Recently, self-supervised learning has proved to be effective to learn representations of events in image sequences, where events are understood as sets of temporally adjacent images that are semantically perceived as a whole. However, although this approach does not require expensive manual annotations, it is data hungry and suffers from domain adaptation problems. As an alternative, in this work, we propose a novel approach for learning event representations named Dynamic Graph Embedding (DGE). The assumption underlying our model is that a sequence of images can be represented by a graph that encodes both semantic and temporal similarity. The key novelty of DGE is to learn jointly the graph and its graph embedding. At its core, DGE works by iterating over two steps: 1) updating the graph representing the semantic and temporal structure of the data based on the current data representation, and 2) updating the data representation to take into account the current data graph structure. The main advantage of DGE over state-of-the-art self-supervised approaches is that it does not require any training set, but instead learns iteratively from the data itself a low-dimensional embedding that reflects their temporal and semantic structure. Experimental results on two benchmark datasets of real image sequences captured at regular intervals demonstrate that the proposed DGE leads to effective event representations. In particular, it achieves robust temporal segmentation on the EDUBSeg and EDUBSeg-Desc benchmark datasets, outperforming the state of the art.

Fake news is a well-documented problem. It's obvious that an AI-based technique is needed to counter that threat. AI-generated videos (also known as deepfakes) and images are easier to come up with than ever before. They can range from funny and quirky to much more sinister and dangerous, such as those of political statements that were never given, or shots of events that never took place. It's easy to see how such content published on social networks or by reputable media outlets could be used to manipulate public opinion.

Welcome to TechTalks' AI book reviews, a series of posts that explore the latest literature on AI. The media is rife with stories that warn of AI algorithms bringing people back from the dead, AI algorithms developing secret languages, mass technological unemployment, and a looming robot apocalypse. Movies and TV series like Her, The Circle and Westworld, which present a mystic portrayal of conscious machines and human-level AI being just around the corner. Rebooting AI is a refreshing read and a much-needed reality check on the current confusing state of artificial intelligence. Consider the following text, mentioned in Rebooting AI: "Elsie tried to reach her aunt on the phone, but she didn't answer." You don't need to be a genius to quickly make the following assumptions after reading this sentence: But even the most sophisticated AI algorithm would struggle to draw the same conclusions.

Add the magic of a voice assistant to your home. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. Believe me guys, you don't know what you're missing out on if you don't yet have a voice assistant in your life. For instance, with over 50,000 skills, Alexa can assist you in ways you didn't even know you needed, like helping you track your fitness goals, improve your sleeping habits, or even advance your child's learning.

Which children are most vulnerable when their nation imposes austerity programs?

A new California law will ban the creation and distribution of deepfake pornography produced without the consent of the person it depicts. Statutory damages range between $1,500 and $30,000, while cases in which malice can be demonstrated, damages rise to $150,000. The bill is part of a larger deepfake package that will also make it illegal to create and distribute deepfake videos of political figures within 60 days of an election. Katy Perry's face (pictured above) was swapped onto an adult film actress' body for a short video, something that the new California law will make illegal. Almost all deepfake videos are circulated online are pornographic, with one study suggesting the figure is 96 percent.

This summer, student interns at Booz Allen Hamilton bested the competition on edge computing with the help of NVIDIA Jetson Nano. The Booz Allen Summer Games Challenge (SGC) calls on student interns across the U.S. to develop breakthrough solutions for its clients' most pressing problems. This summer, Project RAZOR placed top 10 among artificial intelligence and machine learning projects with a fully autonomous ground vehicle powered by Nano. The team competed against 80 other teams of four to five students developing projects over 10 weeks. Previous SGC winning projects include technology that helps the blind navigate, as well as ways to fight human trafficking and global disease.

That said, I am really confused by OpenAI's PR strategy for GPT-2; they push it heavily as the future of text writing, but all of their GPT-2 related repos are archived w/o any updates expected.

Artificial intelligence could be destabilizing the internet news ecosystem. And according to billionaire Elon Musk, social media is the first to fall prey. Elon Musk tweeted early Thursday morning that "advanced AI" will be used to "manipulate social media" -- if, he opined, it hasn't done so already. He added that "anonymous bot swarms" are "evolving rapidly." It's unclear what exactly Musk was referring to when he warned about "advanced AI" and "anonymous bot swarms."