Paper Group ANR 278
JaTeCS an open-source JAva TExt Categorization System. MOBA: a New Arena for Game AI. Online People Tracking and Identification with RFID and Kinect. Unsupervised Generative Adversarial Cross-modal Hashing. Small-loss bounds for online learning with partial information. Unsupervised Representation Learning by Sorting Sequences. Recovering Latent Si …
JaTeCS an open-source JAva TExt Categorization System
| Title | JaTeCS an open-source JAva TExt Categorization System |
| Authors | Andrea Esuli, Tiziano Fagni, Alejandro Moreo Fernandez |
| Abstract | JaTeCS is an open source Java library that supports research on automatic text categorization and other related problems, such as ordinal regression and quantification, which are of special interest in opinion mining applications. It covers all the steps of an experimental activity, from reading the corpus to the evaluation of the experimental results. As JaTeCS is focused on text as the main input data, it provides the user with many text-dedicated tools, e.g.: data readers for many formats, including the most commonly used text corpora and lexical resources, natural language processing tools, multi-language support, methods for feature selection and weighting, the implementation of many machine learning algorithms as well as wrappers for well-known external software (e.g., SVM_light) which enable their full control from code. JaTeCS support its expansion by abstracting through interfaces many of the typical tools and procedures used in text processing tasks. The library also provides a number of “template” implementations of typical experimental setups (e.g., train-test, k-fold validation, grid-search optimization, randomized runs) which enable fast realization of experiments just by connecting the templates with data readers, learning algorithms and evaluation measures. |
| Tasks | Feature Selection, Opinion Mining, Text Categorization |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06802v1 |
| http://arxiv.org/pdf/1706.06802v1.pdf | |
| PWC | https://paperswithcode.com/paper/jatecs-an-open-source-java-text |
| Repo | |
| Framework | |
MOBA: a New Arena for Game AI
| Title | MOBA: a New Arena for Game AI |
| Authors | Victor do Nascimento Silva, Luiz Chaimowicz |
| Abstract | Games have always been popular testbeds for Artificial Intelligence (AI). In the last decade, we have seen the rise of the Multiple Online Battle Arena (MOBA) games, which are the most played games nowadays. In spite of this, there are few works that explore MOBA as a testbed for AI Research. In this paper we present and discuss the main features and opportunities offered by MOBA games to Game AI Research. We describe the various challenges faced along the game and also propose a discrete model that can be used to better understand and explore the game. With this, we aim to encourage the use of MOBA as a novel research platform for Game AI. |
| Tasks | |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10443v1 |
| http://arxiv.org/pdf/1705.10443v1.pdf | |
| PWC | https://paperswithcode.com/paper/moba-a-new-arena-for-game-ai |
| Repo | |
| Framework | |
Online People Tracking and Identification with RFID and Kinect
| Title | Online People Tracking and Identification with RFID and Kinect |
| Authors | Xinyu Li, Yanyi Zhang, Ivan Marsic, Randall S. Burd |
| Abstract | We introduce a novel, accurate and practical system for real-time people tracking and identification. We used a Kinect V2 sensor for tracking that generates a body skeleton for up to six people in the view. We perform identification using both Kinect and passive RFID, by first measuring the velocity vector of person’s skeleton and of their RFID tag using the position of the RFID reader antennas as reference points and then finding the best match between skeletons and tags. We introduce a method for synchronizing Kinect data, which is captured regularly, with irregular or missing RFID data readouts. Our experiments show centimeter-level people tracking resolution with 80% average identification accuracy for up to six people in indoor environments, which meets the needs of many applications. Our system can preserve user privacy and work with different lighting. |
| Tasks | |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03824v1 |
| http://arxiv.org/pdf/1702.03824v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-people-tracking-and-identification |
| Repo | |
| Framework | |
Unsupervised Generative Adversarial Cross-modal Hashing
| Title | Unsupervised Generative Adversarial Cross-modal Hashing |
| Authors | Jian Zhang, Yuxin Peng, Mingkuan Yuan |
