July 27, 2019

2904 words 14 mins read

Paper Group ANR 706

PathTrack: Fast Trajectory Annotation with Path Supervision. Lower Bounds for Higher-Order Convex Optimization. Social Fingerprinting: detection of spambot groups through DNA-inspired behavioral modeling. Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds. Sampling-based speech parameter generation using moment-matching network …

PathTrack: Fast Trajectory Annotation with Path Supervision


Title	PathTrack: Fast Trajectory Annotation with Path Supervision
Authors	Santiago Manen, Michael Gygli, Dengxin Dai, Luc Van Gool
Abstract	Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our novel path supervision the annotator loosely follows the object with the cursor while watching the video, providing a path annotation for each object in the sequence. Our approach is able to turn such weak annotations into dense box trajectories. Our experiments on existing datasets prove that our framework produces more accurate annotations than the state of the art, in a fraction of the time. We further validate our approach by crowdsourcing the PathTrack dataset, with more than 15,000 person trajectories in 720 sequences. Tracking approaches can benefit training on such large-scale datasets, as did object recognition. We prove this by re-training an off-the-shelf person matching network, originally trained on the MOT15 dataset, almost halving the misclassification rate. Additionally, training on our data consistently improves tracking results, both on our dataset and on MOT15. On the latter, we improve the top-performing tracker (NOMT) dropping the number of IDSwitches by 18% and fragments by 5%.
Tasks	Multiple Object Tracking, Object Recognition, Object Tracking
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02437v2
PDF	http://arxiv.org/pdf/1703.02437v2.pdf
PWC	https://paperswithcode.com/paper/pathtrack-fast-trajectory-annotation-with
Repo
Framework

Lower Bounds for Higher-Order Convex Optimization


Title	Lower Bounds for Higher-Order Convex Optimization
Authors	Naman Agarwal, Elad Hazan
Abstract	State-of-the-art methods in convex and non-convex optimization employ higher-order derivative information, either implicitly or explicitly. We explore the limitations of higher-order optimization and prove that even for convex optimization, a polynomial dependence on the approximation guarantee and higher-order smoothness parameters is necessary. As a special case, we show Nesterov’s accelerated cubic regularization method to be nearly tight.
Tasks
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10329v1
PDF	http://arxiv.org/pdf/1710.10329v1.pdf
PWC	https://paperswithcode.com/paper/lower-bounds-for-higher-order-convex
Repo
Framework


Title	Social Fingerprinting: detection of spambot groups through DNA-inspired behavioral modeling
Authors	Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi, Angelo Spognardi, Maurizio Tesconi
Abstract	Spambot detection in online social networks is a long-lasting challenge involving the study and design of detection techniques capable of efficiently identifying ever-evolving spammers. Recently, a new wave of social spambots has emerged, with advanced human-like characteristics that allow them to go undetected even by current state-of-the-art algorithms. In this paper, we show that efficient spambots detection can be achieved via an in-depth analysis of their collective behaviors exploiting the digital DNA technique for modeling the behaviors of social network users. Inspired by its biological counterpart, in the digital DNA representation the behavioral lifetime of a digital account is encoded in a sequence of characters. Then, we define a similarity measure for such digital DNA sequences. We build upon digital DNA and the similarity between groups of users to characterize both genuine accounts and spambots. Leveraging such characterization, we design the Social Fingerprinting technique, which is able to discriminate among spambots and genuine accounts in both a supervised and an unsupervised fashion. We finally evaluate the effectiveness of Social Fingerprinting and we compare it with three state-of-the-art detection algorithms. Among the peculiarities of our approach is the possibility to apply off-the-shelf DNA analysis techniques to study online users behaviors and to efficiently rely on a limited number of lightweight account characteristics.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04482v1
PDF	http://arxiv.org/pdf/1703.04482v1.pdf
PWC	https://paperswithcode.com/paper/social-fingerprinting-detection-of-spambot
Repo
Framework

Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds


Title	Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds
Authors	Daniel R. Jiang, Lina Al-Kanj, Warren B. Powell
Abstract	Monte Carlo Tree Search (MCTS), most famously used in game-play artificial intelligence (e.g., the game of Go), is a well-known strategy for constructing approximate solutions to sequential decision problems. Its primary innovation is the use of a heuristic, known as a default policy, to obtain Monte Carlo estimates of downstream values for states in a decision tree. This information is used to iteratively expand the tree towards regions of states and actions that an optimal policy might visit. However, to guarantee convergence to the optimal action, MCTS requires the entire tree to be expanded asymptotically. In this paper, we propose a new technique called Primal-Dual MCTS that utilizes sampled information relaxation upper bounds on potential actions, creating the possibility of “ignoring” parts of the tree that stem from highly suboptimal choices. This allows us to prove that despite converging to a partial decision tree in the limit, the recommended action from Primal-Dual MCTS is optimal. The new approach shows significant promise when used to optimize the behavior of a single driver navigating a graph while operating on a ride-sharing platform. Numerical experiments on a real dataset of 7,000 trips in New Jersey suggest that Primal-Dual MCTS improves upon standard MCTS by producing deeper decision trees and exhibits a reduced sensitivity to the size of the action space.
Tasks	Game of Go
Published	2017-04-20
URL	http://arxiv.org/abs/1704.05963v1
PDF	http://arxiv.org/pdf/1704.05963v1.pdf
PWC	https://paperswithcode.com/paper/monte-carlo-tree-search-with-sampled
Repo
Framework

Sampling-based speech parameter generation using moment-matching networks


Title	Sampling-based speech parameter generation using moment-matching networks
Authors	Shinnosuke Takamichi, Tomoki Koriyama, Hiroshi Saruwatari
Abstract	This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis produces completely the same speech, i.e., there is no inter-utterance variation in synthetic speech. To give synthetic speech natural inter-utterance variation, this paper builds DNN acoustic models that make it possible to randomly sample speech parameters. The DNNs are trained so that they make the moments of generated speech parameters close to those of natural speech parameters. Since the variation of speech parameters is compressed into a low-dimensional simple prior noise vector, our algorithm has lower computation cost than direct sampling of speech parameters. As the first step towards generating synthetic speech that has natural inter-utterance variation, this paper investigates whether or not the proposed sampling-based generation deteriorates synthetic speech quality. In evaluation, we compare speech quality of conventional maximum likelihood-based generation and proposed sampling-based generation. The result demonstrates the proposed generation causes no degradation in speech quality.
Tasks	Speech Synthesis
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03626v1
PDF	http://arxiv.org/pdf/1704.03626v1.pdf
PWC	https://paperswithcode.com/paper/sampling-based-speech-parameter-generation
Repo
Framework


Title	Cross-modal Deep Metric Learning with Multi-task Regularization
Authors	Xin Huang, Yuxin Peng
Abstract	DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints between different modalities, and cannot take advantage of unlabeled data. This paper proposes Cross-modal Deep Metric Learning with Multi-task Regularization (CDMLMR), which integrates quadruplet ranking loss and semi-supervised contrastive loss for modeling cross-modal semantic similarity in a unified multi-task learning architecture. The quadruplet ranking loss can model the semantically similar and dissimilar constraints to preserve cross-modal relative similarity ranking information. The semi-supervised contrastive loss is able to maximize the semantic similarity on both labeled and unlabeled data. Compared to the existing methods, CDMLMR exploits not only the similarity ranking information but also unlabeled cross-modal data, and thus boosts cross-modal retrieval accuracy.
Tasks	Cross-Modal Retrieval, Metric Learning, Multi-Task Learning, Semantic Similarity, Semantic Textual Similarity
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07026v2
PDF	http://arxiv.org/pdf/1703.07026v2.pdf
PWC	https://paperswithcode.com/paper/cross-modal-deep-metric-learning-with-multi
Repo
Framework

A Multilayer-Based Framework for Online Background Subtraction with Freely Moving Cameras


Title	A Multilayer-Based Framework for Online Background Subtraction with Freely Moving Cameras
Authors	Yizhe Zhu, Ahmed Elgammal
Abstract	The exponentially increasing use of moving platforms for video capture introduces the urgent need to develop the general background subtraction algorithms with the capability to deal with the moving background. In this paper, we propose a multilayer-based framework for online background subtraction for videos captured by moving cameras. Unlike the previous treatments of the problem, the proposed method is not restricted to binary segmentation of background and foreground, but formulates it as a multi-label segmentation problem by modeling multiple foreground objects in different layers when they appear simultaneously in the scene. We assign an independent processing layer to each foreground object, as well as the background, where both motion and appearance models are estimated, and a probability map is inferred using a Bayesian filtering framework. Finally, Multi-label Graph-cut on Markov Random Field is employed to perform pixel-wise labeling. Extensive evaluation results show that the proposed method outperforms state-of-the-art methods on challenging video sequences.
Tasks
Published	2017-09-04
URL	http://arxiv.org/abs/1709.01140v1
PDF	http://arxiv.org/pdf/1709.01140v1.pdf
PWC	https://paperswithcode.com/paper/a-multilayer-based-framework-for-online
Repo
Framework

