recent bookmarks

Twitter
Top story: 10 new features for going Back to School with Microsoft Teams – Microsoft EDU , s…
from twitter_favs
10 days ago by rukku
10 new features for going Back to School with Microsoft Teams – Microsoft EDU
Top story: 10 new features for going Back to School with Microsoft Teams – Microsoft EDU , s…
from twitter_favs
10 days ago by rukku
Twitter
RT : Belay that thermometer, there's a chill in the air, almost as if the River Styx were about to ice over, for today i…
from twitter
10 days ago by mshook
(429) https://twitter.com/i/web/status/1026610629275267074
RT : Did you know that GM technology has improved pest and weed control, increasing crop yields. More production allows…
from twitter
10 days ago by RockyMountainNaturals
Twitter
RT : People do not realise that with os_log(), no logging is actually performed unless *observed* by a tool such as…
from twitter
10 days ago by jasongregori
Twitter
Right? I mean, between this and $40 million yachts being untied, the news is really hitting home these d…
from twitter
10 days ago by laze
Twitter
Favorite tweet:

Nostalgia will cripple you if you aren’t careful.
Don’t become fixated on things, people, and how life used to be simply for nostalgia’s sake. Don’t let memories stop you from growing.

— ERIK FINMAN (@erikfinman) August 7, 2018
IFTTT  Twitter 
10 days ago by ziliang
Twitter
RT : It's not that all religious people are predators. It's that predators will gravitate towards environments where mal…
from twitter
10 days ago by jasongregori
Twitter
When are the plea bargains due for the impending trials in South Carolina? What are the odds in your…
from twitter_favs
10 days ago by aheilbut
Twitter
Interesting dynamic in Nevada...to date, DraftKings has said it wanted to be in Nevada for DFS in some way other than existing law/regs, and never applied to do DFS in the state. Regulators were not big fans of that. Obv would like to do sports betting biz in the state. ªªhttps://twitter.com/DavidPurdum/status/1026610142719160322 …ºº

via Twitter Search / DustinGouker https://twitter.com/DustinGouker
LECTURAS  FEEDLY  SPORTalk 
10 days ago by leconeyc
Twitter
RT : You have to give the Mighty Mighty Bosstones credit, not only for being white guys playing ska, but for their hit s…
from twitter
10 days ago by quicksilvre
Lyft offers Avis rentals to drivers who don't own cars
Lyft offers Avis rentals to drivers who don't own cars https://ift.tt/2vMr6Aw Prospective https://ift.tt/2x8Nun8 August 7, 2018 at 02:15AM

Lyft drivers now have another major choice if they want to offer rides without buying their own cars. The ridesharing service has struck a deal that will have the Avis Budget Group offer "thousands" of vehicles through Lyft's Express Drive program in North America. There's no mention of the rates or terms of the deal, but the aim remains to make Lyft work feasible without the "cost and burden" of ownership. The cars should become available through the Lyft app in the next few months.

Without the financial info, it's not certain just how viable this is compared to buying your own ride. However, it's not really pitched as a long-term option. It's more for "on-demand access," including for people who may have given up their personal cars but don't want to rule Lyft as a source of income. It's more about flexibility (and filling Lyft's driver ranks) than courting full-time workers.

