Archives for 2019

Today I read a paper titled “Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations”

The abstract is:
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) in order 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 100K images where each image has an average of 21 objects, 18 attributes, and 18 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 answers.

Today I read a paper titled “Procedural urban environments for FPS games”

The abstract is:
This paper presents a novel approach to procedural generation of urban maps for First Person Shooter (FPS) games.

A multi-agent evolutionary system is employed to place streets, buildings and other items inside the Unity3D game engine, resulting in playable video game levels.

A computational agent is trained using machine learning techniques to capture the intent of the game designer as part of the multi-agent system, and to enable a semi-automated aesthetic selection for the underlying genetic algorithm.

Today I read a paper titled “Wayfinding and cognitive maps for pedestrian models”

The abstract is:
Usually, routing models in pedestrian dynamics assume that agents have fulfilled and global knowledge about the building’s structure.

However, they neglect the fact that pedestrians possess no or only parts of information about their position relative to final exits and possible routes leading to them.

To get a more realistic description we introduce the systematics of gathering and using spatial knowledge.

A new wayfinding model for pedestrian dynamics is proposed.

The model defines for every pedestrian an individual knowledge representation implying inaccuracies and uncertainties.

In addition, knowledge-driven search strategies are introduced.

The presented concept is tested on a fictive example scenario.

Today I read a paper titled “Live-action Virtual Reality Games”

The abstract is:
This paper proposes the concept of “live-action virtual reality games” as a new genre of digital games based on an innovative combination of live-action, mixed-reality, context-awareness, and interaction paradigms that comprise tangible objects, context-aware input devices, and embedded/embodied interactions.

Live-action virtual reality games are “live-action games” because a player physically acts out (using his/her real body and senses) his/her “avatar” (his/her virtual representation) in the game stage, which is the mixed-reality environment where the game happens.

The game stage is a kind of “augmented virtuality”; a mixed-reality where the virtual world is augmented with real-world information.

In live-action virtual reality games, players wear HMD devices and see a virtual world that is constructed using the physical world architecture as the basic geometry and context information.

Physical objects that reside in the physical world are also mapped to virtual elements.

Live-action virtual reality games keeps the virtual and real-worlds superimposed, requiring players to physically move in the environment and to use different interaction paradigms (such as tangible and embodied interaction) to complete game activities.

This setup enables the players to touch physical architectural elements (such as walls) and other objects, “feeling” the game stage.

Players have free movement and may interact with physical objects placed in the game stage, implicitly and explicitly.

Live-action virtual reality games differ from similar game concepts because they sense and use contextual information to create unpredictable game experiences, giving rise to emergent gameplay.

Today I read a paper titled “Micro-interventions in urban transport from pattern discovery on the flow of passengers and on the bus network”

The abstract is:
In this paper, we describe a case study in a big metropolis, in which from data collected by digital sensors, we tried to understand mobility patterns of persons using buses and how this can generate knowledge to suggest interventions that are applied incrementally into the transportation network in use.

We have first estimated an Origin-Destination matrix of buses users from datasets about the ticket validation and GPS positioning of buses.

Then we represent the supply of buses with their routes through bus stops as a complex network, which allowed us to understand the bottlenecks of the current scenario and, in particular, applying community discovery techniques, to identify clusters that the service supply infrastructure has.

Finally, from the superimposing of the flow of people represented in the OriginDestination matrix in the supply network, we exemplify how micro-interventions can be prospected by means of an example of the introduction of express routes.

Today I read a paper titled “Learning to Blend Computer Game Levels”

The abstract is:
We present an approach to generate novel computer game levels that blend different game concepts in an unsupervised fashion.

Our primary contribution is an analogical reasoning process to construct blends between level design models learned from gameplay videos.

The models represent probabilistic relationships between elements in the game.

An analogical reasoning process maps features between two models to produce blended models that can then generate new level chunks.

As a proof-of-concept we train our system on the classic platformer game Super Mario Bros.

due to its highly-regarded and well understood level design.

We evaluate the extent to which the models represent stylistic level design knowledge and demonstrate the ability of our system to explain levels that were blended by human expert designers.

Today I read a paper titled “A Review of Theoretical and Practical Challenges of Trusted Autonomy in Big Data”

The abstract is:
Despite the advances made in artificial intelligence, software agents, and robotics, there is little we see today that we can truly call a fully autonomous system.

We conjecture that the main inhibitor for advancing autonomy is lack of trust.

Trusted autonomy is the scientific and engineering field to establish the foundations and ground work for developing trusted autonomous systems (robotics and software agents) that can be used in our daily life, and can be integrated with humans seamlessly, naturally and efficiently.

