July 27, 2019

2920 words 14 mins read

Paper Group ANR 631

Graph Based Over-Segmentation Methods for 3D Point Clouds. Mosquito detection with low-cost smartphones: data acquisition for malaria research. A Semantically Motivated Approach to Compute ROUGE Scores. Discovery and recognition of motion primitives in human activities. Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknow …

Graph Based Over-Segmentation Methods for 3D Point Clouds


Title	Graph Based Over-Segmentation Methods for 3D Point Clouds
Authors	Yizhak Ben-Shabat, Tamar Avraham, Michael Lindenbaum, Anath Fischer
Abstract	Over-segmentation, or super-pixel generation, is a common preliminary stage for many computer vision applications. New acquisition technologies enable the capturing of 3D point clouds that contain color and geometrical information. This 3D information introduces a new conceptual change that can be utilized to improve the results of over-segmentation, which uses mainly color information, and to generate clusters of points we call super-points. We consider a variety of possible 3D extensions of the Local Variation (LV) graph based over-segmentation algorithms, and compare them thoroughly. We consider different alternatives for constructing the connectivity graph, for assigning the edge weights, and for defining the merge criterion, which must now account for the geometric information and not only color. Following this evaluation, we derive a new generic algorithm for over-segmentation of 3D point clouds. We call this new algorithm Point Cloud Local Variation (PCLV). The advantages of the new over-segmentation algorithm are demonstrated on both outdoor and cluttered indoor scenes. Performance analysis of the proposed approach compared to state-of-the-art 2D and 3D over-segmentation algorithms shows significant improvement according to the common performance measures.
Tasks
Published	2017-02-14
URL	http://arxiv.org/abs/1702.04114v1
PDF	http://arxiv.org/pdf/1702.04114v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-over-segmentation-methods-for-3d
Repo
Framework

Mosquito detection with low-cost smartphones: data acquisition for malaria research


Title	Mosquito detection with low-cost smartphones: data acquisition for malaria research
Authors	Yunpeng Li, Davide Zilli, Henry Chan, Ivan Kiskin, Marianne Sinka, Stephen Roberts, Kathy Willis
Abstract	Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount importance to the reduction of malaria transmission cases, but understanding in more forensic detail the interplay between malaria, mosquito vectors, vegetation, standing water and human populations is crucial to the deployment of more effective interventions. Typically the presence and detection of malaria-vectoring mosquitoes is only quantified by hand-operated insect traps or signified by the diagnosis of malaria. If we are to gather timely, large-scale data to improve this situation, we need to automate the process of mosquito detection and classification as much as possible. In this paper, we present a candidate mobile sensing system that acts as both a portable early warning device and an automatic acoustic data acquisition pipeline to help fuel scientific inquiry and policy. The machine learning algorithm that powers the mobile system achieves excellent off-line multi-species detection performance while remaining computationally efficient. Further, we have conducted preliminary live mosquito detection tests using low-cost mobile phones and achieved promising results. The deployment of this system for field usage in Southeast Asia and Africa is planned in the near future. In order to accelerate processing of field recordings and labelling of collected data, we employ a citizen science platform in conjunction with automated methods, the former implemented using the Zooniverse platform, allowing crowdsourcing on a grand scale.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1711.06346v3
PDF	http://arxiv.org/pdf/1711.06346v3.pdf
PWC	https://paperswithcode.com/paper/mosquito-detection-with-low-cost-smartphones
Repo
Framework

A Semantically Motivated Approach to Compute ROUGE Scores


Title	A Semantically Motivated Approach to Compute ROUGE Scores
Authors	Elaheh ShafieiBavani, Mohammad Ebrahimi, Raymond Wong, Fang Chen
Abstract	ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate abstractive summaries including lexical variations and paraphrasing. Exploring the effectiveness of lexical resource-based models to address this issue, we adopt a graph-based algorithm into ROUGE to capture the semantic similarities between peer and model summaries. Our semantically motivated approach computes ROUGE scores based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets indicate that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments.
Tasks	Semantic Similarity, Semantic Textual Similarity, Text Summarization
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07441v1
PDF	http://arxiv.org/pdf/1710.07441v1.pdf
PWC	https://paperswithcode.com/paper/a-semantically-motivated-approach-to-compute
Repo
Framework