Scale-Regularized Filter Learning


Title	Scale-Regularized Filter Learning
Authors	Marco Loog, François Lauze
Abstract	We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step, acknowledging that such high-dimensional learning tasks typically benefit from some form of regularization and arguing that the problem of scale has not been taken care of in a very satisfactory manner, we come to a combined resolution of both of these shortcomings by proposing a form of scale regularization. Moreover, using variational method, this regularization problem can also be solved rather efficiently and we demonstrate, on an artificial filter learning problem, the capabilities of our basic linear neuron. From a more general standpoint, we see this work as prime example of how learning and variational methods could, or even should work to their mutual benefit.
Tasks
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02813v1
PDF	http://arxiv.org/pdf/1707.02813v1.pdf
PWC	https://paperswithcode.com/paper/scale-regularized-filter-learning
Repo
Framework

Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment


Title	Machine Learning Algorithms for $b$-Jet Tagging at the ATLAS Experiment
Authors	Michela Paganini
Abstract	The separation of $b$-quark initiated jets from those coming from lighter quark flavors ($b$-tagging) is a fundamental tool for the ATLAS physics program at the CERN Large Hadron Collider. The most powerful $b$-tagging algorithms combine information from low-level taggers, exploiting reconstructed track and vertex information, into machine learning classifiers. The potential of modern deep learning techniques is explored using simulated events, and compared to that achievable from more traditional classifiers such as boosted decision trees.
Tasks
Published	2017-11-23
URL	http://arxiv.org/abs/1711.08811v1
PDF	http://arxiv.org/pdf/1711.08811v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-algorithms-for-b-jet-tagging
Repo
Framework

Detecting English Writing Styles For Non Native Speakers


Title	Detecting English Writing Styles For Non Native Speakers
Authors	Yanging Chen, Rami Al-Rfou’, Yejin Choi
Abstract	This paper presents the first attempt, up to our knowledge, to classify English writing styles on this scale with the challenge of classifying day to day language written by writers with different backgrounds covering various areas of topics.The paper proposes simple machine learning algorithms and simple to generate features to solve hard problems. Relying on the scale of the data available from large sources of knowledge like Wikipedia. We believe such sources of data are crucial to generate robust solutions for the web with high accuracy and easy to deploy in practice. The paper achieves 74% accuracy classifying native versus non native speakers writing styles. Moreover, the paper shows some interesting observations on the similarity between different languages measured by the similarity of their users English writing styles. This technique could be used to show some well known facts about languages as in grouping them into families, which our experiments support.
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07441v1
PDF	http://arxiv.org/pdf/1704.07441v1.pdf
PWC	https://paperswithcode.com/paper/detecting-english-writing-styles-for-non
Repo
Framework

Learning non-maximum suppression


Title	Learning non-maximum suppression
Authors	Jan Hosang, Rodrigo Benenson, Bernt Schiele
Abstract	Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, and the classifier becoming one neural network improved results two-fold on general object detection. One indispensable component is non-maximum suppression (NMS), a post-processing algorithm responsible for merging all detections that belong to the same object. The de facto standard NMS algorithm is still fully hand-crafted, suspiciously simple, and – being based on greedy clustering with a fixed distance threshold – forces a trade-off between recall and precision. We propose a new network architecture designed to perform NMS, using only boxes and their score. We report experiments for person detection on PETS and for general object categories on the COCO dataset. Our approach shows promise providing improved localization and occlusion handling.
Tasks	Human Detection, Object Detection
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02950v2
PDF	http://arxiv.org/pdf/1705.02950v2.pdf
PWC	https://paperswithcode.com/paper/learning-non-maximum-suppression
Repo
Framework

Candidate sentence selection for language learning exercises: from a comprehensive framework to an empirical evaluation