| Abstract | Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Unsupervised cross-modal hashing is more flexible and applicable than supervised methods, since no intensive labeling work is involved. However, existing unsupervised methods learn hashing functions by preserving inter and intra correlations, while ignoring the underlying manifold structure across different modalities, which is extremely helpful to capture meaningful nearest neighbors of different modalities for cross-modal retrieval. To address the above problem, in this paper we propose an Unsupervised Generative Adversarial Cross-modal Hashing approach (UGACH), which makes full use of GAN’s ability for unsupervised representation learning to exploit the underlying manifold structure of cross-modal data. The main contributions can be summarized as follows: (1) We propose a generative adversarial network to model cross-modal hashing in an unsupervised fashion. In the proposed UGACH, given a data of one modality, the generative model tries to fit the distribution over the manifold structure, and select informative data of another modality to challenge the discriminative model. The discriminative model learns to distinguish the generated data and the true positive data sampled from correlation graph to achieve better retrieval accuracy. These two models are trained in an adversarial way to improve each other and promote hashing function learning. (2) We propose a correlation graph based approach to capture the underlying manifold structure across different modalities, so that data of different modalities but within the same manifold can have smaller Hamming distance and promote retrieval accuracy. Extensive experiments compared with 6 state-of-the-art methods verify the effectiveness of our proposed approach. |
| Tasks | Cross-Modal Retrieval, Representation Learning, Unsupervised Representation Learning |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00358v1 |
| http://arxiv.org/pdf/1712.00358v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-generative-adversarial-cross |
| Repo | |
| Framework | |
Small-loss bounds for online learning with partial information
| Title | Small-loss bounds for online learning with partial information |
| Authors | Thodoris Lykouris, Karthik Sridharan, Eva Tardos |
| Abstract | We consider the problem of adversarial (non-stochastic) online learning with partial information feedback, where at each round, a decision maker selects an action from a finite set of alternatives. We develop a black-box approach for such problems where the learner observes as feedback only losses of a subset of the actions that includes the selected action. When losses of actions are non-negative, under the graph-based feedback model introduced by Mannor and Shamir, we offer algorithms that attain the so called “small-loss” $o(\alpha L^{\star})$ regret bounds with high probability, where $\alpha$ is the independence number of the graph, and $L^{\star}$ is the loss of the best action. Prior to our work, there was no data-dependent guarantee for general feedback graphs even for pseudo-regret (without dependence on the number of actions, i.e. utilizing the increased information feedback). Taking advantage of the black-box nature of our technique, we extend our results to many other applications such as semi-bandits (including routing in networks), contextual bandits (even with an infinite comparator class), as well as learning with slowly changing (shifting) comparators. In the special case of classical bandit and semi-bandit problems, we provide optimal small-loss, high-probability guarantees of $\tilde{O}(\sqrt{dL^{\star}})$ for actual regret, where $d$ is the number of actions, answering open questions of Neu. Previous bounds for bandits and semi-bandits were known only for pseudo-regret and only in expectation. We also offer an optimal $\tilde{O}(\sqrt{\kappa L^{\star}})$ regret guarantee for fixed feedback graphs with clique-partition number at most $\kappa$. |
| Tasks | Multi-Armed Bandits |
| Published | 2017-11-09 |
| URL | https://arxiv.org/abs/1711.03639v4 |
| https://arxiv.org/pdf/1711.03639v4.pdf | |
| PWC | https://paperswithcode.com/paper/small-loss-bounds-for-online-learning-with |
| Repo | |
| Framework | |
Unsupervised Representation Learning by Sorting Sequences
| Title | Unsupervised Representation Learning by Sorting Sequences |
| Authors | Hsin-Ying Lee, Jia-Bin Huang, Maneesh Singh, Ming-Hsuan Yang |