Discovery and recognition of motion primitives in human activities


Title	Discovery and recognition of motion primitives in human activities
Authors	Marta Sanzari, Valsamis Ntouskos, Fiora Pirri
Abstract	We present a novel framework for the automatic discovery and recognition of motion primitives in videos of human activities. Given the 3D pose of a human in a video, human motion primitives are discovered by optimizing the `motion flux’, a quantity which captures the motion variation of a group of skeletal joints. A normalization of the primitives is proposed in order to make them invariant with respect to a subject anatomical variations and data sampling rate. The discovered primitives are unknown and unlabeled and are unsupervisedly collected into classes via a hierarchical non-parametric Bayes mixture model. Once classes are determined and labeled they are further analyzed for establishing models for recognizing discovered primitives. Each primitive model is defined by a set of learned parameters. Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models. Using our framework we build a publicly available dataset of human motion primitives, using sequences taken from well-known motion capture datasets. We expect that our framework, by providing an objective way for discovering and categorizing human motion, will be a useful tool in numerous research fields including video analysis, human inspired motion generation, learning by demonstration, intuitive human-robot interaction, and human behavior analysis. \|
Tasks	Motion Capture
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10494v7
PDF	http://arxiv.org/pdf/1709.10494v7.pdf
PWC	https://paperswithcode.com/paper/discovery-and-recognition-of-motion
Repo
Framework

Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknown Dimensions and Piece Orientation


Title	Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknown Dimensions and Piece Orientation
Authors	Dror Sholomon, Eli David, Nathan S. Netanyahu
Abstract	In this paper we propose the first genetic algorithm (GA)-based solver for jigsaw puzzles of unknown puzzle dimensions and unknown piece location and orientation. Our solver uses a novel crossover technique, and sets a new state-of-the-art in terms of the puzzle sizes solved and the accuracy obtained. The results are significantly improved, even when compared to previous solvers assuming known puzzle dimensions. Moreover, the solver successfully contends with a mixed bag of multiple puzzle pieces, assembling simultaneously all puzzles.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06766v1
PDF	http://arxiv.org/pdf/1711.06766v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithm-based-solver-for-very-large
Repo
Framework

Domain-adversarial neural networks to address the appearance variability of histopathology images


Title	Domain-adversarial neural networks to address the appearance variability of histopathology images
Authors	Maxime W. Lafarge, Josien P. W. Pluim, Koen A. J. Eppenhof, Pim Moeskops, Mitko Veta
Abstract	Preparing and scanning histopathology slides consists of several steps, each with a multitude of parameters. The parameters can vary between pathology labs and within the same lab over time, resulting in significant variability of the tissue appearance that hampers the generalization of automatic image analysis methods. Typically, this is addressed with ad-hoc approaches such as staining normalization that aim to reduce the appearance variability. In this paper, we propose a systematic solution based on domain-adversarial neural networks. We hypothesize that removing the domain information from the model representation leads to better generalization. We tested our hypothesis for the problem of mitosis detection in breast cancer histopathology images and made a comparative analysis with two other approaches. We show that combining color augmentation with domain-adversarial training is a better alternative than standard approaches to improve the generalization of deep learning methods.
Tasks	Mitosis Detection
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06183v1
PDF	http://arxiv.org/pdf/1707.06183v1.pdf
PWC	https://paperswithcode.com/paper/domain-adversarial-neural-networks-to-address
Repo
Framework

High-risk learning: acquiring new word vectors from tiny data


Title	High-risk learning: acquiring new word vectors from tiny data
Authors	Aurelie Herbelot, Marco Baroni
Abstract	Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn ‘a good vector’ for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task involving 2-6 sentences’ worth of context, showing a large increase in performance over state-of-the-art models on the definitional task.
Tasks	Language Modelling
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06556v1
PDF	http://arxiv.org/pdf/1707.06556v1.pdf
PWC	https://paperswithcode.com/paper/high-risk-learning-acquiring-new-word-vectors
Repo
Framework

Towards Accurate Markerless Human Shape and Pose Estimation over Time


Title	Towards Accurate Markerless Human Shape and Pose Estimation over Time
Authors	Yinghao Huang, Federica Bogo, Christoph Lassner, Angjoo Kanazawa, Peter V. Gehler, Ijaz Akhter, Michael J. Black
Abstract	Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios. Here we propose a fully automatic method that given multi-view video, estimates 3D human motion and body shape. We take recent SMPLify \cite{bogo2016keep} as the base method, and extend it in several ways. First we fit the body to 2D features detected in multi-view images. Second, we use a CNN method to segment the person in each image and fit the 3D body model to the contours to further improves accuracy. Third we utilize a generic and robust DCT temporal prior to handle the left and right side swapping issue sometimes introduced by the 2D pose estimator. Validation on standard benchmarks shows our results are comparable to the state of the art and also provide a realistic 3D shape avatar. We also demonstrate accurate results on HumanEva and on challenging dance sequences from YouTube in monocular case.
Tasks	Motion Capture, Pose Estimation
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07548v5
PDF	http://arxiv.org/pdf/1707.07548v5.pdf
PWC	https://paperswithcode.com/paper/towards-accurate-markerless-human-shape-and
Repo
Framework

Learning Depthwise Separable Graph Convolution from Data Manifold


Title	Learning Depthwise Separable Graph Convolution from Data Manifold
Authors	Guokun Lai, Hanxiao Liu, Yiming Yang
Abstract	Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations have been proposed for graphs or manifolds, their connections with traditional convolution over grid-structured data are not well-understood. In this paper, we show that depthwise separable convolution can be successfully generalized for the unification of both graph-based and grid-based convolution methods. Based on this insight we propose a novel Depthwise Separable Graph Convolution (DSGC) approach which is compatible with the tradition convolution network and subsumes existing convolution methods as special cases. It is equipped with the combined strengths in model expressiveness, compatibility (relatively small number of parameters), modularity and computational efficiency in training. Extensive experiments show the outstanding performance of DSGC in comparison with strong baselines on multi-domain benchmark datasets.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11577v3
PDF	http://arxiv.org/pdf/1710.11577v3.pdf
PWC	https://paperswithcode.com/paper/learning-depthwise-separable-graph
Repo
Framework

Adaptive Motion Gaming AI for Health Promotion


Title	Adaptive Motion Gaming AI for Health Promotion
Authors	Pujana Paliyawan, Takahiro Kusano, Yuto Nakagawa, Tomohiro Harada, Ruck Thawonmas
Abstract	This paper presents a design of a non-player character (AI) for promoting balancedness in use of body segments when engaging in full-body motion gaming. In our experiment, we settle a battle between the proposed AI and a player by using FightingICE, a fighting game platform for AI development. A middleware called UKI is used to allow the player to control the game by using body motion instead of the keyboard and mouse. During gameplay, the proposed AI analyze health states of the player; it determines its next action by predicting how each candidate action, recommended by a Monte-Carlo tree search algorithm, will induce the player to move, and how the player’s health tends to be affected. Our result demonstrates successful improvement in balancedness in use of body segments on 4 out of 5 subjects.
Tasks
Published	2017-04-04
URL	http://arxiv.org/abs/1704.00961v1
PDF	http://arxiv.org/pdf/1704.00961v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-motion-gaming-ai-for-health
Repo
Framework

Superpixel Based Segmentation and Classification of Polyps in Wireless Capsule Endoscopy


Title	Superpixel Based Segmentation and Classification of Polyps in Wireless Capsule Endoscopy
Authors	Omid Haji Maghsoudi
Abstract	Wireless Capsule Endoscopy (WCE) is a relatively new technology to record the entire GI trace, in vivo. The large amounts of frames captured during an examination cause difficulties for physicians to review all these frames. The need for reducing the reviewing time using some intelligent methods has been a challenge. Polyps are considered as growing tissues on the surface of intestinal tract not inside of an organ. Most polyps are not cancerous, but if one becomes larger than a centimeter, it can turn into cancer by great chance. The WCE frames provide the early stage possibility for detection of polyps. Here, the application of simple linear iterative clustering (SLIC) superpixel for segmentation of polyps in WCE frames is evaluated. Different SLIC superpixel numbers are examined to find the highest sensitivity for detection of polyps. The SLIC superpixel segmentation is promising to improve the results of previous studies. Finally, the superpixels were classified using a support vector machine (SVM) by extracting some texture and color features. The classification results showed a sensitivity of 91%.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07390v2
PDF	http://arxiv.org/pdf/1710.07390v2.pdf
PWC	https://paperswithcode.com/paper/superpixel-based-segmentation-and
Repo
Framework

