Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.

https://mmcheng.net/mftp/SalObj/PosterSaliency.pdf

Global contrast based salient region detection

The measurement of meaning

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a “colorization Turing test,” asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32 % of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

Colorful Image Colorization

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.

The electrostriction of elastomeric polymer dielectrics with compliant electrodes is potentially useful as a small-scale, solid-state actuator technology. Electrostrictive polymer (EP) materials are capable of efficient and fast response with high strains (> 30%), good actuation pressures (up to 1.9 MPa), and high specific energy densities (up to 0.1 J g−1). In this article, the mechanism of electrostriction is shown to be due to the electrostatic attraction of free charges on the electrodes. Although EP actuators are electrostatics based, they are shown to produce 5–20 times the effective actuation pressure of conventional air-gap electrostatics at the same electric field strength. The thin uniform dielectric films necessary for fabrication of EP actuators have been fabricated by techniques such as spin coating, casting, and dipping. A variety of materials and techniques have been used to produce the compliant electrodes, including lift-off stenciling techniques for powdered graphite, selective wetting of ionically conductive polymers, and spray coating of carbon blacks and fibrils in polymeric binders. Prototype actuators have been demonstrated in a variety of configurations such as stretched films, stacks, rolls, tubes, and unimorphs. Potential applications of the technology in areas such as microrobots, sound generators, and displays are discussed in this article.

Electrostriction of polymer dielectrics with compliant electrodes as a means of actuation

BACKGROUND: With the World Health Organization's pandemic declaration and government-initiated actions against coronavirus disease (COVID-19), sentiments surrounding COVID-19 have evolved rapidly. OBJECTIVE: This study aimed to examine worldwide trends of four emotions-fear, anger, sadness, and joy-and the narratives underlying those emotions during the COVID-19 pandemic. METHODS: Over 20 million social media twitter posts made during the early phases of the COVID-19 outbreak from January 28 to April 9, 2020, were collected using "wuhan," "corona," "nCov," and "covid" as search keywords. RESULTS: Public emotions shifted strongly from fear to anger over the course of the pandemic, while sadness and joy also surfaced. Findings from word clouds suggest that fears around shortages of COVID-19 tests and medical supplies became increasingly widespread discussion points. Anger shifted from xenophobia at the beginning of the pandemic to discourse around the stay-at-home notices. Sadness was highlighted by the topics of losing friends and family members, while topics related to joy included words of gratitude and good health. CONCLUSIONS: Overall, global COVID-19 sentiments have shown rapid evolutions within just the span of a few weeks. Findings suggest that emotion-driven collective issues around shared public distress experiences of the COVID-19 pandemic are developing and include large-scale social isolation and the loss of human lives. The steady rise of societal concerns indicated by negative emotions needs to be monitored and controlled by complementing regular crisis communication with strategic public health communication that aims to balance public psychological wellbeing.

/pdf/global-sentiments-surrounding-the-covid-19-pandemic-on-2y5dp3tmxh.pdf

Global Sentiments Surrounding the COVID-19 Pandemic on Twitter: Analysis of Twitter Trends.

Colorization of a grayscale photograph often requires considerable effort from the user, either by placing numerous color scribbles over the image to initialize a color propagation algorithm, or by looking for a suitable reference image from which color information can be transferred. Even with this user supplied data, colorized images may appear unnatural as a result of limited user skill or inaccurate transfer of colors. To address these problems, we propose a colorization system that leverages the rich image content on the internet. As input, the user needs only to provide a semantic text label and segmentation cues for major foreground objects in the scene. With this information, images are downloaded from photo sharing websites and filtered to obtain suitable reference images that are reliable for color transfer to the given grayscale photo. Different image colorizations are generated from the various reference images, and a graphical user interface is provided to easily select the desired result. Our experiments and user study demonstrate the greater effectiveness of this system in comparison to previous techniques.

Semantic colorization with internet images

We present a new example-based method to colorize a gray image. As input, the user needs only to supply a reference color image which is semantically similar to the target image. We extract features from these images at the resolution of superpixels, and exploit these features to guide the colorization process. Our use of a superpixel representation speeds up the colorization process. More importantly, it also empowers the colorizations to exhibit a much higher extent of spatial consistency in the colorization as compared to that using independent pixels. We adopt a fast cascade feature matching scheme to automatically find correspondences between superpixels of the reference and target images. Each correspondence is assigned a confidence based on the feature matching costs computed at different steps in the cascade, and high confidence correspondences are used to assign an initial set of chromatic values to the target superpixels. To further enforce the spatial coherence of these initial color assignments, we develop an image space voting framework which draws evidence from neighboring superpixels to identify and to correct invalid color assignments. Experimental results and user study on a broad range of images demonstrate that our method with a fixed set of parameters yields better colorization results as compared to existing methods.

Image colorization using similar images

The squeezed-film damping component of the pull-in time of an electrostatically-actuated micromechanical fixed-fixed beam is shown to be a sensitive, and nearly linear function of ambient air pressure in the measured range of 0.1 mbar to 1013 mbar (1 atm or 760 Torr). Pull-in time simulations, based on a one-dimensional macromodel using a damping constant proportional to pressure, are in good agreement with measured data. The data and simulations show that pull-in type devices will make excellent microelectromechanical systems (MEMS) sensors for broad-range absolute pressure measurements and for in situ leak monitoring of hermetically scaled packages containing other sensors or IC's. The pull-in sensors are compatible with any MEMS fabrication processes that allow out-of-plane electrostatic actuation, including surface micromachining and silicon wafer-bonding, and they do not require a cavity sealed at vacuum or at a reference air pressure.

Pull-in time dynamics as a measure of absolute pressure

When wet etches are used to release a large microstructural element, it is common practice to distribute small holes in the microstructure to promote under-etching and release, and for reduction of squeezed-film damping. In this paper, we demonstrate that while the mechanical properties are strongly affected by the presence of etch holes, because of fringing-field effects at the edges of the etched holes, the electrostatic-force behaviour of structural elements with an array of small etched holes is nearly that of an unetched element. This leads to an "effective medium" approximation for the mechanical material that can then be used with standard electrostatic actuation models to give good predictions of electromechanical behaviour. Comparison with experimental device behaviour shows the validity of this approach.

Raj Kumar Gupta

Papers

Global Sentiments Surrounding the COVID-19 Pandemic on Twitter: Analysis of Twitter Trends.

Semantic colorization with internet images

Image colorization using similar images

Pull-in time dynamics as a measure of absolute pressure

The effect of release-etch holes on the electromechanical behaviour of MEMS structures