| Abstract | We present an unsupervised representation learning approach using videos without semantic labels. We leverage the temporal coherence as a supervisory signal by formulating representation learning as a sequence sorting task. We take temporally shuffled frames (i.e., in non-chronological order) as inputs and train a convolutional neural network to sort the shuffled sequences. Similar to comparison-based sorting algorithms, we propose to extract features from all frame pairs and aggregate them to predict the correct order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task allows us to learn rich and generalizable visual representation. We validate the effectiveness of the learned representation using our method as pre-training on high-level recognition problems. The experimental results show that our method compares favorably against state-of-the-art methods on action recognition, image classification and object detection tasks. |
| Tasks | Image Classification, Object Detection, Representation Learning, Temporal Action Localization, Unsupervised Representation Learning |
| Published | 2017-08-03 |
| URL | http://arxiv.org/abs/1708.01246v1 |
| http://arxiv.org/pdf/1708.01246v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-representation-learning-by |
| Repo | |
| Framework | |
Recovering Latent Signals from a Mixture of Measurements using a Gaussian Process Prior
| Title | Recovering Latent Signals from a Mixture of Measurements using a Gaussian Process Prior |
| Authors | Felipe Tobar, Gonzalo Rios, Tomás Valdivia, Pablo Guerrero |
| Abstract | In sensing applications, sensors cannot always measure the latent quantity of interest at the required resolution, sometimes they can only acquire a blurred version of it due the sensor’s transfer function. To recover latent signals when only noisy mixed measurements of the signal are available, we propose the Gaussian process mixture of measurements (GPMM), which models the latent signal as a Gaussian process (GP) and allows us to perform Bayesian inference on such signal conditional to a set of noisy mixture of measurements. We describe how to train GPMM, that is, to find the hyperparameters of the GP and the mixing weights, and how to perform inference on the latent signal under GPMM; additionally, we identify the solution to the underdetermined linear system resulting from a sensing application as a particular case of GPMM. The proposed model is validated in the recovery of three signals: a smooth synthetic signal, a real-world heart-rate time series and a step function, where GPMM outperformed the standard GP in terms of estimation error, uncertainty representation and recovery of the spectral content of the latent signal. |
| Tasks | Bayesian Inference, Time Series |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.05909v1 |
| http://arxiv.org/pdf/1707.05909v1.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-latent-signals-from-a-mixture-of |
| Repo | |
| Framework | |
Keyframe-Based Visual-Inertial Online SLAM with Relocalization
| Title | Keyframe-Based Visual-Inertial Online SLAM with Relocalization |
| Authors | Anton Kasyanov, Francis Engelmann, Jörg Stückler, Bastian Leibe |
| Abstract | Complementing images with inertial measurements has become one of the most popular approaches to achieve highly accurate and robust real-time camera pose tracking. In this paper, we present a keyframe-based approach to visual-inertial simultaneous localization and mapping (SLAM) for monocular and stereo cameras. Our visual-inertial SLAM system is based on a real-time capable visual-inertial odometry method that provides locally consistent trajectory and map estimates. We achieve global consistency in the estimate through online loop-closing and non-linear optimization. Furthermore, our system supports relocalization in a map that has been previously obtained and allows for continued SLAM operation. We evaluate our approach in terms of accuracy, relocalization capability and run-time efficiency on public indoor benchmark datasets and on newly recorded outdoor sequences. We demonstrate state-of-the-art performance of our system compared to a visual-inertial odometry method and baseline visual SLAM approaches in recovering the trajectory of the camera. |
| Tasks | Pose Tracking, Simultaneous Localization and Mapping |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.02175v2 |
| http://arxiv.org/pdf/1702.02175v2.pdf | |
| PWC | https://paperswithcode.com/paper/keyframe-based-visual-inertial-online-slam |
| Repo | |
| Framework | |
NIPS 2016 Workshop on Representation Learning in Artificial and Biological Neural Networks (MLINI 2016)
| Title | NIPS 2016 Workshop on Representation Learning in Artificial and Biological Neural Networks (MLINI 2016) |
| Authors | Leila Wehbe, Anwar Nunez-Elizalde, Marcel van Gerven, Irina Rish, Brian Murphy, Moritz Grosse-Wentrup, Georg Langs, Guillermo Cecchi |
| Abstract | This workshop explores the interface between cognitive neuroscience and recent advances in AI fields that aim to reproduce human performance such as natural language processing and computer vision, and specifically deep learning approaches to such problems. When studying the cognitive capabilities of the brain, scientists follow a system identification approach in which they present different stimuli to the subjects and try to model the response that different brain areas have of that stimulus. The goal is to understand the brain by trying to find the function that expresses the activity of brain areas in terms of different properties of the stimulus. Experimental stimuli are becoming increasingly complex with more and more people being interested in studying real life phenomena such as the perception of natural images or natural sentences. There is therefore a need for a rich and adequate vector representation of the properties of the stimulus, that we can obtain using advances in machine learning. In parallel, new ML approaches, many of which in deep learning, are inspired to a certain extent by human behavior or biological principles. Neural networks for example were originally inspired by biological neurons. More recently, processes such as attention are being used which have are inspired by human behavior. However, the large bulk of these methods are independent of findings about brain function, and it is unclear whether it is at all beneficial for machine learning to try to emulate brain function in order to achieve the same tasks that the brain achieves. |
| Tasks | Representation Learning |
| Published | 2017-01-06 |
| URL | http://arxiv.org/abs/1701.01437v2 |
| http://arxiv.org/pdf/1701.01437v2.pdf | |
| PWC | https://paperswithcode.com/paper/nips-2016-workshop-on-representation-learning |
| Repo | |
| Framework | |
Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph
| Title | Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph |
| Authors | Douglas Summers-Stay |
| Abstract | Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a straightforward way at each step in a chain of reasoning, drawing on knowledge from diverse sources and ontologies. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03232v1 |
| http://arxiv.org/pdf/1707.03232v1.pdf | |
| PWC | https://paperswithcode.com/paper/deductive-and-analogical-reasoning-on-a |
| Repo | |
| Framework | |
The impact of Entropy and Solution Density on selected SAT heuristics
| Title | The impact of Entropy and Solution Density on selected SAT heuristics |
| Authors | Dor Cohen, Ofer Strichman |
| Abstract | In a recent article [Oh’15], Oh examined the impact of various key heuristics (e.g., deletion strategy, restart policy, decay factor, database reduction) in competitive SAT solvers. His key findings are that their expected success depends on whether the input formula is satisfiable or not. To further investigate these findings, we focused on two properties of satisfiable formulas: the entropy of the formula, which approximates the freedom we have in assigning the variables, and the solution density, which is the number of solutions divided by the search space. We found that both predict better the effect of these heuristics, and that satisfiable formulas with small entropy `behave’ similarly to unsatisfiable formulas. | |
| Tasks | |
| Published | 2017-06-18 |
| URL | http://arxiv.org/abs/1706.05637v1 |
| http://arxiv.org/pdf/1706.05637v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-impact-of-entropy-and-solution-density-on |
| Repo | |
| Framework | |
DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification
| Title | DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification |
| Authors | Wentao Zhu, Chaochun Liu, Wei Fan, Xiaohui Xie |
| Abstract | In this work, we present a fully automated lung CT cancer diagnosis system, DeepLung. DeepLung contains two parts, nodule detection and classification. Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively. Specifically, a 3D Faster R-CNN is designed for nodule detection with a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network (DPN) features is proposed. The nodule classification subnetwork is validated on a public dataset from LIDC-IDRI, on which it achieves better performance than state-of-the-art approaches, and surpasses the average performance of four experienced doctors. For the DeepLung system, candidate nodules are detected first by the nodule detection subnetwork, and nodule diagnosis is conducted by the classification subnetwork. Extensive experimental results demonstrate the DeepLung is comparable to the experienced doctors both for the nodule-level and patient-level diagnosis on the LIDC-IDRI dataset. |
