Today I finished reading “Nothing Serious” by P.G. Wodehouse
What. The. Fuck.
Who the fuck let the six year old with the box of rainbow Crayola run loose in the Skype offices and scrawl all over the UI diagrams?
With the new version of Skype I feel like all of the colour has been sucked out of my world…
And placed in to the user interface of the application.
Paper – Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects
Today I read a paper titled “Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects”
The abstract is:
Human vision greatly benefits from the information about sizes of objects.
The role of size in several visual reasoning tasks has been thoroughly explored in human perception and cognition.
However, the impact of the information about sizes of objects is yet to be determined in AI.
We postulate that this is mainly attributed to the lack of a comprehensive repository of size information.
In this paper, we introduce a method to automatically infer object sizes, leveraging visual and textual information from web.
By maximizing the joint likelihood of textual and visual observations, our method learns reliable relative size estimates, with no explicit human supervision.
We introduce the relative size dataset and show that our method outperforms competitive textual and visual baselines in reasoning about size comparisons.
Read – Jeeves and the Yule-tide Spirit
Today I finished reading “Jeeves and the Yule-tide Spirit” by P.G. Wodehouse
Read – Jeeves, Jeeves, Jeeves
Today I finished reading “Jeeves, Jeeves, Jeeves” by P.G. Wodehouse
Paper – Vision Based Navigation for a Mobile Robot with Different Field of Views
Today I read a paper titled “Vision Based Navigation for a Mobile Robot with Different Field of Views”
The abstract is:
The basic idea behind evolutionary robotics is to evolve a set of neural controllers for a particular task at hand.
It involves use of various input parameters such as infrared sensors, light sensors and vision based methods.
This paper aims to explore the evolution of vision based navigation in a mobile robot.
It discusses in detail the effect of different field of views for a mobile robot.
The individuals have been evolved using different FOV values and the results have been recorded and analyzed.The optimum values for FOV have been proposed after evaluating more than 100 different values.
It has been observed that the optimum FOV value requires lesser number of generations for evolution and the mobile robot trained with that particular value is able to navigate well in the environment.
Boom! Chicka! Mao! Mao! – 22
When you own a cat (called Mao):
“Mao! Stop sleeping on the vintage computers.”
Paper – Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems
Today I read a paper titled “Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems”
The abstract is:
This paper proposes an approach that predicts the road course from camera sensors leveraging deep learning techniques.
Road pixels are identified by training a multi-scale convolutional neural network on a large number of full-scene-labeled night-time road images including adverse weather conditions.
A framework is presented that applies the proposed approach to longer distance road course estimation, which is the basis for an augmented reality navigation application.
In this framework long range sensor data (radar) and data from a map database are fused with short range sensor data (camera) to produce a precise longitudinal and lateral localization and road course estimation.
The proposed approach reliably detects roads with and without lane markings and thus increases the robustness and availability of road course estimations and augmented reality navigation.
Evaluations on an extensive set of high precision ground truth data taken from a differential GPS and an inertial measurement unit show that the proposed approach reaches state-of-the-art performance without the limitation of requiring existing lane markings.
Paper – Dictionary Learning for Robotic Grasp Recognition and Detection
Today I read a paper titled “Dictionary Learning for Robotic Grasp Recognition and Detection”
The abstract is:
The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics.
For a system to accomplish this, it must autonomously identify grasping locations by using information from various sensors, such as Microsoft Kinect 3D camera.
Despite numerous progress, significant work still remains to be done in this field.
To this effect, we propose a dictionary learning and sparse representation (DLSR) framework for representing RGBD images from 3D sensors in the context of determining such good grasping locations.
In contrast to previously proposed approaches that relied on sophisticated regularization or very large datasets, the derived perception system has a fast training phase and can work with small datasets.
It is also theoretically founded for dealing with masked-out entries, which are common with 3D sensors.
We contribute by presenting a comparative study of several DLSR approach combinations for recognizing and detecting grasp candidates on the standard Cornell dataset.
Importantly, experimental results show a performance improvement of 1.69% in detection and 3.16% in recognition over current state-of-the-art convolutional neural network (CNN).
Even though nowadays most popular vision-based approach is CNN, this suggests that DLSR is also a viable alternative with interesting advantages that CNN has not.
Read – Do Butlers Burgle Banks?
Today I finished reading “Do Butlers Burgle Banks?” by P.G. Wodehouse
Read – Money in the Bank
Today I finished reading “Money in the Bank” by P.G. Wodehouse
Paper – An artificial intelligence tool for heterogeneous team formation in the classroom
Today I read a paper titled “An artificial intelligence tool for heterogeneous team formation in the classroom”
The abstract is:
Nowadays, there is increasing interest in the development of teamwork skills in the educational context.
