Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userVideo Pandemics: Worldwide Viral Spreading of Psys Gangnam Style Video
48
0
0.0
(
0
)
Added by
Gabor Vattay
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Viral videos can reach global penetration traveling through international channels of communication similarly to real diseases starting from a well-localized source. In past centuries, disease fronts propagated in a concentric spatial fashion from the the source of the outbreak via the short range human contact network. The emergence of long-distance air-travel changed these ancient patterns. However, recently, Brockmann and Helbing have shown that concentric propagation waves can be reinstated if propagation time and distance is measured in the flight-time and travel volume weighted underlying air-travel network. Here, we adopt this method for the analysis of viral meme propagation in Twitter messages, and define a similar weighted network distance in the communication network connecting countries and states of the World. We recover a wave-like behavior on average and assess the randomizing effect of non-locality of spreading. We show that similar result can be recovered from Google Trends data as well.
rate research
Read More
We model the spreading of a crisis by constructing a global economic network and applying the Susceptible-Infected-Recovered (SIR) epidemic model with a variable probability of infection. The probability of infection depends on the strength of economic relations between the pair of countries, and the strength of the target country. It is expected that a crisis which originates in a large country, such as the USA, has the potential to spread globally, like the recent crisis. Surprisingly we show that also countries with much lower GDP, such as Belgium, are able to initiate a global crisis. Using the {it k}-shell decomposition method to quantify the spreading power (of a node), we obtain a measure of ``centrality as a spreader of each country in the economic network. We thus rank the different countries according to the shell they belong to, and find the 12 most central countries. These countries are the most likely to spread a crisis globally. Of these 12 only six are large economies, while the other six are medium/small ones, a result that could not have been otherwise anticipated. Furthermore, we use our model to predict the crisis spreading potential of countries belonging to different shells according to the crisis magnitude.
We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism. Local regions may be selected either fully automatically from an image, through using video segmentation algorithms, or from casual user guidance such as scribbles. Our method, based on a deep neural network architecture inspired by recent work in photorealistic style transfer, is real-time and works on arbitrary inputs without runtime optimization once trained on a diverse dataset of artistic styles. By augmenting our video dataset with noisy semantic labels and jointly optimizing over style, content, mask, and temporal losses, our method can cope with a variety of imperfections in the input and produce temporally coherent videos without visual artifacts. We demonstrate our method on a variety of style images and target videos, including the ability to transfer different styles onto multiple objects simultaneously, and smoothly transition between styles in time.
Video style transfer is getting more attention in AI community for its numerous applications such as augmented reality and animation productions. Compared with traditional image style transfer, performing this task on video presents new challenges: how to effectively generate satisfactory stylized results for any specified style, and maintain temporal coherence across frames at the same time. Towards this end, we propose Multi-Channel Correction network (MCCNet), which can be trained to fuse the exemplar style features and input content features for efficient style transfer while naturally maintaining the coherence of input videos. Specifically, MCCNet works directly on the feature space of style and content domain where it learns to rearrange and fuse style features based on their similarity with content features. The outputs generated by MCC are features containing the desired style patterns which can further be decoded into images with vivid style textures. Moreover, MCCNet is also designed to explicitly align the features to input which ensures the output maintains the content structures as well as the temporal continuity. To further improve the performance of MCCNet under complex light conditions, we also introduce the illumination loss during training. Qualitative and quantitative evaluations demonstrate that MCCNet performs well in both arbitrary video and image style transfer tasks.
Video popularity is an essential reference for optimizing resource allocation and video recommendation in online video services. However, there is still no convincing model that can accurately depict a videos popularity evolution. In this paper, we propose a dynamic popularity model by modeling the video information diffusion process driven by various forms of recommendation. Through fitting the model with real traces collected from a practical system, we can quantify the strengths of the recommendation forces. Such quantification can lead to characterizing video popularity patterns, user behaviors and recommendation strategies, which is illustrated by a case study of TV episodes.
Detecting groups of people who are jointly deceptive in video conversations is crucial in settings such as meetings, sales pitches, and negotiations. Past work on deception in videos focuses on detecting a single deceiver and uses facial or visual features only. In this paper, we propose the concept of Face-to-Face Dynamic Interaction Networks (FFDINs) to model the interpersonal interactions within a group of people. The use of FFDINs enables us to leverage network relations in detecting group deception in video conversations for the first time. We use a dataset of 185 videos from a deception-based game called Resistance. We first characterize the behavior of individual, pairs, and groups of deceptive participants and compare them to non-deceptive participants. Our analysis reveals that pairs of deceivers tend to avoid mutual interaction and focus their attention on non-deceivers. In contrast, non-deceivers interact with everyone equally. We propose Negative Dynamic Interaction Networks to capture the notion of missing interactions. We create the DeceptionRank algorithm to detect deceivers from NDINs extracted from videos that are just one minute long. We show that our method outperforms recent state-of-the-art computer vision, graph embedding, and ensemble methods by at least 20.9% AUROC in identifying deception from videos.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