In this paper, we review this literature to reveal opportunities for researchers and practitioners to work on topics that can create a leap forward in advancing the field of trusted autonomy.

We focus the paper on the `trust’ component as the uniting technology between humans and machines.

Our inquiry into this topic revolves around three sub-topics: (1) reviewing and positioning the trust modelling literature for the purpose of trusted autonomy; (2) reviewing a critical subset of sensor technologies that allow a machine to sense human states; and (3) distilling some critical questions for advancing the field of trusted autonomy.

The inquiry is augmented with conceptual models that we propose along the way by recompiling and reshaping the literature into forms that enables trusted autonomous systems to become a reality.

The paper offers a vision for a Trusted Cyborg Swarm, an extension of our previous Cognitive Cyber Symbiosis concept, whereby humans and machines meld together in a harmonious, seamless, and coordinated manner.

Today I read a paper titled “WalkieLokie: Relative Positioning for Augmented Reality Using a Dummy Acoustic Speaker”

The abstract is:
We propose and implement a novel relative positioning system, WalkieLokie, to enable more kinds of Augmented Reality applications, e.g., virtual shopping guide, virtual business card sharing.

WalkieLokie calculates the distance and direction between an inquiring user and the corresponding target.

It only requires a dummy speaker binding to the target and broadcasting inaudible acoustic signals.

Then the user walking around can obtain the position using a smart device.

The key insight is that when a user walks, the distance between the smart device and the speaker changes; and the pattern of displacement (variance of distance) corresponds to the relative position.

We use a second-order phase locked loop to track the displacement and further estimate the position.

To enhance the accuracy and robustness of our strategy, we propose a synchronization mechanism to synthesize all estimation results from different timeslots.

We show that the mean error of ranging and direction estimation is 0.63m and 2.46 degrees respectively, which is accurate even in case of virtual business card sharing.

Furthermore, in the shopping mall where the environment is quite severe, we still achieve high accuracy of positioning one dummy speaker, and the mean position error is 1.28m.

Today I read a paper titled “Robust Downbeat Tracking Using an Ensemble of Convolutional Networks”

The abstract is:
In this paper, we present a novel state of the art system for automatic downbeat tracking from music signals.

The audio signal is first segmented in frames which are synchronized at the tatum level of the music.

We then extract different kind of features based on harmony, melody, rhythm and bass content to feed convolutional neural networks that are adapted to take advantage of each feature characteristics.

This ensemble of neural networks is combined to obtain one downbeat likelihood per tatum.

The downbeat sequence is finally decoded with a flexible and efficient temporal model which takes advantage of the metrical continuity of a song.

We then perform an evaluation of our system on a large base of 9 datasets, compare its performance to 4 other published algorithms and obtain a significant increase of 16.8 percent points compared to the second best system, for altogether a moderate cost in test and training.

The influence of each step of the method is studied to show its strengths and shortcomings.

Today I read a paper titled “Region Based Approximation for High Dimensional Bayesian Network Models”

The abstract is:
Performing efficient inference on Bayesian Networks (BNs), with large numbers of densely connected variables is challenging.

With exact inference methods, such as the Junction Tree algorithm, clustering complexity can grow exponentially with the number of nodes and so computation becomes intractable.

This paper presents a general purpose approximate inference algorithm called Triplet Region Construction (TRC) that reduces the clustering complexity for factorized models from worst case exponential to polynomial.

We employ graph factorization to reduce connection complexity and produce clusters of limited size.

Unlike MCMC algorithms TRC is guaranteed to converge and we present experiments that show that TRC achieves accurate results when compared with exact solutions.

Today I read a paper titled “A Practical Approach to Spatiotemporal Data Compression”

The abstract is:
Datasets representing the world around us are becoming ever more unwieldy as data volumes grow.

This is largely due to increased measurement and modelling resolution, but the problem is often exacerbated when data are stored at spuriously high precisions.

In an effort to facilitate analysis of these datasets, computationally intensive calculations are increasingly being performed on specialised remote servers before the reduced data are transferred to the consumer.

Due to bandwidth limitations, this often means data are displayed as simple 2D data visualisations, such as scatter plots or images.

We present here a novel way to efficiently encode and transmit 4D data fields on-demand so that they can be locally visualised and interrogated.

This nascent “4D video” format allows us to more flexibly move the boundary between data server and consumer client.

However, it has applications beyond purely scientific visualisation, in the transmission of data to virtual and augmented reality.

Today I read a paper titled “Research Priorities for Robust and Beneficial Artificial Intelligence”

The abstract is:
Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls.

This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.