This growing interest is motivated by its pedagogical effectiveness and the fact that, in labour contexts, enterprises organize their employees in teams to carry out complex projects.
Despite its crucial importance in the classroom and industry, there is a lack of support for the team formation process.
Not only do many factors influence team performance, but the problem becomes exponentially costly if teams are to be optimized.
In this article, we propose a tool whose aim it is to cover such a gap.
It combines artificial intelligence techniques such as coalition structure generation, Bayesian learning, and Belbin’s role theory to facilitate the generation of working groups in an educational context.
This tool improves current state of the art proposals in three ways: i) it takes into account the feedback of other teammates in order to establish the most predominant role of a student instead of self-perception questionnaires; ii) it handles uncertainty with regard to each student’s predominant team role; iii) it is iterative since it considers information from several interactions in order to improve the estimation of role assignments.
We tested the performance of the proposed tool in an experiment involving students that took part in three different team activities.
The experiments suggest that the proposed tool is able to improve different teamwork aspects such as team dynamics and student satisfaction.
Read – Laughing Gas
Today I finished reading “Laughing Gas” by P.G. Wodehouse
Read – Empowered Special #1: The Wench with a Million Sighs
Today I finished reading “Empowered Special #1: The Wench with a Million Sighs” by Adam Warren
Paper – Auditory Brain-Computer Interface Paradigm with Head Related Impulse Response-based Spatial Cues
Today I read a paper titled “Auditory Brain-Computer Interface Paradigm with Head Related Impulse Response-based Spatial Cues”
The abstract is:
The aim of this study is to provide a comprehensive test of head related impulse response (HRIR) for an auditory spatial speller brain-computer interface (BCI) paradigm.
The study is conducted with six users in an experimental set up based on five Japanese hiragana vowels.
Auditory evoked potentials resulted with encouragingly good and stable “aha-” or P300-responses in real-world online BCI experiments.
Our case study indicated that the auditory HRIR spatial sound reproduction paradigm could be a viable alternative to the established multi-loudspeaker surround sound BCI-speller applications, as far as healthy pilot study users are concerned.
Studying – Cocos2D Game Development
This month I am studying “Cocos2D Game Development”
Video. Lots of video. Online class.
I have already worked on a couple of projects using Cocos2D when it first released, and have helped a number of companies in the past few years get their projects launched that made use of Cocos2D.
Familiarity with the material should enable me to run through it very quickly.
It will be interesting to see if there are any gaps in my knowledge.
Paper – Real-Time Human Motion Capture with Multiple Depth Cameras
Today I read a paper titled “Real-Time Human Motion Capture with Multiple Depth Cameras”
The abstract is:
Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras.
In this work we present an efficient and inexpensive solution to markerless motion capture using only a few Kinect sensors.
Unlike the previous work on 3d pose estimation using a single depth camera, we relax constraints on the camera location and do not assume a co-operative user.
We apply recent image segmentation techniques to depth images and use curriculum learning to train our system on purely synthetic data.
Our method accurately localizes body parts without requiring an explicit shape model.
The body joint locations are then recovered by combining evidence from multiple views in real-time.
We also introduce a dataset of ~6 million synthetic depth frames for pose estimation from multiple cameras and exceed state-of-the-art results on the Berkeley MHAD dataset.
Promoted Spam
When I am browsing Pinterest for whatever latest piece of woodworking jig or furniture design idea I am inundated with utterly useless “Promoted By” spam ads. Not once have I ever been interested in any of these promoted ads. And the number of them, sometimes five or six on a page is ridiculous.
I know there are various plug-ins for Chrome and Firefox that let you block the Promoted By ads on Pinterest. But they always seem to generate a bad user experience, and really, that’s not taking care of the problem, merely hiding it with CSS.
On Sunday I built a little plug-in for Chrome that removes the Promoted By ad by promptly selecting it, flagging it as inappropriate, e.g. gore, intellectual property violation, nudity or pornography, and then hitting that “Block this user” button right afterwards. So far it seems to be working reasonably well.
Read – French Leave
Today I finished reading “French Leave” by P.G. Wodehouse
Boom! Chicka! Mao! Mao! – 21
When you own a cat (called Mao):
“Mao! Stop pooping in the recycling can!”
Paper – Graph-based compression of dynamic 3D point cloud sequences
Today I read a paper titled “Graph-based compression of dynamic 3D point cloud sequences”
The abstract is:
This paper addresses the problem of compression of 3D point cloud sequences that are characterized by moving 3D positions and color attributes.
