Goto

Collaborating Authors

 Country


Constructing Hierarchical Q&A Datasets for Video Story Understanding

arXiv.org Artificial Intelligence

Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for video understanding. While several previous studies have suggested datasets for video Q&A tasks, they did not really incorporate story-level understanding, resulting in highly-biased and lack of variance in degree of question difficulty. In this paper, we propose a hierarchical method for building Q&A datasets, i.e. hierarchical difficulty levels. We introduce three criteria for video story understanding, i.e. memory capacity, logical complexity, and DIKW (Data-Information-Knowledge-Wisdom) pyramid. We discuss how three-dimensional map constructed from these criteria can be used as a metric for evaluating the levels of intelligence relating to video story understanding.


Towards Ranking Geometric Automated Theorem Provers

arXiv.org Artificial Intelligence

The field of geometric automated theorem provers has a long and rich history, from the early AI approaches of the 1960s, synthetic provers, to today algebraic and synthetic provers. The geometry automated deduction area differs from other areas by the strong connection between the axiomatic theories and its standard models. In many cases the geometric constructions are used to establish the theorems' statements, geometric constructions are, in some provers, used to conduct the proof, used as counter-examples to close some branches of the automatic proof. Synthetic geometry proofs are done using geometric properties, proofs that can have a visual counterpart in the supporting geometric construction. With the growing use of geometry automatic deduction tools as applications in other areas, e.g. in education, the need to evaluate them, using different criteria, is felt. Establishing a ranking among geometric automated theorem provers will be useful for the improvement of the current methods/implementations. Improvements could concern wider scope, better efficiency, proof readability and proof reliability. To achieve the goal of being able to compare geometric automated theorem provers a common test bench is needed: a common language to describe the geometric problems; a comprehensive repository of geometric problems and a set of quality measures.


Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints

arXiv.org Artificial Intelligence

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level lateral decision-making and low-level rule-based trajectory modification, a safe and efficient lane change behavior can be achieved. With the setting of our state representation and reward function, the trained agent is able to take appropriate actions in a real-world-like simulator. The generated policy is evaluated on the simulator for 10 times, and the results demonstrate that the proposed rule-based DQN method outperforms the rule-based approach and the DQN method.


Alexas, stop fighting! This house is big enough for more than one voice assistant

USATODAY - Tech Top Stories

The Amazon Echo, Dot and other Alexa-enabled devices don't often play well together in the same house โ€“ particularly if they're within earshot of each other. That wasn't a problem because most of us had only one smart speaker โ€“ if we had any at all. Amazon says the number of households with more than one smart assistant-enabled device doubled last year. That lends credence to an independent survey taken late last year declaring that nearly 1 in 4 US households had a voice-enabled device inside โ€“ and about 40 percent of those have more than one. Which can only mean that more of us are experiencing the headaches of these early days in the Alexa multi-device experience.


In video game 'Destiny's Sword,' mental health is as important as combat strategy

USATODAY - Tech Top Stories

Promotional artwork for the upcoming video game, 'Destiny's Sword,' in which your characters' mental health are as important as their strengths and weaponry. Most combat video games stress tactics and firepower, but in the upcoming sci-fi strategy game "Destiny's Sword" you will also want to take into account your bedside manner. The online role-playing computer game from Ontario, Canada, studio 2Dogs Games puts players in the role of a squadron commander in a futuristic faction war. Scores of players can compete online โ€“ think "World of Warcraft" mashed up with the movie "Starship Troopers." But there's another unique twist: As you direct your troops, their experiences in combat will affect each character differently โ€“ that, in turn, influences their effectiveness in subsequent battles.


How the Brain Links Gestures, Perception, and Meaning

WIRED

Remember the last time someone flipped you the bird? Whether or not that single finger was accompanied by spoken obscenities, you knew exactly what it meant. The conversion from movement into meaning is both seamless and direct, because we are endowed with the capacity to speak without talking and comprehend without hearing. We can direct attention by pointing, enhance narrative by miming, emphasize with rhythmic strokes and convey entire responses with a simple combination of fingers. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences. The tendency to supplement communication with motion is universal, though the nuances of delivery vary slightly.


Inside a Ferrari Hypercar, Lyft's IPO, and More Car News

WIRED

Let the unicorn feast begin! Now the big question, which will answer itself in the weeks and months to come: How do investors feel about the prospect of the mustachioed company actually making money? Still, plenty of transportation interestings were happening off Wall Street this week. We took a look at the current state of automotive software safety standards, and talked to people wondering how self-driving cars might fit into the mix. We reminded ourselves that self-driving cars aren't going to be driverless for a while, and about the role of remote drivers in the ecosystem.


Deep Learning Market Insight: Globally Grow at a CAGR by Revenue during the Forecast Period 2019-2024 - Flatland Today

#artificialintelligence

Industry Research is an upscale platform to help key personnel in the business world in strategizing and taking visionary decisions based on facts and figures derived from in depth market research. We are one of the top report resellers in the market, dedicated towards bringing you an ingenious concoction of data parameters.


Developments in Quantum Computing - Connected World

#artificialintelligence

One of the hallmarks of this century will be the progress made toward a new paradigm in computing: quantum computing. A quantum computer has the potential to quickly and efficiently solve problems that conventional computers can't tackle by leveraging principles of quantum physics, such as superposition. While still in its early stages, the quantum computing market is already expanding, and there's much more growth expected in the years to come. This expected growth is thanks to the efforts of computing companies that see the benefits of a quantum future and want to capitalize on it. Tractica says the enterprise quantum computing market will reach $2.2 billion by 2025, up from $39.2 million in 2017.