July 29, 2019

2951 words 14 mins read

Paper Group ANR 38

From Bach to the Beatles: The simulation of human tonal expectation using ecologically-trained predictive models. Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication. Holistic, Instance-Level Human Parsing. A Non-monotone Alternating Updating Method for A Class of Matrix Factorization Problems. ToxTrac: a fas …

From Bach to the Beatles: The simulation of human tonal expectation using ecologically-trained predictive models


Title	From Bach to the Beatles: The simulation of human tonal expectation using ecologically-trained predictive models
Authors	Carlos Cancino-Chacón, Maarten Grachten, Kat Agres
Abstract	Tonal structure is in part conveyed by statistical regularities between musical events, and research has shown that computational models reflect tonal structure in music by capturing these regularities in schematic constructs like pitch histograms. Of the few studies that model the acquisition of perceptual learning from musical data, most have employed self-organizing models that learn a topology of static descriptions of musical contexts. Also, the stimuli used to train these models are often symbolic rather than acoustically faithful representations of musical material. In this work we investigate whether sequential predictive models of musical memory (specifically, recurrent neural networks), trained on audio from commercial CD recordings, induce tonal knowledge in a similar manner to listeners (as shown in behavioral studies in music perception). Our experiments indicate that various types of recurrent neural networks produce musical expectations that clearly convey tonal structure. Furthermore, the results imply that although implicit knowledge of tonal structure is a necessary condition for accurate musical expectation, the most accurate predictive models also use other cues beyond the tonal structure of the musical context.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06231v1
PDF	http://arxiv.org/pdf/1707.06231v1.pdf
PWC	https://paperswithcode.com/paper/from-bach-to-the-beatles-the-simulation-of
Repo
Framework

Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication


Title	Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication
Authors	Agniva Chowdhury, Jiasen Yang, Petros Drineas
Abstract	Projection-cost preservation is a low-rank approximation guarantee which ensures that the cost of any rank-$k$ projection can be preserved using a smaller sketch of the original data matrix. We present a general structural result outlining four sufficient conditions to achieve projection-cost preservation. These conditions can be satisfied using tools from the Randomized Linear Algebra literature.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10102v2
PDF	http://arxiv.org/pdf/1705.10102v2.pdf
PWC	https://paperswithcode.com/paper/structural-conditions-for-projection-cost
Repo
Framework

Holistic, Instance-Level Human Parsing


Title	Holistic, Instance-Level Human Parsing
Authors	Qizhu Li, Anurag Arnab, Philip H. S. Torr
Abstract	Object parsing – the task of decomposing an object into its semantic parts – has traditionally been formulated as a category-level segmentation problem. Consequently, when there are multiple objects in an image, current methods cannot count the number of objects in the scene, nor can they determine which part belongs to which object. We address this problem by segmenting the parts of objects at an instance-level, such that each pixel in the image is assigned a part label, as well as the identity of the object it belongs to. Moreover, we show how this approach benefits us in obtaining segmentations at coarser granularities as well. Our proposed network is trained end-to-end given detections, and begins with a category-level segmentation module. Thereafter, a differentiable Conditional Random Field, defined over a variable number of instances for every input image, reasons about the identity of each part by associating it with a human detection. In contrast to other approaches, our method can handle the varying number of people in each image and our holistic network produces state-of-the-art results in instance-level part and human segmentation, together with competitive results in category-level part segmentation, all achieved by a single forward-pass through our neural network.
Tasks	Human Detection, Human Parsing, Multi-Human Parsing
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03612v1
PDF	http://arxiv.org/pdf/1709.03612v1.pdf
PWC	https://paperswithcode.com/paper/holistic-instance-level-human-parsing
Repo
Framework

A Non-monotone Alternating Updating Method for A Class of Matrix Factorization Problems


Title	A Non-monotone Alternating Updating Method for A Class of Matrix Factorization Problems
Authors	Lei Yang, Ting Kei Pong, Xiaojun Chen
Abstract	In this paper we consider a general matrix factorization model which covers a large class of existing models with many applications in areas such as machine learning and imaging sciences. To solve this possibly nonconvex, nonsmooth and non-Lipschitz problem, we develop a non-monotone alternating updating method based on a potential function. Our method essentially updates two blocks of variables in turn by inexactly minimizing this potential function, and updates another auxiliary block of variables using an explicit formula. The special structure of our potential function allows us to take advantage of efficient computational strategies for non-negative matrix factorization to perform the alternating minimization over the two blocks of variables. A suitable line search criterion is also incorporated to improve the numerical performance. Under some mild conditions, we show that the line search criterion is well defined, and establish that the sequence generated is bounded and any cluster point of the sequence is a stationary point. Finally, we conduct some numerical experiments using real datasets to compare our method with some existing efficient methods for non-negative matrix factorization and matrix completion. The numerical results show that our method can outperform these methods for these specific applications.
Tasks	Matrix Completion
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06499v2
PDF	http://arxiv.org/pdf/1705.06499v2.pdf
PWC	https://paperswithcode.com/paper/a-non-monotone-alternating-updating-method
Repo
Framework

ToxTrac: a fast and robust software for tracking organisms


Title	ToxTrac: a fast and robust software for tracking organisms
Authors	Alvaro Rodriquez, Hanqing Zhang, Jonatan Klaminder, Tomas Brodin, Patrik L. Andersson, Magnus Andersson
Abstract	1. Behavioral analysis based on video recording is becoming increasingly popular within research fields such as; ecology, medicine, ecotoxicology, and toxicology. However, the programs available to analyze the data, which are; free of cost, user-friendly, versatile, robust, fast and provide reliable statistics for different organisms (invertebrates, vertebrates and mammals) are significantly limited. 2. We present an automated open-source executable software (ToxTrac) for image-based tracking that can simultaneously handle several organisms monitored in a laboratory environment. We compare the performance of ToxTrac with current accessible programs on the web. 3. The main advantages of ToxTrac are: i) no specific knowledge of the geometry of the tracked bodies is needed; ii) processing speed, ToxTrac can operate at a rate >25 frames per second in HD videos using modern desktop computers; iii) simultaneous tracking of multiple organisms in multiple arenas; iv) integrated distortion correction and camera calibration; v) robust against false positives; vi) preservation of individual identification if crossing occurs; vii) useful statistics and heat maps in real scale are exported in: image, text and excel formats. 4. ToxTrac can be used for high speed tracking of insects, fish, rodents or other species, and provides useful locomotor information. We suggest using ToxTrac for future studies of animal behavior independent of research area. Download ToxTrac here: https://toxtrac.sourceforge.io
Tasks	Calibration
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02577v1
PDF	http://arxiv.org/pdf/1706.02577v1.pdf
PWC	https://paperswithcode.com/paper/toxtrac-a-fast-and-robust-software-for
Repo
Framework

Particle Filter Re-detection for Visual Tracking via Correlation Filters


Title	Particle Filter Re-detection for Visual Tracking via Correlation Filters
Authors	Di Yuan, Donghao Li, Zhenyu He, Xinming Zhang
Abstract	Most of the correlation filter based tracking algorithms can achieve good performance and maintain fast computational speed. However, in some complicated tracking scenes, there is a fatal defect that causes the object to be located inaccurately. In order to address this problem, we propose a particle filter redetection based tracking approach for accurate object localization. During the tracking process, the kernelized correlation filter (KCF) based tracker locates the object by relying on the maximum response value of the response map; when the response map becomes ambiguous, the KCF tracking result becomes unreliable. Our method can provide more candidates by particle resampling to detect the object accordingly. Additionally, we give a new object scale evaluation mechanism, which merely considers the differences between the maximum response values in consecutive frames. Extensive experiments on OTB2013 and OTB2015 datasets demonstrate that the proposed tracker performs favorably in relation to the state-of-the-art methods.
Tasks	Object Localization, Visual Tracking
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10069v2
PDF	http://arxiv.org/pdf/1711.10069v2.pdf
PWC	https://paperswithcode.com/paper/particle-filter-re-detection-for-visual
Repo
Framework

Fine-grained Pattern Matching Over Streaming Time Series


Title	Fine-grained Pattern Matching Over Streaming Time Series
Authors	Rong Kang, Chen Wang, Peng Wang, Yuting Ding, Jianmin Wang
Abstract	Pattern matching of streaming time series with lower latency under limited computing resource comes to a critical problem, especially as the growth of Industry 4.0 and Industry Internet of Things. However, against traditional single pattern matching problem, a pattern may contain multiple segments representing different statistical properties or physical meanings for more precise and expressive matching in real world. Hence, we formulate a new problem, called “fine-grained pattern matching”, which allows users to specify varied granularities of matching deviation to different segments of a given pattern, and fuzzy regions for adaptive breakpoints determination between consecutive segments. In this paper, we propose a novel two-phase approach. In the pruning phase, we introduce Equal-Length Block (ELB) representation together with Block-Skipping Pruning (BSP) policy, which guarantees low cost feature calculation, effective pruning and no false dismissals. In the post-processing phase, a delta-function is proposed to enable us to conduct exact matching in linear complexity. Extensive experiments are conducted to evaluate on synthetic and real-world datasets, which illustrates that our algorithm outperforms the brute-force method and MSM, a multi-step filter mechanism over the multi-scaled representation.
Tasks	Time Series
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10088v3
PDF	http://arxiv.org/pdf/1710.10088v3.pdf
PWC	https://paperswithcode.com/paper/fine-grained-pattern-matching-over-streaming
Repo
Framework

Query-Efficient Black-box Adversarial Examples (superceded)


Title	Query-Efficient Black-box Adversarial Examples (superceded)
Authors	Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin
Abstract	Note that this paper is superceded by “Black-Box Adversarial Attacks with Limited Queries and Information.” Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods — substitute networks and coordinate-based finite-difference methods — are either unreliable or query-inefficient, making these methods impractical for certain problems. We introduce a new method for reliably generating adversarial examples under more restricted, practical black-box threat models. First, we apply natural evolution strategies to perform black-box attacks using two to three orders of magnitude fewer queries than previous methods. Second, we introduce a new algorithm to perform targeted adversarial attacks in the partial-information setting, where the attacker only has access to a limited number of target classes. Using these techniques, we successfully perform the first targeted adversarial attack against a commercially deployed machine learning system, the Google Cloud Vision API, in the partial information setting.
Tasks	Adversarial Attack
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07113v2
PDF	http://arxiv.org/pdf/1712.07113v2.pdf
PWC	https://paperswithcode.com/paper/query-efficient-black-box-adversarial
Repo
Framework

PSF field learning based on Optimal Transport Distances


Title	PSF field learning based on Optimal Transport Distances
Authors	F. M. Ngolè Mboula, J. -L. Starck
Abstract	Context: in astronomy, observing large fractions of the sky within a reasonable amount of time implies using large field-of-view (fov) optical instruments that typically have a spatially varying Point Spread Function (PSF). Depending on the scientific goals, galaxies images need to be corrected for the PSF whereas no direct measurement of the PSF is available. Aims: given a set of PSFs observed at random locations, we want to estimate the PSFs at galaxies locations for shapes measurements correction. Contributions: we propose an interpolation framework based on Sliced Optimal Transport. A non-linear dimension reduction is first performed based on local pairwise approximated Wasserstein distances. A low dimensional representation of the unknown PSFs is then estimated, which in turn is used to derive representations of those PSFs in the Wasserstein metric. Finally, the interpolated PSFs are calculated as approximated Wasserstein barycenters. Results: the proposed method was tested on simulated monochromatic PSFs of the Euclid space mission telescope (to be launched in 2020). It achieves a remarkable accuracy in terms of pixels values and shape compared to standard methods such as Inverse Distance Weighting or Radial Basis Function based interpolation methods.
Tasks	Dimensionality Reduction
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06066v1
PDF	http://arxiv.org/pdf/1703.06066v1.pdf
PWC	https://paperswithcode.com/paper/psf-field-learning-based-on-optimal-transport
Repo
Framework

Learning to Segment Moving Objects


Title	Learning to Segment Moving Objects
Authors	Pavel Tokmakov, Cordelia Schmid, Karteek Alahari
Abstract	We study the problem of segmenting moving objects in unconstrained videos. Given a video, the task is to segment all the objects that exhibit independent motion in at least one frame. We formulate this as a learning problem and design our framework with three cues: (i) independent object motion between a pair of frames, which complements object recognition, (ii) object appearance, which helps to correct errors in motion estimation, and (iii) temporal consistency, which imposes additional constraints on the segmentation. The framework is a two-stream neural network with an explicit memory module. The two streams encode appearance and motion cues in a video sequence respectively, while the memory module captures the evolution of objects over time, exploiting the temporal consistency. The motion stream is a convolutional neural network trained on synthetic videos to segment independently moving objects in the optical flow field. The module to build a ‘visual memory’ in video, i.e., a joint representation of all the video frames, is realized with a convolutional recurrent unit learned from a small number of training video sequences. For every pixel in a frame of a test video, our approach assigns an object or background label based on the learned spatio-temporal features as well as the ‘visual memory’ specific to the video. We evaluate our method extensively on three benchmarks, DAVIS, Freiburg-Berkeley motion segmentation dataset and SegTrack. In addition, we provide an extensive ablation study to investigate both the choice of the training data and the influence of each component in the proposed framework.
Tasks	Motion Estimation, Motion Segmentation, Object Recognition, Optical Flow Estimation
Published	2017-12-01
URL	http://arxiv.org/abs/1712.01127v1
PDF	http://arxiv.org/pdf/1712.01127v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-segment-moving-objects
Repo
Framework

Challenge of Multi-Camera Tracking


Title	Challenge of Multi-Camera Tracking
Authors	Yong Wang, Ke Lu
Abstract	Multi-camera tracking is quite different from single camera tracking, and it faces new technology and system architecture challenges. By analyzing the corresponding characteristics and disadvantages of the existing algorithms, problems in multi-camera tracking are summarized and some new directions for future work are also generalized.
Tasks
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01507v1
PDF	http://arxiv.org/pdf/1702.01507v1.pdf
PWC	https://paperswithcode.com/paper/challenge-of-multi-camera-tracking
Repo
Framework

A Random-Fern based Feature Approach for Image Matching


Title	A Random-Fern based Feature Approach for Image Matching
Authors	Yong Khoo, Seo-hyeon Keun
Abstract	Image or object recognition is an important task in computer vision. With the hight-speed processing power on modern platforms and the availability of mobile phones everywhere, millions of photos are uploaded to the internet per minute, it is critical to establish a generic framework for fast and accurate image processing for automatic recognition and information retrieval. In this paper, we proposed an efficient image recognition and matching method that is originally derived from Naive Bayesian classification method to construct a probabilistic model. Our method support real-time performance and have very high ability to distinguish similar images with high details. Experiments are conducted together with intensive comparison with state-of-the-arts on image matching, such as Ferns recognition and SIFT recognition. The results demonstrate satisfactory performance.
Tasks	Information Retrieval, Object Recognition
Published	2017-06-04
URL	http://arxiv.org/abs/1706.01115v1
PDF	http://arxiv.org/pdf/1706.01115v1.pdf
PWC	https://paperswithcode.com/paper/a-random-fern-based-feature-approach-for
Repo
Framework

CityPersons: A Diverse Dataset for Pedestrian Detection


Title	CityPersons: A Diverse Dataset for Pedestrian Detection
Authors	Shanshan Zhang, Rodrigo Benenson, Bernt Schiele
Abstract	Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.
Tasks	Pedestrian Detection
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05693v1
PDF	http://arxiv.org/pdf/1702.05693v1.pdf
PWC	https://paperswithcode.com/paper/citypersons-a-diverse-dataset-for-pedestrian
Repo
Framework

Content-based Approach for Vietnamese Spam SMS Filtering


Title	Content-based Approach for Vietnamese Spam SMS Filtering
Authors	Thai-Hoang Pham, Phuong Le-Hong
Abstract	Short Message Service (SMS) spam is a serious problem in Vietnam because of the availability of very cheap pre-paid SMS packages. There are some systems to detect and filter spam messages for English, most of which use machine learning techniques to analyze the content of messages and classify them. For Vietnamese, there is some research on spam email filtering but none focused on SMS. In this work, we propose the first system for filtering Vietnamese spam SMS. We first propose an appropriate preprocessing method since existing tools for Vietnamese preprocessing cannot give good accuracy on our dataset. We then experiment with vector representations and classifiers to find the best model for this problem. Our system achieves an accuracy of 94% when labelling spam messages while the misclassification rate of legitimate messages is relatively small, about only 0.4%. This is an encouraging result compared to that of English and can be served as a strong baseline for future development of Vietnamese SMS spam prevention systems.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04003v1
PDF	http://arxiv.org/pdf/1705.04003v1.pdf
PWC	https://paperswithcode.com/paper/content-based-approach-for-vietnamese-spam
Repo
Framework

Detecting hip fractures with radiologist-level performance using deep neural networks


Title	Detecting hip fractures with radiologist-level performance using deep neural networks
Authors	William Gale, Luke Oakden-Rayner, Gustavo Carneiro, Andrew P. Bradley, Lyle J. Palmer
Abstract	We developed an automated deep learning system to detect hip fractures from frontal pelvic x-rays, an important and common radiological task. Our system was trained on a decade of clinical x-rays (~53,000 studies) and can be applied to clinical data, automatically excluding inappropriate and technically unsatisfactory studies. We demonstrate diagnostic performance equivalent to a human radiologist and an area under the ROC curve of 0.994. Translated to clinical practice, such a system has the potential to increase the efficiency of diagnosis, reduce the need for expensive additional testing, expand access to expert level medical image interpretation, and improve overall patient outcomes.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06504v1
PDF	http://arxiv.org/pdf/1711.06504v1.pdf
PWC	https://paperswithcode.com/paper/detecting-hip-fractures-with-radiologist
Repo
Framework