As temporally successive point cloud frames are similar, motion estimation is key to effective compression of these sequences.
It however remains a challenging problem as the point cloud frames have varying numbers of points without explicit correspondence information.
We represent the time-varying geometry of these sequences with a set of graphs, and consider 3D positions and color attributes of the points clouds as signals on the vertices of the graphs.
We then cast motion estimation as a feature matching problem between successive graphs.
The motion is estimated on a sparse set of representative vertices using new spectral graph wavelet descriptors.
A dense motion field is eventually interpolated by solving a graph-based regularization problem.
The estimated motion is finally used for removing the temporal redundancy in the predictive coding of the 3D positions and the color characteristics of the point cloud sequences.
Experimental results demonstrate that our method is able to accurately estimate the motion between consecutive frames.
Moreover, motion estimation is shown to bring significant improvement in terms of the overall compression performance of the sequence.
To the best of our knowledge, this is the first paper that exploits both the spatial correlation inside each frame (through the graph) and the temporal correlation between the frames (through the motion estimation) to compress the color and the geometry of 3D point cloud sequences in an efficient way.
Boom! Chicka! Mao! Mao! – 20
When you own a cat (called Mao):
“Mao! Stop flushing the toilet you little shithead. California has a drought because of you!”
Paper – InAR:Inverse Augmented Reality
Today I read a paper titled “InAR:Inverse Augmented Reality”
The abstract is:
Augmented reality is the art to seamlessly fuse virtual objects into real ones.
In this short note, we address the opposite problem, the inverse augmented reality, that is, given a perfectly augmented reality scene where human is unable to distinguish real objects from virtual ones, how the machine could help do the job.
We show by structure from motion (SFM), a simple 3D reconstruction technique from images in computer vision, the real and virtual objects can be easily separated in the reconstructed 3D scene.
Read – The Druid of Shannara
Today I finished reading “The Druid of Shannara” by Terry Brooks
Read – A Princess of Landover
Today I finished reading “A Princess of Landover” by Terry Brooks
Paper – Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation
Today I read a paper titled “Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation”
The abstract is:
Recently, mid-level features have shown promising performance in computer vision.
Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features.
In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition.
Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints.
Secondly, limbs are combined into parts and the limb’s states are mapped into part states.
Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames.
These parts are referred to as Frequent Local Parts or FLPs.
The FLPs allow us to build powerful bag-of-FLP-based action representation.
This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.
Studying – Game development with EaselJS
This month I am studying “Game development with EaselJS”
Two evenings a week for the next month of an in-person class at one of the local code camp schools.
JavaScript, EaselJS, game development. Should be an easy class. I could learn this on my own (the EaselJS part) but I think an instructor lead class would be more interesting.
Update #1: Very slow class. Assumes you know no programming whatsoever.
Update #2: End of week two and I am done. I’ve gone through all of the course ware, done the exercises, and done a bunch of extra work. I didn’t realize this class would be so basic.
Paper – Ownership and Agency of an Independent Supernumerary Hand Induced by an Imitation Brain-Computer Interface
Today I read a paper titled “Ownership and Agency of an Independent Supernumerary Hand Induced by an Imitation Brain-Computer Interface”
The abstract is:
To study body ownership and control, illusions that elicit these feelings in non-body objects are widely used.
Classically introduced with the Rubber Hand Illusion, these illusions have been replicated more recently in virtual reality and by using brain-computer interfaces.
Traditionally these illusions investigate the replacement of a body part by an artificial counterpart, however as brain-computer interface research develops it offers us the possibility to explore the case where non-body objects are controlled in addition to movements of our own limbs.
Therefore we propose a new illusion designed to test the feeling of ownership and control of an independent supernumerary hand.
Subjects are under the impression they control a virtual reality hand via a brain-computer interface, but in reality there is no causal connection between brain activity and virtual hand movement but correct movements are observed with 80% probability.
These imitation brain-computer interface trials are interspersed with movements in both the subjects’ real hands, which are in view throughout the experiment.
We show that subjects develop strong feelings of ownership and control over the third hand, despite only receiving visual feedback with no causal link to the actual brain signals.
Our illusion is crucially different from previously reported studies as we demonstrate independent ownership and control of the third hand without loss of ownership in the real hands.
Boom! Chicka! Mao! Mao! – 19
When you own a cat (called Mao):
“Mao! Keep your paws out of the path of the laser!”
Recruiter without a clue
What kind of moron sends a recruitment email with 28 separate images attached to it?
Boom! Chicka! Mao! Mao! – 18
When you own a cat (called Mao):
“Mao! Do not interrupt the Linux kernel build by sleeping on the keyboard or I swear you’ll be made personal assistant to Torvalds in your next life.”
Paper – Interactive 3D Face Stylization Using Sculptural Abstraction
Today I read a paper titled “Interactive 3D Face Stylization Using Sculptural Abstraction”
The abstract is:
Sculptors often deviate from geometric accuracy in order to enhance the appearance of their sculpture.
These subtle stylizations may emphasize anatomy, draw the viewer’s focus to characteristic features of the subject, or symbolize textures that might not be accurately reproduced in a particular sculptural medium, while still retaining fidelity to the unique proportions of an individual.
In this work we demonstrate an interactive system for enhancing face geometry using a class of stylizations based on visual decomposition into abstract semantic regions, which we call sculptural abstraction.
We propose an interactive two-scale optimization framework for stylization based on sculptural abstraction, allowing real-time adjustment of both global and local parameters.
We demonstrate this system’s effectiveness in enhancing physical 3D prints of scans from various sources.
Paper – A New Generation of Brain-Computer Interface Based on Riemannian Geometry
Today I read a paper titled “A New Generation of Brain-Computer Interface Based on Riemannian Geometry”
The abstract is:
Based on the cumulated experience over the past 25 years in the field of Brain-Computer Interface (BCI) we can now envision a new generation of BCI.
Such BCIs will not require training; instead they will be smartly initialized using remote massive databases and will adapt to the user fast and effectively in the first minute of use.
They will be reliable, robust and will maintain good performances within and across sessions.
A general classification framework based on recent advances in Riemannian geometry and possessing these characteristics is presented.
It applies equally well to BCI based on event-related potentials (ERP), sensorimotor (mu) rhythms and steady-state evoked potential (SSEP).
The framework is very simple, both algorithmically and computationally.
Due to its simplicity, its ability to learn rapidly (with little training data) and its good across-subject and across-session generalization, this strategy a very good candidate for building a new generation of BCIs, thus we hereby propose it as a benchmark method for the field.
Read – The Golf Omnibus
Today I finished reading “The Golf Omnibus” by P.G. Wodehouse
Read – The Cookie Tree
Today I finished reading “The Cookie Tree” by Jay Williams
Paper – Facial Expression Cloning with Elastic and Muscle Models
Today I read a paper titled “Facial Expression Cloning with Elastic and Muscle Models”
The abstract is:
Expression cloning plays an important role in facial expression synthesis.
In this paper, a novel algorithm is proposed for facial expression cloning.
The proposed algorithm first introduces a new elastic model to balance the global and local warping effects, such that the impacts from facial feature diversity among people can be minimized, and thus more effective geometric warping results can be achieved.
Furthermore, a muscle-distribution-based (MD) model is proposed, which utilizes the muscle distribution of the human face and results in more accurate facial illumination details.
In addition, we also propose a new distance-based metric to automatically select the optimal parameters such that the global and local warping effects in the elastic model can be suitably balanced.
Experimental results show that our proposed algorithm outperforms the existing methods.
Read – Little Platinum Book of Cha-Ching
Today I finished reading “Little Platinum Book of Cha-Ching: 32.5 Strategies to Ring Your Own (Cash) Register in Business and Personal Success” by Jeffrey Gitomer
Paper – An Evolved Neural Controller for Bipdedal Walking with Dynamic Balance
Today I read a paper titled “An Evolved Neural Controller for Bipdedal Walking with Dynamic Balance”
The abstract is:
We successfully evolved a neural network controller that produces dynamic walking in a simulated bipedal robot with compliant actuators, a difficult control problem.
The evolutionary evaluation uses a detailed software simulation of a physical robot.
We describe: 1) a novel theoretical method to encourage populations to evolve “around” local optima, which employs multiple demes and fitness functions of progressively increasing difficulty, and 2) the novel genetic representation of the neural controller.
Boom! Chicka! Mao! Mao! – 17
When you own a cat (called Mao):
“Mao! I swear to God if you explode playing with that I will clean up your remains with the cheap kitchen towels I reserve for the dog vomit!”
Read – Mr. Mulliner Speaking
Today I finished reading “Mr. Mulliner Speaking” by P.G. Wodehouse
Read – The 80/20 Revolution
Today I finished reading “The 80/20 Revolution” by Richard Koch
Paper – Preprint: Bringing immersive enjoyment to hyperbaric oxygen chamber users using virtual reality glasses
Today I read a paper titled “Preprint: Bringing immersive enjoyment to hyperbaric oxygen chamber users using virtual reality glasses”
The abstract is:
This is the preprint version of our paper on REHAB2015.
This paper proposed a novel immersive entertainment system for the users of hyperbaric oxygen therapy chamber.
The system is a hybrid of hardware and software, the scheme is described in this paper.
The hardware is combined by a HMD (i.e.
virtual reality glasses shell), a smartphone and a waterproof bag.
The software is able to transfer the stereoscopic images of the 3D game to the screen of the smartphone synchronously.
The comparison and selection of the hardware are discussed according to the practical running scene of the clinical hyperbaric oxygen treatment.
Finally, a preliminary guideline for designing this kind of system is raised accordingly.
Read – Pieces 3: Wild Wet Quest
Today I finished reading “Pieces 3: Wild Wet Quest” by Masamune Shirow
Paper – Development of a wheelchair simulator for children with multiple disabilities
Today I read a paper titled “Development of a wheelchair simulator for children with multiple disabilities”
The abstract is:
Virtual reality allows to create situations which can be experimented under the control of the user, without risks, in a very flexible way.
This allows to develop skills and to have confidence to work in real conditions with real equipment.
VR is then widely used as a training and learning tool.
More recently, VR has also showed its potential in rehabilitation and therapy fields because it provides users with the ability of repeat their actions several times and to progress at their own pace.
In this communication, we present our work in the development of a wheelchair simulator designed to allow children with multiple disabilities to familiarize themselves with the wheelchair.
Read – Spook Country
Today I finished reading “Spook Country” by William Gibson
Read – The Coming Of Bill
Today I finished reading “The Coming Of Bill” by P.G. Wodehouse
Read – Three Men and A Maid Plus A Damsel In Distress
Today I finished reading “Three Men and A Maid Plus A Damsel In Distress” by P.G. Wodehouse
Paper – When Augmented Reality Meets Big Data
Today I read a paper titled “When Augmented Reality Meets Big Data”
The abstract is:
With computing and sensing woven into the fabric of everyday life, we live in an era where we are awash in a flood of data from which we can gain rich insights.
Augmented reality (AR) is able to collect and help analyze the growing torrent of data about user engagement metrics within our personal mobile and wearable devices.
This enables us to blend information from our senses and the digitalized world in a myriad of ways that was not possible before.
AR and big data have a logical maturity that inevitably converge them.
The tread of harnessing AR and big data to breed new interesting applications is starting to have a tangible presence.
In this paper, we explore the potential to capture value from the marriage between AR and big data technologies, following with several challenges that must be addressed to fully realize this potential.
Paper – The Dark Side of Ethical Robots
Today I read a paper titled “The Dark Side of Ethical Robots”
The abstract is:
Concerns over the risks associated with advances in Artificial Intelligence have prompted calls for greater efforts toward robust and beneficial AI, including machine ethics.
Recently, roboticists have responded by initiating the development of so-called ethical robots.
These robots would, ideally, evaluate the consequences of their actions and morally justify their choices.
This emerging field promises to develop extensively over the next years.
However, in this paper, we point out an inherent limitation of the emerging field of ethical robots.
We show that building ethical robots also necessarily facilitates the construction of unethical robots.
In three experiments, we show that it is remarkably easy to modify an ethical robot so that it behaves competitively, or even aggressively.
The reason for this is that the specific AI, required to make an ethical robot, can always be exploited to make unethical robots.
Hence, the development of ethical robots will not guarantee the responsible deployment of AI.
While advocating for ethical robots, we conclude that preventing the misuse of robots is beyond the scope of engineering, and requires instead governance frameworks underpinned by legislation.
Without this, the development of ethical robots will serve to increase the risks of robotic malpractice instead of diminishing it.
Paper – Spontaneous vs. Posed smiles – can we tell the difference?
Today I read a paper titled “Spontaneous vs. Posed smiles – can we tell the difference?”
The abstract is:
Smile is an irrefutable expression that shows the physical state of the mind in both true and deceptive ways.
Generally, it shows happy state of the mind, however, `smiles’ can be deceptive, for example people can give a smile when they feel happy and sometimes they might also give a smile (in a different way) when they feel pity for others.
This work aims to distinguish spontaneous (felt) smile expressions from posed (deliberate) smiles by extracting and analyzing both global (macro) motion of the face and subtle (micro) changes in the facial expression features through both tracking a series of facial fiducial markers as well as using dense optical flow.
Specifically the eyes and lips features are captured and used for analysis.
It aims to automatically classify all smiles into either `spontaneous’ or `posed’ categories, by using support vector machines (SVM).
Experimental results on large database show promising results as compared to other relevant methods.