Reinforcement Learning under Model Mismatch


Title	Reinforcement Learning under Model Mismatch
Authors	Aurko Roy, Huan Xu, Sebastian Pokutta
Abstract	We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the model-free Reinforcement Learning setting, where we do not have access to the model parameters, but can only sample states from it. We define robust versions of Q-learning, SARSA, and TD-learning and prove convergence to an approximately optimal robust policy and approximate value function respectively. We scale up the robust algorithms to large MDPs via function approximation and prove convergence under two different settings. We prove convergence of robust approximate policy iteration and robust approximate value iteration for linear architectures (under mild assumptions). We also define a robust loss function, the mean squared robust projected Bellman error and give stochastic gradient descent algorithms that are guaranteed to converge to a local minimum.
Tasks	Q-Learning
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04711v2
PDF	http://arxiv.org/pdf/1706.04711v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-under-model-mismatch
Repo
Framework

Auxiliary Guided Autoregressive Variational Autoencoders


Title	Auxiliary Guided Autoregressive Variational Autoencoders
Authors	Thomas Lucas, Jakob Verbeek
Abstract	Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local image statistics respectively, suggest hybrid models that encode global image structure into latent variables while autoregressively modeling low level detail. Previous approaches to such hybrid models restrict the capacity of the autoregressive decoder to prevent degenerate models that ignore the latent variables and only rely on autoregressive modeling. Our contribution is a training procedure relying on an auxiliary loss function that controls which information is captured by the latent variables and what is left to the autoregressive decoder. Our approach can leverage arbitrarily powerful autoregressive decoders, achieves state-of-the art quantitative performance among models with latent variables, and generates qualitatively convincing samples.
Tasks	Latent Variable Models
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11479v2
PDF	http://arxiv.org/pdf/1711.11479v2.pdf
PWC	https://paperswithcode.com/paper/auxiliary-guided-autoregressive-variational
Repo
Framework

Minimax Regret Bounds for Reinforcement Learning


Title	Minimax Regret Bounds for Reinforcement Learning
Authors	Mohammad Gheshlaghi Azar, Ian Osband, Rémi Munos
Abstract	We consider the problem of provably optimal exploration in reinforcement learning for finite horizon MDPs. We show that an optimistic modification to value iteration achieves a regret bound of $\tilde{O}( \sqrt{HSAT} + H^2S^2A+H\sqrt{T})$ where $H$ is the time horizon, $S$ the number of states, $A$ the number of actions and $T$ the number of time-steps. This result improves over the best previous known bound $\tilde{O}(HS \sqrt{AT})$ achieved by the UCRL2 algorithm of Jaksch et al., 2010. The key significance of our new results is that when $T\geq H^3S^3A$ and $SA\geq H$, it leads to a regret of $\tilde{O}(\sqrt{HSAT})$ that matches the established lower bound of $\Omega(\sqrt{HSAT})$ up to a logarithmic factor. Our analysis contains two key insights. We use careful application of concentration inequalities to the optimal value function as a whole, rather than to the transitions probabilities (to improve scaling in $S$), and we define Bernstein-based “exploration bonuses” that use the empirical variance of the estimated values at the next states (to improve scaling in $H$).
Tasks
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05449v2
PDF	http://arxiv.org/pdf/1703.05449v2.pdf
PWC	https://paperswithcode.com/paper/minimax-regret-bounds-for-reinforcement
Repo
Framework

Solving the L1 regularized least square problem via a box-constrained smooth minimization


Title	Solving the L1 regularized least square problem via a box-constrained smooth minimization
Authors	Majid Mohammadi, Wout Hofman, Yaohua Tan, S. Hamid Mousavi
Abstract	In this paper, an equivalent smooth minimization for the L1 regularized least square problem is proposed. The proposed problem is a convex box-constrained smooth minimization which allows applying fast optimization methods to find its solution. Further, it is investigated that the property “the dual of dual is primal” holds for the L1 regularized least square problem. A solver for the smooth problem is proposed, and its affinity to the proximal gradient is shown. Finally, the experiments on L1 and total variation regularized problems are performed, and the corresponding results are reported.
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03443v2
PDF	http://arxiv.org/pdf/1704.03443v2.pdf
PWC	https://paperswithcode.com/paper/solving-the-l1-regularized-least-square
Repo
Framework