| Tasks | Automated Pulmonary Nodule Detection And Classification |
| Published | 2017-09-16 |
| URL | http://arxiv.org/abs/1709.05538v1 |
| http://arxiv.org/pdf/1709.05538v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeplung-3d-deep-convolutional-nets-for |
| Repo | |
| Framework | |
Bayesian Filtering for ODEs with Bounded Derivatives
| Title | Bayesian Filtering for ODEs with Bounded Derivatives |
| Authors | Emilia Magnani, Hans Kersting, Michael Schober, Philipp Hennig |
| Abstract | Recently there has been increasing interest in probabilistic solvers for ordinary differential equations (ODEs) that return full probability measures, instead of point estimates, over the solution and can incorporate uncertainty over the ODE at hand, e.g. if the vector field or the initial value is only approximately known or evaluable. The ODE filter proposed in recent work models the solution of the ODE by a Gauss-Markov process which serves as a prior in the sense of Bayesian statistics. While previous work employed a Wiener process prior on the (possibly multiple times) differentiated solution of the ODE and established equivalence of the corresponding solver with classical numerical methods, this paper raises the question whether other priors also yield practically useful solvers. To this end, we discuss a range of possible priors which enable fast filtering and propose a new prior–the Integrated Ornstein Uhlenbeck Process (IOUP)–that complements the existing Integrated Wiener process (IWP) filter by encoding the property that a derivative in time of the solution is bounded in the sense that it tends to drift back to zero. We provide experiments comparing IWP and IOUP filters which support the belief that IWP approximates better divergent ODE’s solutions whereas IOUP is a better prior for trajectories with bounded derivatives. |
| Tasks | |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08471v1 |
| http://arxiv.org/pdf/1709.08471v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-filtering-for-odes-with-bounded |
| Repo | |
| Framework | |
Learning to Inpaint for Image Compression
| Title | Learning to Inpaint for Image Compression |
| Authors | Mohammad Haris Baig, Vladlen Koltun, Lorenzo Torresani |
| Abstract | We study the design of deep architectures for lossy image compression. We present two architectural recipes in the context of multi-stage progressive encoders and empirically demonstrate their importance on compression performance. Specifically, we show that: (a) predicting the original image data from residuals in a multi-stage progressive architecture facilitates learning and leads to improved performance at approximating the original content and (b) learning to inpaint (from neighboring image pixels) before performing compression reduces the amount of information that must be stored to achieve a high-quality approximation. Incorporating these design choices in a baseline progressive encoder yields an average reduction of over $60%$ in file size with similar quality compared to the original residual encoder. |
| Tasks | Image Compression |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.08855v4 |
| http://arxiv.org/pdf/1709.08855v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-inpaint-for-image-compression |
| Repo | |
| Framework | |
Boosting Dictionary Learning with Error Codes
| Title | Boosting Dictionary Learning with Error Codes |
| Authors | Yigit Oktar, Mehmet Turkan |
| Abstract | In conventional sparse representations based dictionary learning algorithms, initial dictionaries are generally assumed to be proper representatives of the system at hand. However, this may not be the case, especially in some systems restricted to random initializations. Therefore, a supposedly optimal state-update based on such an improper model might lead to undesired effects that will be conveyed to successive iterations. In this paper, we propose a dictionary learning method which includes a general feedback process that codes the intermediate error left over from a less intensive initial learning attempt, and then adjusts sparse codes accordingly. Experimental observations show that such an additional step vastly improves rates of convergence in high-dimensional cases, also results in better converged states in the case of random initializations. Improvements also scale up with more lenient sparsity constraints. |
| Tasks | Dictionary Learning |
| Published | 2017-01-15 |
| URL | http://arxiv.org/abs/1701.04018v1 |
| http://arxiv.org/pdf/1701.04018v1.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-dictionary-learning-with-error-codes |
| Repo | |
| Framework | |