Source: Avis Budget Group

http://www.engadget.com Engadget https://ift.tt/1aOKVWi August 7, 2018 at 02:15AM
Prospective 
10 days ago by SergioWerner
Table of Contents - IEEE Journals & Magazine
Table of Contents https://ift.tt/2AIvoyC Prospective August 7, 2018 at 02:09AM https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Cover - IEEE Journals & Magazine
Cover https://ift.tt/2vlA8W2 Prospective August 7, 2018 at 02:09AM https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Twitter
Another hummingbird portrait from today....
from twitter_favs
10 days ago by madamjujujive
A Functional Regression Approach to Facial Landmark Tracking - IEEE Journals & Magazine
A Functional Regression Approach to Facial Landmark Tracking https://ift.tt/2AUnxOO Prospective August 7, 2018 at 02:09AM Linear regression is a fundamental building block in many face detection and tracking algorithms, typically used to predict shape displacements from image features through a linear mapping. This paper presents a Functional Regression solution to the least squares problem, which we coin Continuous Regression, resulting in the first real-time incremental face tracker. Contrary to prior work in Functional Regression, in which B-splines or Fourier series were used, we propose to approximate the input space by its first-order Taylor expansion, yielding a closed-form solution for the continuous domain of displacements. We then extend the continuous least squares problem to correlated variables, and demonstrate the generalisation of our approach. We incorporate Continuous Regression into the cascaded regression framework, and show its computational benefits for both training and testing. We then present a fast approach for incremental learning within Cascaded Continuous Regression, coined iCCR, and show that its complexity allows real-time face tracking, being 20 times faster than the state of the art. To the best of our knowledge, this is the first incremental face tracker that is shown to operate in real-time. We show that iCCR achieves state-of-the-art performance on the 300-VW dataset, the most recent, large-scale benchmark for face tracking. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object Labeling - IEEE Journals & Magazine
A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object Labeling https://ift.tt/2OO0IPq Prospective August 7, 2018 at 02:09AM While deep convolutional neural networks have shown a remarkable success in image classification, the problems of inter-class similarities, intra-class variances, the effective combination of multi-modal data, and the spatial variability in images of objects remain to be major challenges. To address these problems, this paper proposes a novel framework to learn a discriminative and spatially invariant classification model for object and indoor scene recognition using multi-modal RGB-D imagery. This is achieved through three postulates: 1) spatial invariance this is achieved by combining a spatial transformer network with a deep convolutional neural network to learn features which are invariant to spatial translations, rotations, and scale changes, 2) high discriminative capabilitythis is achieved by introducing Fisher encoding within the CNN architecture to learn features which have small inter-class similarities and large intra-class compactness, and 3) multi-modal hierarchical fusionthis is achieved through the regularization of semantic segmentation to a multi-modal CNN architecture, where class probabilities are estimated at different hierarchical levels (i.e., image- and pixel-levels), and fused into a Conditional Random Field (CRF)-based inference hypothesis, the optimization of which produces consistent class labels in RGB-D images. Extensive experimental evaluations on RGB-D object and scene datasets, and live video streams (acquired from Kinect) show that our framework produces superior object an- scene classification results compared to the state-of-the-art methods. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications - IEEE Journals & Magazine
Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications https://ift.tt/2ANrXXv Prospective August 7, 2018 at 02:09AM The heavy-tailed distributions of corrupted outliers and singular values of all channels in low-level vision have proven effective priors for many applications such as background modeling, photometric stereo and image alignment. And they can be well modeled by a hyper-Laplacian. However, the use of such distributions generally leads to challenging non-convex, non-smooth and non-Lipschitz problems, and makes existing algorithms very slow for large-scale applications. Together with the analytic solutions to -norm minimization with two specific values of , i.e., and , we propose two novel bilinear factor matrix norm minimization models for robust principal component analysis. We first define the double nuclear norm and Frobenius/nuclear hybrid norm penalties, and then prove that they are in essence the Schatten- and quasi-norms, respectively, which lead to much more tractable and scalable Lipschitz optimization problems. Our experimental analysis shows that both our methods yield more accurate solutions than original Sch- tten quasi-norm minimization, even when the number of observations is very limited. Finally, we apply our penalties to various low-level vision problems, e.g., text removal, moving object detection, image alignment and inpainting, and show that our methods usually outperform the state-of-the-art methods. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Colour Constancy Beyond the Classical Receptive Field - IEEE Journals & Magazine
Colour Constancy Beyond the Classical Receptive Field https://ift.tt/2volBc7 Prospective August 7, 2018 at 02:09AM The problem of removing illuminant variations to preserve the colours of objects (colour constancy) has already been solved by the human brain using mechanisms that rely largely on centre-surround computations of local contrast. In this paper we adopt some of these biological solutions described by long known physiological findings into a simple, fully automatic, functional model (termed Adaptive Surround Modulation or ASM). In ASM, the size of a visual neuron's receptive field (RF) as well as the relationship with its surround varies according to the local contrast within the stimulus, which in turn determines the nature of the centre-surround normalisation of cortical neurons higher up in the processing chain. We modelled colour constancy by means of two overlapping asymmetric Gaussian kernels whose sizes are adapted based on the contrast of the surround pixels, resembling the change of RF size. We simulated the contrast-dependent surround modulation by weighting the contribution of each Gaussian according to the centre-surround contrast. In the end, we obtained an estimation of the illuminant from the set of the most activated RFs’ outputs. Our results on three single-illuminant and one multi-illuminant benchmark datasets show that ASM is highly competitive against the state-of-the-art and it even outperforms learning-based algorithms in one case. Moreover, the robustness of our model is more tangible if we consider that our results were obtained using the same parameters for all datasets, that is, mimicking how the human visual system operates. These results suggest a dynamical adaptation mechanisms contribute to achieving higher accuracy in computational colour constancy. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Twitter