Title	Candidate sentence selection for language learning exercises: from a comprehensive framework to an empirical evaluation
Authors	Ildikó Pilán, Elena Volodina, Lars Borin
Abstract	We present a framework and its implementation relying on Natural Language Processing methods, which aims at the identification of exercise item candidates from corpora. The hybrid system combining heuristics and machine learning methods includes a number of relevant selection criteria. We focus on two fundamental aspects: linguistic complexity and the dependence of the extracted sentences on their original context. Previous work on exercise generation addressed these two criteria only to a limited extent, and a refined overall candidate sentence selection framework appears also to be lacking. In addition to a detailed description of the system, we present the results of an empirical evaluation conducted with language teachers and learners which indicate the usefulness of the system for educational purposes. We have integrated our system into a freely available online learning platform.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03530v1
PDF	http://arxiv.org/pdf/1706.03530v1.pdf
PWC	https://paperswithcode.com/paper/candidate-sentence-selection-for-language
Repo
Framework

STNet: Selective Tuning of Convolutional Networks for Object Localization


Title	STNet: Selective Tuning of Convolutional Networks for Object Localization
Authors	Mahdi Biparva, John Tsotsos
Abstract	Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the inherent nature of feedback processing has remained computationally controversial. Inspired by the computational models of covert visual attention, we propose the Selective Tuning of Convolutional Networks (STNet). It is composed of both streams of Bottom-Up and Top-Down information processing to selectively tune the visual representation of Convolutional networks. We experimentally evaluate the performance of STNet for the weakly-supervised localization task on the ImageNet benchmark dataset. We demonstrate that STNet not only successfully surpasses the state-of-the-art results but also generates attention-driven class hypothesis maps.
Tasks	Object Localization
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06418v1
PDF	http://arxiv.org/pdf/1708.06418v1.pdf
PWC	https://paperswithcode.com/paper/stnet-selective-tuning-of-convolutional
Repo
Framework

Viewpoint Adaptation for Rigid Object Detection


Title	Viewpoint Adaptation for Rigid Object Detection
Authors	Patrick Wang, Kenneth Morton, Peter Torrione, Leslie Collins
Abstract	An object detector performs suboptimally when applied to image data taken from a viewpoint different from the one with which it was trained. In this paper, we present a viewpoint adaptation algorithm that allows a trained single-view object detector to be adapted to a new, distinct viewpoint. We first illustrate how a feature space transformation can be inferred from a known homography between the source and target viewpoints. Second, we show that a variety of trained classifiers can be modified to behave as if that transformation were applied to each testing instance. The proposed algorithm is evaluated on a person detection task using images from the PETS 2007 and CAVIAR datasets, as well as from a new synthetic multi-view person detection dataset. It yields substantial performance improvements when adapting single-view person detectors to new viewpoints, and simultaneously reduces computational complexity. This work has the potential to improve detection performance for cameras viewing objects from arbitrary viewpoints, while simplifying data collection and feature extraction.
Tasks	Human Detection, Object Detection
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07451v1
PDF	http://arxiv.org/pdf/1702.07451v1.pdf
PWC	https://paperswithcode.com/paper/viewpoint-adaptation-for-rigid-object
Repo
Framework

Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition


Title	Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition
Authors	Vincent Dorie, Jennifer Hill, Uri Shalit, Marc Scott, Dan Cervone
Abstract	Statisticians have made great progress in creating methods that reduce our reliance on parametric assumptions. However this explosion in research has resulted in a breadth of inferential strategies that both create opportunities for more reliable inference as well as complicate the choices that an applied researcher has to make and defend. Relatedly, researchers advocating for new methods typically compare their method to at best 2 or 3 other causal inference strategies and test using simulations that may or may not be designed to equally tease out flaws in all the competing methods. The causal inference data analysis challenge, “Is Your SATT Where It’s At?", launched as part of the 2016 Atlantic Causal Inference Conference, sought to make progress with respect to both of these issues. The researchers creating the data testing grounds were distinct from the researchers submitting methods whose efficacy would be evaluated. Results from 30 competitors across the two versions of the competition (black box algorithms and do-it-yourself analyses) are presented along with post-hoc analyses that reveal information about the characteristics of causal inference strategies and settings that affect performance. The most consistent conclusion was that methods that flexibly model the response surface perform better overall than methods that fail to do so. Finally new methods are proposed that combine features of several of the top-performing submitted methods.
Tasks	Causal Inference
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02641v5
PDF	http://arxiv.org/pdf/1707.02641v5.pdf
PWC	https://paperswithcode.com/paper/automated-versus-do-it-yourself-methods-for
Repo
Framework