached with either deterministic or stochastic methods. In this paper, we walk through the space of graphs by modeling the appearance and disappearance of edges as a birth and death process and compare our novel approach to the popular Metropolis-Hastings search strategy. We give empirical evidence that the birth and death process has superior mixing properties. |
| Tasks | |
| Published | 2016-10-01 |
| URL | http://arxiv.org/abs/1610.00189v1 |
| http://arxiv.org/pdf/1610.00189v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-birth-and-death-process-for-bayesian |
| Repo | |
| Framework | |
Patient Flow Prediction via Discriminative Learning of Mutually-Correcting Processes
| Title | Patient Flow Prediction via Discriminative Learning of Mutually-Correcting Processes |
| Authors | Hongteng Xu, Weichang Wu, Shamim Nemati, Hongyuan Zha |
| Abstract | Over the past decade the rate of care unit (CU) use in the United States has been increasing. With an aging population and ever-growing demand for medical care, effective management of patients’ transitions among different care facilities will prove indispensible for shortening the length of hospital stays, improving patient outcomes, allocating critical care resources, and reducing preventable re-admissions. In this paper, we focus on an important problem of predicting the so-called “patient flow” from longitudinal electronic health records (EHRs), which has not been explored via existing machine learning techniques. By treating a sequence of transition events as a point process, we develop a novel framework for modeling patient flow through various CUs and jointly predicting patients’ destination CUs and duration days. Instead of learning a generative point process model via maximum likelihood estimation, we propose a novel discriminative learning algorithm aiming at improving the prediction of transition events in the case of sparse data. By parameterizing the proposed model as a mutually-correcting process, we formulate the estimation problem via generalized linear models, which lends itself to efficient learning based on alternating direction method of multipliers (ADMM). Furthermore, we achieve simultaneous feature selection and learning by adding a group-lasso regularizer to the ADMM algorithm. Additionally, for suppressing the negative influence of data imbalance on the learning of model, we synthesize auxiliary training data for the classes with extremely few samples, and improve the robustness of our learning method accordingly. Testing on real-world data, we show that our method obtains superior performance in terms of accuracy of predicting the destination CU transition and duration of each CU occupancy. |
| Tasks | Feature Selection |
| Published | 2016-02-14 |
| URL | http://arxiv.org/abs/1602.05112v3 |
| http://arxiv.org/pdf/1602.05112v3.pdf | |
| PWC | https://paperswithcode.com/paper/patient-flow-prediction-via-discriminative |
| Repo | |
| Framework | |
Towards Resolving Unidentifiability in Inverse Reinforcement Learning
| Title | Towards Resolving Unidentifiability in Inverse Reinforcement Learning |
| Authors | Kareem Amin, Satinder Singh |
| Abstract | We consider a setting for Inverse Reinforcement Learning (IRL) where the learner is extended with the ability to actively select multiple environments, observing an agent’s behavior on each environment. We first demonstrate that if the learner can experiment with any transition dynamics on some fixed set of states and actions, then there exists an algorithm that reconstructs the agent’s reward function to the fullest extent theoretically possible, and that requires only a small (logarithmic) number of experiments. We contrast this result to what is known about IRL in single fixed environments, namely that the true reward function is fundamentally unidentifiable. We then extend this setting to the more realistic case where the learner may not select any transition dynamic, but rather is restricted to some fixed set of environments that it may try. We connect the problem of maximizing the information derived from experiments to submodular function maximization and demonstrate that a greedy algorithm is near optimal (up to logarithmic factors). Finally, we empirically validate our algorithm on an environment inspired by behavioral psychology. |
| Tasks | |
| Published | 2016-01-25 |
| URL | http://arxiv.org/abs/1601.06569v1 |
| http://arxiv.org/pdf/1601.06569v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-resolving-unidentifiability-in |
| Repo | |
| Framework | |
Bayesian Inference on Matrix Manifolds for Linear Dimensionality Reduction
| Title | Bayesian Inference on Matrix Manifolds for Linear Dimensionality Reduction |
| Authors | Andrew Holbrook, Alexander Vandenberg-Rodes, Babak Shahbaba |
| Abstract | We reframe linear dimensionality reduction as a problem of Bayesian inference on matrix manifolds. This natural paradigm extends the Bayesian framework to dimensionality reduction tasks in higher dimensions with simpler models at greater speeds. Here an orthogonal basis is treated as a single point on a manifold and is associated with a linear subspace on which observations vary maximally. Throughout this paper, we employ the Grassmann and Stiefel manifolds for various dimensionality reduction problems, explore the connection between the two manifolds, and use Hybrid Monte Carlo for posterior sampling on the Grassmannian for the first time. We delineate in which situations either manifold should be considered. Further, matrix manifold models are used to yield scientific insight in the context of cognitive neuroscience, and we conclude that our methods are suitable for basic inference as well as accurate prediction. |
| Tasks | Bayesian Inference, Dimensionality Reduction |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04478v1 |
| http://arxiv.org/pdf/1606.04478v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-inference-on-matrix-manifolds-for |
| Repo | |
| Framework | |
Mining Social Media for Open Innovation in Transportation Systems
| Title | Mining Social Media for Open Innovation in Transportation Systems |
| Authors | Daniela Ulloa, Pedro Saleiro, Rosaldo J. F. Rossetti, Elis Regina Silva |
| Abstract | This work proposes a novel framework for the development of new products and services in transportation through an open innovation approach based on automatic content analysis of social media data. The framework is able to extract users comments from Online Social Networks (OSN), to process and analyze text through information extraction and sentiment analysis techniques to obtain relevant information about product reception on the market. A use case was developed using the mobile application Uber, which is today one of the fastest growing technology companies in the world. We measured how a controversial, highly diffused event influences the volume of tweets about Uber and the perception of its users. While there is no change in the image of Uber, a large increase in the number of tweets mentioning the company is observed, which meant a free and important diffusion of its product. |
| Tasks | Sentiment Analysis |
| Published | 2016-10-31 |
| URL | http://arxiv.org/abs/1610.09894v1 |
| http://arxiv.org/pdf/1610.09894v1.pdf | |
| PWC | https://paperswithcode.com/paper/mining-social-media-for-open-innovation-in |
| Repo | |
| Framework | |
Mitosis Detection in Intestinal Crypt Images with Hough Forest and Conditional Random Fields
| Title | Mitosis Detection in Intestinal Crypt Images with Hough Forest and Conditional Random Fields |
| Authors | Gerda Bortsova, Michael Sterr, Lichao Wang, Fausto Milletari, Nassir Navab, Anika Böttcher, Heiko Lickert, Fabian Theis, Tingying Peng |
| Abstract | Intestinal enteroendocrine cells secrete hormones that are vital for the regulation of glucose metabolism but their differentiation from intestinal stem cells is not fully understood. Asymmetric stem cell divisions have been linked to intestinal stem cell homeostasis and secretory fate commitment. We monitored cell divisions using 4D live cell imaging of cultured intestinal crypts to characterize division modes by means of measurable features such as orientation or shape. A statistical analysis of these measurements requires annotation of mitosis events, which is currently a tedious and time-consuming task that has to be performed manually. To assist data processing, we developed a learning based method to automatically detect mitosis events. The method contains a dual-phase framework for joint detection of dividing cells (mothers) and their progeny (daughters). In the first phase we detect mother and daughters independently using Hough Forest whilst in the second phase we associate mother and daughters by modelling their joint probability as Conditional Random Field (CRF). The method has been evaluated on 32 movies and has achieved an AUC of 72%, which can be used in conjunction with manual correction and dramatically speed up the processing pipeline. |
| Tasks | Mitosis Detection |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.07616v1 |
| http://arxiv.org/pdf/1608.07616v1.pdf | |
| PWC | https://paperswithcode.com/paper/mitosis-detection-in-intestinal-crypt-images |
| Repo | |
| Framework | |
The Right Mutation Strength for Multi-Valued Decision Variables
| Title | The Right Mutation Strength for Multi-Valued Decision Variables |
| Authors | Benjamin Doerr, Carola Doerr, Timo Kötzing |
| Abstract | The most common representation in evolutionary computation are bit strings. This is ideal to model binary decision variables, but less useful for variables taking more values. With very little theoretical work existing on how to use evolutionary algorithms for such optimization problems, we study the run time of simple evolutionary algorithms on some OneMax-like functions defined over $\Omega = {0, 1, \dots, r-1}^n$. More precisely, we regard a variety of problem classes requesting the component-wise minimization of the distance to an unknown target vector $z \in \Omega$. For such problems we see a crucial difference in how we extend the standard-bit mutation operator to these multi-valued domains. While it is natural to select each position of the solution vector to be changed independently with probability $1/n$, there are various ways to then change such a position. If we change each selected position to a random value different from the original one, we obtain an expected run time of $\Theta(nr \log n)$. If we change each selected position by either $+1$ or $-1$ (random choice), the optimization time reduces to $\Theta(nr + n\log n)$. If we use a random mutation strength $i \in {0,1,\ldots,r-1}^n$ with probability inversely proportional to $i$ and change the selected position by either $+i$ or $-i$ (random choice), then the optimization time becomes $\Theta(n \log(r)(\log(n)+\log(r)))$, bringing down the dependence on $r$ from linear to polylogarithmic. One of our results depends on a new variant of the lower bounding multiplicative drift theorem. |
| Tasks | |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03277v1 |
| http://arxiv.org/pdf/1604.03277v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-right-mutation-strength-for-multi-valued |
| Repo | |
| Framework | |