The sky tonight in Summerville is gorgeous
chswx  from twitter_favs
10 days ago by mcg
Coresets for Triangulation - IEEE Journals & Magazine
Coresets for Triangulation https://ift.tt/2AJWJAH Prospective August 7, 2018 at 02:09AM Multiple-view triangulation by minimisation has become established in computer vision. State-of-the-art triangulation algorithms exploit the quasiconvexity of the cost function to derive iterative update rules that deliver the global minimum. Such algorithms, however, can be computationally costly for large problem instances that contain many image measurements, e.g., from web-based photo sharing sites or long-term video recordings. In this paper, we prove that triangulation admits a coreset approximation scheme, which seeks small representative subsets of the input data called coresets. A coreset possesses the special property that the error of the solution on the coreset is within known bounds from the global minimum. We establish the necessary mathematical underpinnings of the coreset algorithm, specifically, by enacting the stopping criterion of the algorithm and proving that the resulting coreset gives the desired approximation accuracy. On large-scale triangulation problems, our method provides theoretically sound approximate solutions. Iterated until convergence, our coreset algorithm is also guaranteed to reach the true optimum. On practical datasets, we show that our technique can in fact attain the global minimiser much faster than current methods. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Twitter
This article describes, from the user side, what we’ve been seeing in our log data for years: accounts that mass-tw…
from twitter_favs
10 days ago by mathewi
Twitter
This article describes, from the user side, what we’ve been seeing in our log data for years: accounts that mass-tw…
from twitter_favs
10 days ago by andriak
Crafting GBD-Net for Object Detection - IEEE Journals & Magazine
Crafting GBD-Net for Object Detection https://ift.tt/2OS5OKK Prospective August 7, 2018 at 02:09AM The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a fundamental problem in object detection. In this paper, we propose a gated bi-directional CNN (GBD-Net) to pass messages among features from different support regions during both feature learning and feature extraction. Such message passing can be implemented through convolution between neighboring support regions in two directions and can be conducted in various layers. Therefore, local and contextual visual patterns can validate the existence of each other by learning their nonlinear relationships and their close interactions are modeled in a more complex way. It is also shown that message passing is not always helpful but dependent on individual samples. Gated functions are therefore needed to control message transmission, whose on-or-offs are controlled by extra visual evidence from the input sample. The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO. Besides the GBD-Net, this paper also shows the details of our approach in winning the ImageNet object detection challenge of 2016, with source code provided on . In this winning system, the modified GBD-Net, new pretraining scheme and better region proposal designs are provided. We also show the effectiveness of different network structures and existing techniques for object detection, such as multi-scale testing, left-right flip, bounding box voting, NMS, and context. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Fixed Points of Belief Propagation—An Analysis via Polynomial Homotopy Continuation - IEEE Journals & Magazine
Fixed Points of Belief Propagation—An Analysis via Polynomial Homotopy Continuation https://ift.tt/2AIviHg Prospective August 7, 2018 at 02:09AM Belief propagation (BP) is an iterative method to perform approximate inference on arbitrary graphical models. Whether BP converges and if the solution is a unique fixed point depends on both the structure and the parametrization of the model. To understand this dependence it is interesting to find all fixed points. In this work, we formulate a set of polynomial equations, the solutions of which correspond to BP fixed points. To solve such a nonlinear system we present the numerical polynomial-homotopy-continuation (NPHC) method. Experiments on binary Ising models and on error-correcting codes show how our method is capable of obtaining all BP fixed points. On Ising models with fixed parameters we show how the structure influences both the number of fixed points and the convergence properties. We further asses the accuracy of the marginals and weighted combinations thereof. Weighting marginals with their respective partition function increases the accuracy in all experiments. Contrary to the conjecture that uniqueness of BP fixed points implies convergence, we find graphs for which BP fails to converge, even though a unique fixed point exists. Moreover, we show that this fixed point gives a good approximation, and the NPHC method is able to obtain this fixed point. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation - IEEE Journals & Magazine
Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation https://ift.tt/2OL3mp4 Prospective August 7, 2018 at 02:09AM This paper addresses the problem of simultaneously recovering 3D shape, pose and the elastic model of a deformable object from only 2D point tracks in a monocular video. This is a severely under-constrained problem that has been typically addressed by enforcing the shape or the point trajectories to lie on low-rank dimensional spaces. We show that formulating the problem in terms of a low-rank force space that induces the deformation and introducing the elastic model as an additional unknown, allows for a better physical interpretation of the resulting priors and a more accurate representation of the actual object’s behavior. In order to simultaneously estimate force, pose, and the elastic model of the object we use an expectation maximization strategy, where each of these parameters are successively learned by partial M-steps. Once the elastic model is learned, it can be transfered to similar objects to code its 3D deformation. Moreover, our approach can robustly deal with missing data, and encode both rigid and non-rigid points under the same formalism. We thoroughly validate the approach on Mocap and real sequences, showing more accurate 3D reconstructions than state-of-the-art, and additionally providing an estimate of the full elastic model with no a priori information. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Hierarchical Sparse Representation for Robust Image Registration - IEEE Journals & Magazine
