October 19, 2019

2770 words 14 mins read

Paper Group ANR 179

Paper Group ANR 179

Multi-granularity Generator for Temporal Action Proposal. Subsampled Optimization: Statistical Guarantees, Mean Squared Error Approximation, and Sampling Method. Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold. Multidomain Document Layout Understanding using Few Shot Object Detection. Intrinsic Universal Measurements o …

Multi-granularity Generator for Temporal Action Proposal

Title Multi-granularity Generator for Temporal Action Proposal
Authors Yuan Liu, Lin Ma, Yifeng Zhang, Wei Liu, Shih-Fu Chang
Abstract Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information. First, we propose to use a bilinear matching model to exploit the rich local information within the video sequence. Afterwards, two components, namely segment proposal producer (SPP) and frame actionness producer (FAP), are combined to perform the task of temporal action proposal at two distinct granularities. SPP considers the whole video in the form of feature pyramid and generates segment proposals from one coarse perspective, while FAP carries out a finer actionness evaluation for each video frame. Our proposed MGG can be trained in an end-to-end fashion. By temporally adjusting the segment proposals with fine-grained frame actionness information, MGG achieves the superior performance over state-of-the-art methods on the public THUMOS-14 and ActivityNet-1.3 datasets. Moreover, we employ existing action classifiers to perform the classification of the proposals generated by MGG, leading to significant improvements compared against the competing methods for the video detection task.
Tasks Action Recognition In Videos, Temporal Action Proposal Generation
Published 2018-11-28
URL http://arxiv.org/abs/1811.11524v2
PDF http://arxiv.org/pdf/1811.11524v2.pdf
PWC https://paperswithcode.com/paper/multi-granularity-generator-for-temporal
Repo
Framework

Subsampled Optimization: Statistical Guarantees, Mean Squared Error Approximation, and Sampling Method

Title Subsampled Optimization: Statistical Guarantees, Mean Squared Error Approximation, and Sampling Method
Authors Rong Zhu, Jiming Jiang
Abstract For optimization on large-scale data, exactly calculating its solution may be computationally difficulty because of the large size of the data. In this paper we consider subsampled optimization for fast approximating the exact solution. In this approach, one gets a surrogate dataset by sampling from the full data, and then obtains an approximate solution by solving the subsampled optimization based on the surrogate. One main theoretical contributions are to provide the asymptotic properties of the approximate solution with respect to the exact solution as statistical guarantees, and to rigorously derive an accurate approximation of the mean squared error (MSE) and an approximately unbiased MSE estimator. These results help us better diagnose the subsampled optimization in the context that a confidence region on the exact solution is provided using the approximate solution. The other consequence of our results is to propose an optimal sampling method, Hessian-based sampling, whose probabilities are proportional to the norms of Newton directions. Numerical experiments with least-squares and logistic regression show promising performance, in line with our results.
Tasks
Published 2018-04-10
URL http://arxiv.org/abs/1804.03615v1
PDF http://arxiv.org/pdf/1804.03615v1.pdf
PWC https://paperswithcode.com/paper/subsampled-optimization-statistical
Repo
Framework

Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold

Title Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
Authors Shixiang Chen, Shiqian Ma, Anthony Man-Cho So, Tong Zhang
Abstract We consider optimization problems over the Stiefel manifold whose objective function is the summation of a smooth function and a nonsmooth function. Existing methods for solving this kind of problems can be classified into three classes. Algorithms in the first class rely on information of the subgradients of the objective function and thus tend to converge slowly in practice. Algorithms in the second class are proximal point algorithms, which involve subproblems that can be as difficult as the original problem. Algorithms in the third class are based on operator-splitting techniques, but they usually lack rigorous convergence guarantees. In this paper, we propose a retraction-based proximal gradient method for solving this class of problems. We prove that the proposed method globally converges to a stationary point. Iteration complexity for obtaining an $\epsilon$-stationary solution is also analyzed. Numerical results on solving sparse PCA and compressed modes problems are reported to demonstrate the advantages of the proposed method.
Tasks
Published 2018-11-02
URL https://arxiv.org/abs/1811.00980v2
PDF https://arxiv.org/pdf/1811.00980v2.pdf
PWC https://paperswithcode.com/paper/proximal-gradient-method-for-manifold
Repo
Framework

Multidomain Document Layout Understanding using Few Shot Object Detection

Title Multidomain Document Layout Understanding using Few Shot Object Detection
Authors Pranaydeep Singh, Srikrishna Varadarajan, Ankit Narayan Singh, Muktabh Mayank Srivastava
Abstract We try to address the problem of document layout understanding using a simple algorithm which generalizes across multiple domains while training on just few examples per domain. We approach this problem via supervised object detection method and propose a methodology to overcome the requirement of large datasets. We use the concept of transfer learning by pre-training our object detector on a simple artificial (source) dataset and fine-tuning it on a tiny domain specific (target) dataset. We show that this methodology works for multiple domains with training samples as less as 10 documents. We demonstrate the effect of each component of the methodology in the end result and show the superiority of this methodology over simple object detectors.
Tasks Few-Shot Object Detection, Object Detection, Transfer Learning
Published 2018-08-22
URL http://arxiv.org/abs/1808.07330v1
PDF http://arxiv.org/pdf/1808.07330v1.pdf
PWC https://paperswithcode.com/paper/multidomain-document-layout-understanding
Repo
Framework

Intrinsic Universal Measurements of Non-linear Embeddings

Title Intrinsic Universal Measurements of Non-linear Embeddings
Authors Ke Sun
Abstract A basic problem in machine learning is to find a mapping $f$ from a low dimensional latent space to a high dimensional observation space. Equipped with the representation power of non-linearity, a learner can easily find a mapping which perfectly fits all the observations. However such a mapping is often not considered as good as it is not simple enough and over-fits. How to define simplicity? This paper tries to make such a formal definition of the amount of information imposed by a non-linear mapping. This definition is based on information geometry and is independent of observations, nor specific parametrizations. We prove these basic properties and discuss relationships with parametric and non-parametric embeddings.
Tasks
Published 2018-11-05
URL http://arxiv.org/abs/1811.01464v1
PDF http://arxiv.org/pdf/1811.01464v1.pdf
PWC https://paperswithcode.com/paper/intrinsic-universal-measurements-of-non
Repo
Framework

Fast Vessel Segmentation and Tracking in Ultra High-Frequency Ultrasound Images

Title Fast Vessel Segmentation and Tracking in Ultra High-Frequency Ultrasound Images
Authors Tejas Sudharshan Mathai, Lingbo Jin, Vijay Gorantla, John Galeotti
Abstract Ultra High Frequency Ultrasound (UHFUS) enables the visualization of highly deformable small and medium vessels in the hand. Intricate vessel-based measurements, such as intimal wall thickness and vessel wall compliance, require sub-millimeter vessel tracking between B-scans. Our fast GPU-based approach combines the advantages of local phase analysis, a distance-regularized level set, and an Extended Kalman Filter (EKF), to rapidly segment and track the deforming vessel contour. We validated on 35 UHFUS sequences of vessels in the hand, and we show the transferability of the approach to 5 more diverse datasets acquired by a traditional High Frequency Ultrasound (HFUS) machine. To the best of our knowledge, this is the first algorithm capable of rapidly segmenting and tracking deformable vessel contours in 2D UHFUS images. It is also the fastest and most accurate system for 2D HFUS images.
Tasks
Published 2018-07-23
URL http://arxiv.org/abs/1807.08784v1
PDF http://arxiv.org/pdf/1807.08784v1.pdf
PWC https://paperswithcode.com/paper/fast-vessel-segmentation-and-tracking-in
Repo
Framework

Joint Flow: Temporal Flow Fields for Multi Person Tracking

Title Joint Flow: Temporal Flow Fields for Multi Person Tracking
Authors Andreas Doering, Umar Iqbal, Juergen Gall
Abstract In this work we propose an online multi person pose tracking approach which works on two consecutive frames $I_{t-1}$ and $I_t$. The general formulation of our temporal network allows to rely on any multi person pose estimation approach as spatial network. From the spatial network we extract image features and pose features for both frames. These features serve as input for our temporal model that predicts Temporal Flow Fields (TFF). These TFF are vector fields which indicate the direction in which each body joint is going to move from frame $I_{t-1}$ to frame $I_t$. This novel representation allows to formulate a similarity measure of detected joints. These similarities are used as binary potentials in a bipartite graph optimization problem in order to perform tracking of multiple poses. We show that these TFF can be learned by a relative small CNN network whilst achieving state-of-the-art multi person pose tracking results.
Tasks Multi-Person Pose Estimation, Pose Estimation, Pose Tracking
Published 2018-05-11
URL http://arxiv.org/abs/1805.04596v2
PDF http://arxiv.org/pdf/1805.04596v2.pdf
PWC https://paperswithcode.com/paper/joint-flow-temporal-flow-fields-for-multi
Repo
Framework

Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models - An Overview

Title Towards Identifying and Managing Sources of Uncertainty in AI and Machine Learning Models - An Overview
Authors Michael Kläs
Abstract Quantifying and managing uncertainties that occur when data-driven models such as those provided by AI and machine learning methods are applied is crucial. This whitepaper provides a brief motivation and first overview of the state of the art in identifying and quantifying sources of uncertainty for data-driven components as well as means for analyzing their impact.
Tasks
Published 2018-11-28
URL http://arxiv.org/abs/1811.11669v1
PDF http://arxiv.org/pdf/1811.11669v1.pdf
PWC https://paperswithcode.com/paper/towards-identifying-and-managing-sources-of
Repo
Framework

A generalized concept-cognitive learning: A machine learning viewpoint

Title A generalized concept-cognitive learning: A machine learning viewpoint
Authors Yunlong Mi, Yong Shi, Jinhai Li
Abstract Concept-cognitive learning (CCL) is a hot topic in recent years, and it has attracted much attention from the communities of formal concept analysis, granular computing and cognitive computing. However, the relationship among cognitive computing (CC), concept-cognitive computing (CCC), CCL and concept-cognitive learning model (CCLM) is not clearly described. To this end, we first explain the relationship of CC, CCC, CCL and CCLM. Then, we propose a generalized concept-cognitive learning (GCCL) from the point of view of machine learning. Finally, experiments on some data sets are conducted to verify the feasibility of concept formation and concept-cognitive process of GCCL.
Tasks
Published 2018-01-08
URL http://arxiv.org/abs/1801.02334v3
PDF http://arxiv.org/pdf/1801.02334v3.pdf
PWC https://paperswithcode.com/paper/a-generalized-concept-cognitive-learning-a
Repo
Framework

Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-convex Optimization

Title Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-convex Optimization
Authors Yiyang Wang, Risheng Liu, Long Ma, Xiaoliang Song
Abstract We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical algorithms, for optimizing univariate sub-problems with nice properties. From the other side, it also augments probabilities to receive desired results, by embedding advanced techniques in optimizations of realistic tasks. Integrating both numerical algorithms and advanced techniques together, TECU is proposed in a unified framework for solving a class of non-convex problems. Although the task embedded strategies bring inaccuracies in sub-problem optimizations, we provide a realizable criterion to control the errors, meanwhile, to ensure robust performances with rigid theoretical analyses. By respectively embedding ADMM and a residual-type CNN in our algorithm framework, the experimental results verify both efficiency and effectiveness of embedding task-oriented strategies in coordinate descent for solving practical problems.
Tasks
Published 2018-11-05
URL http://arxiv.org/abs/1811.01587v2
PDF http://arxiv.org/pdf/1811.01587v2.pdf
PWC https://paperswithcode.com/paper/task-embedded-coordinate-update-a-realizable
Repo
Framework

Design and Evaluation of a Tutor Platform for Personalized Vocabulary Learning

Title Design and Evaluation of a Tutor Platform for Personalized Vocabulary Learning
Authors Ravi Kokku, Aditya Vempaty, Tamer Abuelsaad, Prasenjit Dey, Tammy Humphrey, Akimi Gibson, Jennifer Kotler
Abstract This paper presents our experiences in designing, implementing, and piloting an intelligent vocabulary learning tutor. The design builds on several intelligent tutoring design concepts, including graph-based knowledge representation, learner modeling, and adaptive learning content and assessment exposition. Specifically, we design a novel phased learner model approach to enable systematic exposure to words during vocabulary instruction. We also built an example application over the tutor platform that uses a learning activity involving videos and an assessment activity involving word to picture/image association. More importantly, the tutor adapts to the significant variation in children’s knowledge at the beginning of kindergarten, and evolves the application at the speed of each individual learner. A pilot study with 180 kindergarten learners allowed the tutor to collect various kinds of activity information suitable for insights and interventions both at an individual- and class-level. The effort also demonstrates that we can do A/B testing for a variety of hypotheses at scale with such a framework.
Tasks
Published 2018-07-09
URL http://arxiv.org/abs/1807.03224v1
PDF http://arxiv.org/pdf/1807.03224v1.pdf
PWC https://paperswithcode.com/paper/design-and-evaluation-of-a-tutor-platform-for
Repo
Framework

Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations

Title Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations
Authors Koki Washio, Tsuneaki Kato
Abstract Recognizing lexical semantic relations between word pairs is an important task for many applications of natural language processing. One of the mainstream approaches to this task is to exploit the lexico-syntactic paths connecting two target words, which reflect the semantic relations of word pairs. However, this method requires that the considered words co-occur in a sentence. This requirement is hardly satisfied because of Zipf’s law, which states that most content words occur very rarely. In this paper, we propose novel methods with a neural model of $P(pathw_1, w_2)$ to solve this problem. Our proposed model of $P(pathw_1, w_2)$ can be learned in an unsupervised manner and can generalize the co-occurrences of word pairs and dependency paths. This model can be used to augment the path data of word pairs that do not co-occur in the corpus, and extract features capturing relational information from word pairs. Our experimental results demonstrate that our methods improve on previous neural approaches based on dependency paths and successfully solve the focused problem.
Tasks
Published 2018-09-10
URL http://arxiv.org/abs/1809.03411v1
PDF http://arxiv.org/pdf/1809.03411v1.pdf
PWC https://paperswithcode.com/paper/filling-missing-paths-modeling-co-occurrences
Repo
Framework

Anticipating cryptocurrency prices using machine learning

Title Anticipating cryptocurrency prices using machine learning
Authors Laura Alessandretti, Abeer ElBahrawy, Luca Maria Aiello, Andrea Baronchelli
Abstract Machine learning and AI-assisted trading have attracted growing interest for the past few years. Here, we use this approach to test the hypothesis that the inefficiency of the cryptocurrency market can be exploited to generate abnormal profits. We analyse daily data for $1,681$ cryptocurrencies for the period between Nov. 2015 and Apr. 2018. We show that simple trading strategies assisted by state-of-the-art machine learning algorithms outperform standard benchmarks. Our results show that nontrivial, but ultimately simple, algorithmic mechanisms can help anticipate the short-term evolution of the cryptocurrency market.
Tasks
Published 2018-05-22
URL http://arxiv.org/abs/1805.08550v4
PDF http://arxiv.org/pdf/1805.08550v4.pdf
PWC https://paperswithcode.com/paper/180508550
Repo
Framework

An LSTM Network for Highway Trajectory Prediction

Title An LSTM Network for Highway Trajectory Prediction
Authors Florent Altché, Arnaud de La Fortelle
Abstract In order to drive safely and efficiently on public roads, autonomous vehicles will have to understand the intentions of surrounding vehicles, and adapt their own behavior accordingly. If experienced human drivers are generally good at inferring other vehicles’ motion up to a few seconds in the future, most current Advanced Driving Assistance Systems (ADAS) are unable to perform such medium-term forecasts, and are usually limited to high-likelihood situations such as emergency braking. In this article, we present a first step towards consistent trajectory prediction by introducing a long short-term memory (LSTM) neural network, which is capable of accurately predicting future longitudinal and lateral trajectories for vehicles on highway. Unlike previous work focusing on a low number of trajectories collected from a few drivers, our network was trained and validated on the NGSIM US-101 dataset, which contains a total of 800 hours of recorded trajectories in various traffic densities, representing more than 6000 individual drivers.
Tasks Autonomous Vehicles, Trajectory Prediction
Published 2018-01-24
URL http://arxiv.org/abs/1801.07962v1
PDF http://arxiv.org/pdf/1801.07962v1.pdf
PWC https://paperswithcode.com/paper/an-lstm-network-for-highway-trajectory
Repo
Framework

Super-Efficient Spatially Adaptive Contrast Enhancement Algorithm for Superficial Vein Imaging

Title Super-Efficient Spatially Adaptive Contrast Enhancement Algorithm for Superficial Vein Imaging
Authors A. M. R. R. Bandara, K. A. S. H. Kulathilake, P. W. G. R. M. P. B. Giragama
Abstract This paper presents a super-efficient spatially adaptive contrast enhancement algorithm for enhancing infrared (IR) radiation based superficial vein images in real-time. The super-efficiency permits the algorithm to run in consumer-grade handheld devices, which ultimately reduces the cost of vein imaging equipment. The proposed method utilizes the response from the low-frequency range of the IR image signal to adjust the boundaries of the reference dynamic range in a linear contrast stretching process with a tunable contrast enhancement parameter, as opposed to traditional approaches which use costly adaptive histogram equalization based methods. The algorithm has been implemented and deployed in a consumer grade Android-based mobile device to evaluate the performance. The results revealed that the proposed algorithm can process IR images of veins in real-time on low-performance computers. It was compared with several well-performed traditional methods and the results revealed that the new algorithm stands out with several beneficial features, namely, the fastest processing, the ability to enhance the desired details, the excellent illumination normalization capability and the ability to enhance details where the traditional methods failed.
Tasks
Published 2018-02-28
URL http://arxiv.org/abs/1803.00039v1
PDF http://arxiv.org/pdf/1803.00039v1.pdf
PWC https://paperswithcode.com/paper/super-efficient-spatially-adaptive-contrast
Repo
Framework
comments powered by Disqus