July 28, 2019

2933 words 14 mins read

Paper Group ANR 382

Hand Gesture Recognition with Leap Motion. Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network. Learning detectors of malicious web requests for intrusion detection in network traffic. Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo. Content-based similar documen …

Hand Gesture Recognition with Leap Motion


Title	Hand Gesture Recognition with Leap Motion
Authors	Youchen Du, Shenglan Liu, Lin Feng, Menghui Chen, Jie Wu
Abstract	The recent introduction of depth cameras like Leap Motion Controller allows researchers to exploit the depth information to recognize hand gesture more robustly. This paper proposes a novel hand gesture recognition system with Leap Motion Controller. A series of features are extracted from Leap Motion tracking data, we feed these features along with HOG feature extracted from sensor images into a multi-class SVM classifier to recognize performed gesture, dimension reduction and feature weighted fusion are also discussed. Our results show that our model is much more accurate than previous work.
Tasks	Dimensionality Reduction, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2017-11-12
URL	http://arxiv.org/abs/1711.04293v1
PDF	http://arxiv.org/pdf/1711.04293v1.pdf
PWC	https://paperswithcode.com/paper/hand-gesture-recognition-with-leap-motion
Repo
Framework

Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network


Title	Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network
Authors	Oluwatobi Olabiyi, Eric Martinson, Vijay Chintalapudi, Rui Guo
Abstract	Advanced driver assistance systems (ADAS) can be significantly improved with effective driver action prediction (DAP). Predicting driver actions early and accurately can help mitigate the effects of potentially unsafe driving behaviors and avoid possible accidents. In this paper, we formulate driver action prediction as a timeseries anomaly prediction problem. While the anomaly (driver actions of interest) detection might be trivial in this context, finding patterns that consistently precede an anomaly requires searching for or extracting features across multi-modal sensory inputs. We present such a driver action prediction system, including a real-time data acquisition, processing and learning framework for predicting future or impending driver action. The proposed system incorporates camera-based knowledge of the driving environment and the driver themselves, in addition to traditional vehicle dynamics. It then uses a deep bidirectional recurrent neural network (DBRNN) to learn the correlation between sensory inputs and impending driver behavior achieving accurate and high horizon action prediction. The proposed system performs better than other existing systems on driver action prediction tasks and can accurately predict key driver actions including acceleration, braking, lane change and turning at durations of 5sec before the action is executed by the driver.
Tasks
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02257v1
PDF	http://arxiv.org/pdf/1706.02257v1.pdf
PWC	https://paperswithcode.com/paper/driver-action-prediction-using-deep
Repo
Framework

Learning detectors of malicious web requests for intrusion detection in network traffic


Title	Learning detectors of malicious web requests for intrusion detection in network traffic
Authors	Lukas Machlica, Karel Bartos, Michal Sofka
Abstract	This paper proposes a generic classification system designed to detect security threats based on the behavior of malware samples. The system relies on statistical features computed from proxy log fields to train detectors using a database of malware samples. The behavior detectors serve as basic reusable building blocks of the multi-level detection architecture. The detectors identify malicious communication exploiting encrypted URL strings and domains generated by a Domain Generation Algorithm (DGA) which are frequently used in Command and Control (C&C), phishing, and click fraud. Surprisingly, very precise detectors can be built given only a limited amount of information extracted from a single proxy log. This way, the computational requirements of the detectors are kept low which allows for deployment on a wide range of security devices and without depending on traffic context such as DNS logs, Whois records, webpage content, etc. Results on several weeks of live traffic from 100+ companies having 350k+ hosts show correct detection with a precision exceeding 95% of malicious flows, 95% of malicious URLs and 90% of infected hosts. In addition, a comparison with a signature and rule-based solution shows that our system is able to detect significant amount of new threats.
Tasks	Intrusion Detection
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02530v1
PDF	http://arxiv.org/pdf/1702.02530v1.pdf
PWC	https://paperswithcode.com/paper/learning-detectors-of-malicious-web-requests
Repo
Framework

Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo


Title	Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo
Authors	Mitsuru Igami
Abstract	Artificial intelligence (AI) has achieved superhuman performance in a growing number of tasks, but understanding and explaining AI remain challenging. This paper clarifies the connections between machine-learning algorithms to develop AIs and the econometrics of dynamic structural models through the case studies of three famous game AIs. Chess-playing Deep Blue is a calibrated value function, whereas shogi-playing Bonanza is an estimated value function via Rust’s (1987) nested fixed-point method. AlphaGo’s “supervised-learning policy network” is a deep neural network implementation of Hotz and Miller’s (1993) conditional choice probability estimation; its “reinforcement-learning value network” is equivalent to Hotz, Miller, Sanders, and Smith’s (1994) conditional choice simulation method. Relaxing these AIs’ implicit econometric assumptions would improve their structural interpretability.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10967v3
PDF	http://arxiv.org/pdf/1710.10967v3.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-as-structural
Repo
Framework

Content-based similar document image retrieval using fusion of CNN features


Title	Content-based similar document image retrieval using fusion of CNN features
Authors	Mao Tan, Si-Ping Yuan, Yong-Xin Su
Abstract	Rapid increase of digitized document give birth to high demand of document image retrieval. While conventional document image retrieval approaches depend on complex OCR-based text recognition and text similarity detection, this paper proposes a new content-based approach, in which more attention is paid to features extraction and fusion. In the proposed approach, multiple features of document images are extracted by different CNN models. After that, the extracted CNN features are reduced and fused into weighted average feature. Finally, the document images are ranked based on feature similarity to a provided query image. Experimental procedure is performed on a group of document images that transformed from academic papers, which contain both English and Chinese document, the results show that the proposed approach has good ability to retrieve document images with similar text content, and the fusion of CNN features can effectively improve the retrieval accuracy.
Tasks	Image Retrieval, Optical Character Recognition
Published	2017-03-23
URL	http://arxiv.org/abs/1703.08013v3
PDF	http://arxiv.org/pdf/1703.08013v3.pdf
PWC	https://paperswithcode.com/paper/content-based-similar-document-image
Repo
Framework

What’s In A Patch, II: Visualizing generic surfaces


Title	What’s In A Patch, II: Visualizing generic surfaces
Authors	Benjamin S. Kunsberg, Daniel Niels Holtmann-Rice, Steven W. Zucker
Abstract	We continue the development of a linear algebraic framework for the shape-from-shading problem, exploiting the manner in which tensors arise when scalar (e.g. image) and vector (e.g. surface normal) fields are differentiated multiple times. In this paper we apply that framework to develop Taylor expansions of the normal field and build a boot-strapping algorithm to find these polynomial surface solutions (under any light source) consistent with a given patch to arbitrary order. A generic constraint on the image derivatives restricts these solutions to a 2-D subspace, plus an unknown rotation matrix. The parameters for the subspace and rotation matrix encapsulate the ambiguity in the shading problem.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05902v1
PDF	http://arxiv.org/pdf/1705.05902v1.pdf
PWC	https://paperswithcode.com/paper/whats-in-a-patch-ii-visualizing-generic
Repo
Framework

Stochastic Gradient MCMC Methods for Hidden Markov Models


Title	Stochastic Gradient MCMC Methods for Hidden Markov Models
Authors	Yi-An Ma, Nicholas J. Foti, Emily B. Fox
Abstract	Stochastic gradient MCMC (SG-MCMC) algorithms have proven useful in scaling Bayesian inference to large datasets under an assumption of i.i.d data. We instead develop an SG-MCMC algorithm to learn the parameters of hidden Markov models (HMMs) for time-dependent data. There are two challenges to applying SG-MCMC in this setting: The latent discrete states, and needing to break dependencies when considering minibatches. We consider a marginal likelihood representation of the HMM and propose an algorithm that harnesses the inherent memory decay of the process. We demonstrate the effectiveness of our algorithm on synthetic experiments and an ion channel recording data, with runtimes significantly outperforming batch MCMC.
Tasks	Bayesian Inference
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04632v1
PDF	http://arxiv.org/pdf/1706.04632v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-gradient-mcmc-methods-for-hidden
Repo
Framework

Design and Implementation of Modified Fuzzy based CPU Scheduling Algorithm


Title	Design and Implementation of Modified Fuzzy based CPU Scheduling Algorithm
Authors	Rajani Kumari, Vivek Kumar Sharma, Sandeep Kumar
Abstract	CPU Scheduling is the base of multiprogramming. Scheduling is a process which decides order of task from a set of multiple tasks that are ready to execute. There are number of CPU scheduling algorithms available, but it is very difficult task to decide which one is better. This paper discusses the design and implementation of modified fuzzy based CPU scheduling algorithm. This paper present a new set of fuzzy rules. It demonstrates that scheduling done with new priority improves average waiting time and average turnaround time.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1706.02621v1
PDF	http://arxiv.org/pdf/1706.02621v1.pdf
PWC	https://paperswithcode.com/paper/design-and-implementation-of-modified-fuzzy
Repo
Framework


Title	Fake News in Social Networks
Authors	Christoph Aymanns, Jakob Foerster, Co-Pierre Georg
Abstract	We model the spread of news as a social learning game on a network. Agents can either endorse or oppose a claim made in a piece of news, which itself may be either true or false. Agents base their decision on a private signal and their neighbors’ past actions. Given these inputs, agents follow strategies derived via multi-agent deep reinforcement learning and receive utility from acting in accordance with the veracity of claims. Our framework yields strategies with agent utility close to a theoretical, Bayes optimal benchmark, while remaining flexible to model re-specification. Optimized strategies allow agents to correctly identify most false claims, when all agents receive unbiased private signals. However, an adversary’s attempt to spread fake news by targeting a subset of agents with a biased private signal can be successful. Even more so when the adversary has information about agents’ network position or private signal. When agents are aware of the presence of an adversary they re-optimize their strategies in the training stage and the adversary’s attack is less effective. Hence, exposing agents to the possibility of fake news can be an effective way to curtail the spread of fake news in social networks. Our results also highlight that information about the users’ private beliefs and their social network structure can be extremely valuable to adversaries and should be well protected.
Tasks
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06233v1
PDF	http://arxiv.org/pdf/1708.06233v1.pdf
PWC	https://paperswithcode.com/paper/fake-news-in-social-networks
Repo
Framework

Kernel Truncated Regression Representation for Robust Subspace Clustering


Title	Kernel Truncated Regression Representation for Robust Subspace Clustering
Authors	Liangli Zhen, Dezhong Peng, Wei Wang, Xin Yao
Abstract	Subspace clustering aims to group data points into multiple clusters of which each corresponds to one subspace. Most existing subspace clustering approaches assume that input data lie on linear subspaces. In practice, however, this assumption usually does not hold. To achieve nonlinear subspace clustering, we propose a novel method, called kernel truncated regression representation. Our method consists of the following four steps: 1) projecting the input data into a hidden space, where each data point can be linearly represented by other data points; 2) calculating the linear representation coefficients of the data representations in the hidden space; 3) truncating the trivial coefficients to achieve robustness and block-diagonality; and 4) executing the graph cutting operation on the coefficient matrix by solving a graph Laplacian problem. Our method has the advantages of a closed-form solution and the capacity of clustering data points that lie on nonlinear subspaces. The first advantage makes our method efficient in handling large-scale datasets, and the second one enables the proposed method to conquer the nonlinear subspace clustering challenge. Extensive experiments on six benchmarks demonstrate the effectiveness and the efficiency of the proposed method in comparison with current state-of-the-art approaches.
Tasks
Published	2017-05-15
URL	https://arxiv.org/abs/1705.05108v3
PDF	https://arxiv.org/pdf/1705.05108v3.pdf
PWC	https://paperswithcode.com/paper/kernel-truncated-regression-representation
Repo
Framework

Stochastic IMT (insulator-metal-transition) neurons: An interplay of thermal and threshold noise at bifurcation


Title	Stochastic IMT (insulator-metal-transition) neurons: An interplay of thermal and threshold noise at bifurcation
Authors	Abhinav Parihar, Matthew Jerry, Suman Datta, Arijit Raychowdhury
Abstract	Artificial neural networks can harness stochasticity in multiple ways to enable a vast class of computationally powerful models. Electronic implementation of such stochastic networks is currently limited to addition of algorithmic noise to digital machines which is inherently inefficient; albeit recent efforts to harness physical noise in devices for stochasticity have shown promise. To succeed in fabricating electronic neuromorphic networks we need experimental evidence of devices with measurable and controllable stochasticity which is complemented with the development of reliable statistical models of such observed stochasticity. Current research literature has sparse evidence of the former and a complete lack of the latter. This motivates the current article where we demonstrate a stochastic neuron using an insulator-metal-transition (IMT) device, based on electrically induced phase-transition, in series with a tunable resistance. We show that an IMT neuron has dynamics similar to a piecewise linear FitzHugh-Nagumo (FHN) neuron and incorporates all characteristics of a spiking neuron in the device phenomena. We experimentally demonstrate spontaneous stochastic spiking along with electrically controllable firing probabilities using Vanadium Dioxide (VO$_2$) based IMT neurons which show a sigmoid-like transfer function. The stochastic spiking is explained by two noise sources - thermal noise and threshold fluctuations, which act as precursors of bifurcation. As such, the IMT neuron is modeled as an Ornstein-Uhlenbeck (OU) process with a fluctuating boundary resulting in transfer curves that closely match experiments. As one of the first comprehensive studies of a stochastic neuron hardware and its statistical properties, this article would enable efficient implementation of a large class of neuro-mimetic networks and algorithms.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.06238v4
PDF	http://arxiv.org/pdf/1708.06238v4.pdf
PWC	https://paperswithcode.com/paper/stochastic-imt-insulator-metal-transition
Repo
Framework

Exact Approaches for the Travelling Thief Problem


Title	Exact Approaches for the Travelling Thief Problem
Authors	Junhua Wu, Markus Wagner, Sergey Polyakovskiy, Frank Neumann
Abstract	Many evolutionary and constructive heuristic approaches have been introduced in order to solve the Traveling Thief Problem (TTP). However, the accuracy of such approaches is unknown due to their inability to find global optima. In this paper, we propose three exact algorithms and a hybrid approach to the TTP. We compare these with state-of-the-art approaches to gather a comprehensive overview on the accuracy of heuristic methods for solving small TTP instances.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00331v1
PDF	http://arxiv.org/pdf/1708.00331v1.pdf
PWC	https://paperswithcode.com/paper/exact-approaches-for-the-travelling-thief
Repo
Framework

Active Control of Camera Parameters for Object Detection Algorithms


Title	Active Control of Camera Parameters for Object Detection Algorithms
Authors	Yulong Wu, John Tsotsos
Abstract	Camera parameters not only play an important role in determining the visual quality of perceived images, but also affect the performance of vision algorithms, for a vision-guided robot. By quantitatively evaluating four object detection algorithms, with respect to varying ambient illumination, shutter speed and voltage gain, it is observed that the performance of the algorithms is highly dependent on these variables. From this observation, a novel active control of camera parameters method is proposed, to make robot vision more robust under different light conditions. Experimental results demonstrate the effectiveness of our proposed approach, which improves the performance of object detection algorithms, compared with the conventional auto-exposure algorithm.
Tasks	Object Detection
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05685v1
PDF	http://arxiv.org/pdf/1705.05685v1.pdf
PWC	https://paperswithcode.com/paper/active-control-of-camera-parameters-for
Repo
Framework

Face Clustering: Representation and Pairwise Constraints


Title	Face Clustering: Representation and Pairwise Constraints
Authors	Yichun Shi, Charles Otto, Anil K. Jain
Abstract	Clustering face images according to their identity has two important applications: (i) grouping a collection of face images when no external labels are associated with images, and (ii) indexing for efficient large scale face retrieval. The clustering problem is composed of two key parts: face representation and choice of similarity for grouping faces. We first propose a representation based on ResNet, which has been shown to perform very well in image classification problems. Given this representation, we design a clustering algorithm, Conditional Pairwise Clustering (ConPaC), which directly estimates the adjacency matrix only based on the similarity between face images. This allows a dynamic selection of number of clusters and retains pairwise similarity between faces. ConPaC formulates the clustering problem as a Conditional Random Field (CRF) model and uses Loopy Belief Propagation to find an approximate solution for maximizing the posterior probability of the adjacency matrix. Experimental results on two benchmark face datasets (LFW and IJB-B) show that ConPaC outperforms well known clustering algorithms such as k-means, spectral clustering and approximate rank-order. Additionally, our algorithm can naturally incorporate pairwise constraints to obtain a semi-supervised version that leads to improved clustering performance. We also propose an k-NN variant of ConPaC, which has a linear time complexity given a k-NN graph, suitable for large datasets.
Tasks	Image Classification
Published	2017-06-15
URL	http://arxiv.org/abs/1706.05067v2
PDF	http://arxiv.org/pdf/1706.05067v2.pdf
PWC	https://paperswithcode.com/paper/face-clustering-representation-and-pairwise
Repo
Framework

Learning to Organize Knowledge and Answer Questions with N-Gram Machines


Title	Learning to Organize Knowledge and Answer Questions with N-Gram Machines
Authors	Fan Yang, Jiazhong Nie, William W. Cohen, Ni Lao
Abstract	Though deep neural networks have great success in natural language processing, they are limited at more knowledge intensive AI tasks, such as open-domain Question Answering (QA). Existing end-to-end deep QA models need to process the entire text after observing the question, and therefore their complexity in responding a question is linear in the text size. This is prohibitive for practical tasks such as QA from Wikipedia, a novel, or the Web. We propose to solve this scalability issue by using symbolic meaning representations, which can be indexed and retrieved efficiently with complexity that is independent of the text size. We apply our approach, called the N-Gram Machine (NGM), to three representative tasks. First as proof-of-concept, we demonstrate that NGM successfully solves the bAbI tasks of synthetic text. Second, we show that NGM scales to large corpus by experimenting on “life-long bAbI”, a special version of bAbI that contains millions of sentences. Lastly on the WikiMovies dataset, we use NGM to induce latent structure (i.e. schema) and answer questions from natural language Wikipedia text, with only QA pairs as weak supervision.
Tasks	Open-Domain Question Answering, Question Answering
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06744v4
PDF	http://arxiv.org/pdf/1711.06744v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-organize-knowledge-and-answer
Repo
Framework