As new applications of artificial intelligence continue to emerge, there is an increasing interest to explore how this type of technology can improve automated service interactions between the firm ...and its customers. This paper aims to develop a conceptual framework that details how firms and customers can enhance the outcomes of firm-solicited and firm-unsolicited online customer engagement behaviors through the use of information processing systems enabled by artificial intelligence. By building on the metaphor of artificial intelligence systems as organisms and taking a Stimulus-Organism-Response theory perspective, this paper identifies different types of firm-solicited and firm-unsolicited online customer engagement behaviors that act as stimuli for artificial intelligence organisms to process customer-related information resulting in both artificial intelligence and human responses which, in turn, shape the contexts of future online customer engagement behaviors.
Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent ...transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, up-sample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.
Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that ...involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked “What vehicle is the person riding?”, computers will need to identify the objects in an image as well as the relationships
riding(man, carriage)
and
pulling(horse, carriage)
to answer correctly that “the person is riding a horse-drawn carriage.” In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of
35
objects,
26
attributes, and
21
pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.
Timely and accurate delineation of global urban land is fundamental to the understanding of global environmental changes. However, most of the contemporary global urban land maps have coarse ...resolutions and are available for one or two years only. In this study, we developed the multi-temporal global urban land maps based on Landsat images for the 1990–2010 period with a five-year interval (‘Urban land’ in these maps refers to ‘impervious surface’, i.e., artificial cover and structures such as pavement, concrete, brick, stone and other man-made impenetrable cover types). We proposed the method of Normalized Urban Areas Composite Index (NUACI) and utilized the Google Earth Engine to facilitate the global urban land classifications from an extensive number of Landsat images. The global level's overall accuracy, producer's accuracy and user's accuracy for our mapping results are 0.81–0.84, 0.50–0.60 and 0.49–0.61, respectively. The Kappa values are 0.43–0.50 at the global level, and ~0.33 (in China) and ~0.42 (in the U.S.) at the country level. By analyzing the presented dataset, we found that the world's urban land area had increased from 450.97 ± 1.18 thousand km2 in 1990 to 747.05 ± 1.50 thousand km2 in 2010, reaching a global coverage of 0.63%. China, the United States and India together (14% of the world's terrestrial area in total) contributed almost 43% of the total increase of global urban land area. A free download link for these data is attached at the end of this paper.
•Multi-temporal global urban land maps at 30-m resolution are presented.•Google Earth Engine Platform is utilized for global urban land classifications.•The resulting global urban land has overall accuracy of 0.81–0.84.
Single image dehazing has been a challenging problem which aims to recover clear images from hazy ones. The performance of existing image dehazing methods is limited by hand-designed features and ...priors. In this paper, we propose a multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines dehazed results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. In addition, we propose a holistic edge guided network to refine edges of the estimated transmission map. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.
In this work we present an end-to-end system for text spotting—localising and recognising text in natural scene images—and text based image retrieval. This system is based on a region proposal ...mechanism for detection and deep convolutional neural networks for recognition. Our pipeline uses a novel combination of complementary proposal generation techniques to ensure high recall, and a fast subsequent filtering stage for improving precision. For the recognition and ranking of proposals, we train very large convolutional neural networks to perform word recognition on the whole proposal region at the same time, departing from the character classifier based systems of the past. These networks are trained solely on data produced by a synthetic text generation engine, requiring no human labelled data. Analysing the stages of our pipeline, we show state-of-the-art performance throughout. We perform rigorous experiments across a number of standard end-to-end text spotting benchmarks and text-based image retrieval datasets, showing a large improvement over all previous methods. Finally, we demonstrate a real-world application of our text spotting system to allow thousands of hours of news footage to be instantly searchable via a text query.
Portraiture is a major art form in both photography and painting. In most instances, artists seek to make the subject stand out from its surrounding, for instance, by making it brighter or sharper. ...In the digital world, similar effects can be achieved by processing a portrait image with photographic or painterly filters that adapt to the semantics of the image. While many successful user‐guided methods exist to delineate the subject, fully automatic techniques are lacking and yield unsatisfactory results. Our paper first addresses this problem by introducing a new automatic segmentation algorithm dedicated to portraits. We then build upon this result and describe several portrait filters that exploit our automatic segmentation algorithm to generate high‐quality portraits.