Today I read a paper titled “A Collaborative Untethered Virtual Reality Environment for Interactive Social Network Visualization”

The abstract is:
The increasing prevalence of Virtual Reality technologies as a platform for gaming and video playback warrants research into how to best apply the current state of the art to challenges in data visualization.

Many current VR systems are noncollaborative, while data analysis and visualization is often a multi-person process.

Our goal in this paper is to address the technical and user experience challenges that arise when creating VR environments for collaborative data visualization.

We focus on the integration of multiple tracking systems and the new interaction paradigms that this integration can enable, along with visual design considerations that apply specifically to collaborative network visualization in virtual reality.

We demonstrate a system for collaborative interaction with large 3D layouts of Twitter friend/follow networks.

The system is built by combining a ‘Holojam’ architecture (multiple GearVR Headsets within an OptiTrack motion capture stage) and Perception Neuron motion suits, to offer an untethered, full-room multi-person visualization experience.

Today I read a paper titled “Empath: Understanding Topic Signals in Large-Scale Text”

The abstract is:
Human language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them.

We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like “bleed” and “punch” to generate the category violence).

Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction.

Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the category with a crowd-powered filter.

Empath also analyzes text across 200 built-in, pre-validated categories we have generated from common topics in our web dataset, like neglect, government, and social media.

We show that Empath’s data-driven, human validated categories are highly correlated (r=0.906) with similar categories in LIWC.

Today I read a paper titled “Do You See What I Mean? Visual Resolution of Linguistic Ambiguities”

The abstract is:
Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via perception.

In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a visual scene which depicts one of the possible interpretations of that sentence.

To this end, we introduce a new multimodal corpus containing ambiguous sentences, representing a wide range of syntactic, semantic and discourse ambiguities, coupled with videos that visualize the different interpretations for each sentence.

We address this task by extending a vision model which determines if a sentence is depicted by a video.

We demonstrate how such a model can be adjusted to recognize different interpretations of the same underlying sentence, allowing to disambiguate sentences in a unified fashion across the different ambiguity types.

Today I read a paper titled “The GPU-based Parallel Ant Colony System”

The abstract is:
The Ant Colony System (ACS) is, next to Ant Colony Optimization (ACO) and the MAX-MIN Ant System (MMAS), one of the most efficient metaheuristic algorithms inspired by the behavior of ants.

In this article we present three novel parallel versions of the ACS for the graphics processing units (GPUs).

To the best of our knowledge, this is the first such work on the ACS which shares many key elements of the ACO and the MMAS, but differences in the process of building solutions and updating the pheromone trails make obtaining an efficient parallel version for the GPUs a difficult task.

The proposed parallel versions of the ACS differ mainly in their implementations of the pheromone memory.

The first two use the standard pheromone matrix, and the third uses a novel selective pheromone memory.

Computational experiments conducted on several Travelling Salesman Problem (TSP) instances of sizes ranging from 198 to 2392 cities showed that the parallel ACS on Nvidia Kepler GK104 GPU (1536 CUDA cores) is able to obtain a speedup up to 24.29x vs the sequential ACS running on a single core of Intel Xeon E5-2670 CPU.

The parallel ACS with the selective pheromone memory achieved speedups up to 16.85x, but in most cases the obtained solutions were of significantly better quality than for the sequential ACS.

Today I read a paper titled “Robust Supervisors for Intersection Collision Avoidance in the Presence of Uncontrolled Vehicles”

The abstract is:
We present the design and validation of a centralized controller, called a supervisor, for collision avoidance of multiple human-driven vehicles at a road intersection, considering measurement errors, unmodeled dynamics, and uncontrolled vehicles.

We design the supervisor to be least restrictive, that is, to minimize its interferences with human drivers.

This performance metric is given a precise mathematical form by splitting the design process into two subproblems: verification problem and supervisor-design problem.

The verification problem determines whether an input signal exists that makes controlled vehicles avoid collisions at all future times.

The supervisor is designed such that if the verification problem returns yes, it allows the drivers’ desired inputs; otherwise, it overrides controlled vehicles to prevent collisions.

As a result, we propose exact and efficient supervisors.

The exact supervisor solves the verification problem exactly but with combinatorial complexity.

In contrast, the efficient supervisor solves the verification problem within a quantified approximation bound in polynomially bounded time with the number of controlled vehicles.

We validate the performances of both supervisors through simulation and experimental testing.

Today I read a paper titled “PolyDepth: Real-time Penetration Depth Computation using Iterative Contact-Space Projection”

The abstract is:
We present a real-time algorithm that finds the Penetration Depth (PD) between general polygonal models based on iterative and local optimization techniques.

Given an in-collision configuration of an object in configuration space, we find an initial collision-free configuration using several methods such as centroid difference, maximally clear configuration, motion coherence, random configuration, and sampling-based search.

We project this configuration on to a local contact space using a variant of continuous collision detection algorithm and construct a linear convex cone around the projected configuration.

We then formulate a new projection of the in-collision configuration onto the convex cone as a Linear Complementarity Problem (LCP), which we solve using a type of Gauss-Seidel iterative algorithm.

We repeat this procedure until a locally optimal PD is obtained.

Our algorithm can process complicated models consisting of tens of thousands triangles at interactive rates.

Today I read a paper titled “Preprint Virtual Reality Assistant Technology for Learning Primary Geography”

The abstract is:
This is the preprint version of our paper on ICWL2015.

A virtual reality based enhanced technology for learning primary geography is proposed, which synthesizes several latest information technologies including virtual reality(VR), 3D geographical information system(GIS), 3D visualization and multimodal human-computer-interaction (HCI).

The main functions of the proposed system are introduced, i.e.

Buffer analysis, Overlay analysis, Space convex hull calculation, Space convex decomposition, 3D topology analysis and 3D space intersection detection.

The multimodal technologies are employed in the system to enhance the immersive perception of the users.

Today I read a paper titled “Real-time correction of panoramic images using hyperbolic Möbius transformations”

The abstract is:
Wide-angle images gained a huge popularity in the last years due to the development of computational photography and imaging technological advances.

They present the information of a scene in a way which is more natural for the human eye but, on the other hand, they introduce artifacts such as bent lines.

These artifacts become more and more unnatural as the field of view increases.

In this work, we present a technique aimed to improve the perceptual quality of panorama visualization.

The main ingredients of our approach are, on one hand, considering the viewing sphere as a Riemann sphere, what makes natural the application of M\”obius (complex) transformations to the input image, and, on the other hand, a projection scheme which changes in function of the field of view used.

We also introduce an implementation of our method, compare it against images produced with other methods and show that the transformations can be done in real-time, which makes our technique very appealing for new settings, as well as for existing interactive panorama applications.

Today I read a paper titled “Self-propelled Chimeras”

The abstract is:
We report the appearance of chimera states in a minimal extension of the classical Vicsek model for collective motion of self-propelled particle systems.

Inspired by earlier works on chimera states in the Kuramoto model, we introduce a phase lag parameter in the particle alignment dynamics.

Compared to the oscillatory networks with fixed site positions, the self-propelled particle systems can give rise to distinct forms of chimeras resembling moving flocks through an incoherent surrounding, for which we characterize their parameter domains.

More specifically, we detect localized directional one-headed and multi-headed chimera states, as well as scattered directional chimeras without space localization.

We discuss canonical generalizations of the elementary Vicsek model and show chimera states for them indicating the universality of this novel behavior.

A continuum limit of the particle system is derived that preserves the chimeric behavior.

Today I read a paper titled “Real-time 3D scene description using Spheres, Cones and Cylinders”

The abstract is:
The paper describes a novel real-time algorithm for finding 3D geometric primitives (cylinders, cones and spheres) from 3D range data.

In its core, it performs a fast model fitting with a model update in constant time (O(1)) for each new data point added to the model.

We use a three stage approach.The first step inspects 1.5D sub spaces, to find ellipses.

The next stage uses these ellipses as input by examining their neighborhood structure to form sets of candidates for the 3D geometric primitives.

Finally, candidate ellipses are fitted to the geometric primitives.

The complexity for point processing is O(n); additional time of lower order is needed for working on significantly smaller amount of mid-level objects.

This allows the approach to process 30 frames per second on Kinect depth data, which suggests this approach as a pre-processing step for 3D real-time higher level tasks in robotics, like tracking or feature based mapping.

Today I read a paper titled “Lens Factory: Automatic Lens Generation Using Off-the-shelf Components”

The abstract is:
Custom optics is a necessity for many imaging applications.

Unfortunately, custom lens design is costly (thousands to tens of thousands of dollars), time consuming (10-12 weeks typical lead time), and requires specialized optics design expertise.

By using only inexpensive, off-the-shelf lens components the Lens Factory automatic design system greatly reduces cost and time.

Design, ordering of parts, delivery, and assembly can be completed in a few days, at a cost in the low hundreds of dollars.

Lens design constraints, such as focal length and field of view, are specified in terms familiar to the graphics community so no optics expertise is necessary.

Unlike conventional lens design systems, which only use continuous optimization methods, Lens Factory adds a discrete optimization stage.

This stage searches the combinatorial space of possible combinations of lens elements to find novel designs, evolving simple canonical lens designs into more complex, better designs.

Intelligent pruning rules make the combinatorial search feasible.

We have designed and built several high performance optical systems which demonstrate the practicality of the system.