Hierarchical Sparse Representation for Robust Image Registration https://ift.tt/2AUnpyO Prospective August 7, 2018 at 02:09AM Similarity measure is an essential component in image registration. In this article, we propose a novel similarity measure for registration of two or more images. The proposed method is motivated by the fact that optimally registered images can be sparsified hierarchically in the gradient domain and frequency domain with the separation of sparse errors. One of the key advantages of the proposed similarity measure is its robustness in dealing with severe intensity distortions, which widely exist on medical images, remotely sensed images and natural photos due to differences of acquisition modalities or illumination conditions. Two efficient algorithms are proposed to solve the batch image registration and pair registration problems in a unified framework. We have validated our method on extensive and challenging data sets. The experimental results demonstrate the robustness, accuracy and efficiency of our method over nine traditional and state-of-the-art algorithms on synthetic images and a wide range of real-world applications. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Highly Articulated Kinematic Structure Estimation Combining Motion and Skeleton Information - IEEE Journals & Magazine
Highly Articulated Kinematic Structure Estimation Combining Motion and Skeleton Information https://ift.tt/2vrySAs Prospective August 7, 2018 at 02:09AM In this paper, we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view 2D image sequence. In contrast to prior motion-based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology via a successive iterative merging strategy. The iterative merge process is guided by a density weighted skeleton map which is generated from a novel object boundary generation method from sparse 2D feature points. Our main contributions can be summarised as follows: (i) An unsupervised complex articulated kinematic structure estimation method that combines motion segments with skeleton information. (ii) An iterative fine-to-coarse merging strategy for adaptive motion segmentation and structural topology embedding. (iii) A skeleton estimation method based on a novel silhouette boundary generation from sparse feature points using an adaptive model selection method. (iv) A new highly articulated object dataset with ground truth annotation. We have verified the effectiveness of our proposed method in terms of computational time and estimation accuracy through rigorous experiments with multiple datasets. Our experiments show that the proposed method outperforms state-of-the-art methods both quantitatively and qualitatively. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
xkcd: Disaster Movie
via Starred items from BazQux Reader https://ift.tt/1cAKc9M and IFTTT
Starred  items  from  BazQux  Reader 
10 days ago by stinkingpig
Image Visual Realism: From Human Perception to Machine Computation - IEEE Journals & Magazine
Image Visual Realism: From Human Perception to Machine Computation https://ift.tt/2ANrWCV Prospective August 7, 2018 at 02:09AM Visual realism is defined as the extent to which an image appears to people as a photo rather than computer generated. Assessing visual realism is important in applications like computer graphics rendering and photo retouching. However, current realism evaluation approaches use either labor-intensive human judgments or automated algorithms largely dependent on comparing renderings to reference images. We develop a reference-free computational framework for visual realism prediction to overcome these constraints. First, we construct a benchmark dataset of 2,520 images with comprehensive human annotated attributes. From statistical modeling on this data, we identify image attributes most relevant for visual realism. We propose both empirically-based (guided by our statistical modeling of human data) and deep convolutional neural network models to predict visual realism of images. Our framework has the following advantages: (1) it creates an interpretable and concise empirical model that characterizes human perception of visual realism; (2) it links computational features to latent factors of human image perception. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Learning from Narrated Instruction Videos - IEEE Journals & Magazine
Learning from Narrated Instruction Videos https://ift.tt/2vll22M Prospective August 7, 2018 at 02:09AM Automatic assistants could guide a person or a robot in performing new tasks, such as changing a car tire or repotting a plant. Creating such assistants, however, is non-trivial and requires understanding of visual and verbal content of a video. Towards this goal, we here address the problem of automatically learning the main steps of a task from a set of narrated instruction videos. We develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method sequentially clusters textual and visual representations of a task, where the two clustering problems are linked by joint constraints to obtain a single coherent sequence of steps in both modalities. To evaluate our method, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains videos for five different tasks with complex interactions between people and objects, captured in a variety of indoor and outdoor settings. We experimentally demonstrate that the proposed method can automatically discover, learn and localize the main steps of a task in input videos. https://ift.tt/HcLYSE IEEE Transactions on Pattern Analysis and Machine Intelligence https://ift.tt/2E37M93 August 7, 2018 at 02:09AM
Prospective 
10 days ago by SergioWerner
Twitter
Leftism is for everyone! And also I think it‘s important that folks are honest with themselves and community about…
from twitter_favs
10 days ago by justincharles
« earlier      later »

Copy this bookmark:



description:


tags:



Copy this bookmark:



description:


tags: