Archives for 2017

Today I read a paper titled “Verifiable Source Code Documentation in Controlled Natural Language”

The abstract is:
Writing documentation about software internals is rarely considered a rewarding activity.

It is highly time-consuming and the resulting documentation is fragile when the software is continuously evolving in a multi-developer setting.

Unfortunately, traditional programming environments poorly support the writing and maintenance of documentation.

Consequences are severe as the lack of documentation on software structure negatively impacts the overall quality of the software product.

We show that using a controlled natural language with a reasoner and a query engine is a viable technique for verifying the consistency and accuracy of documentation and source code.

Using ACE, a state-of-the-art controlled natural language, we present positive results on the comprehensibility and the general feasibility of creating and verifying documentation.

As a case study, we used automatic documentation verification to identify and fix severe flaws in the architecture of a non-trivial piece of software.

Moreover, a user experiment shows that our language is faster and easier to learn and understand than other formal languages for software documentation.

Today I read a paper titled “Kinects and Human Kinetics: A New Approach for Studying Crowd Behavior”

The abstract is:
Modeling crowd behavior relies on accurate data of pedestrian movements at a high level of detail.

Imaging sensors such as cameras provide a good basis for capturing such detailed pedestrian motion data.

However, currently available computer vision technologies, when applied to conventional video footage, still cannot automatically unveil accurate motions of groups of people or crowds from the image sequences.

We present a novel data collection approach for studying crowd behavior which uses the increasingly popular low-cost sensor Microsoft Kinect.

The Kinect captures both standard camera data and a three-dimensional depth map.

Our human detection and tracking algorithm is based on agglomerative clustering of depth data captured from an elevated view – in contrast to the lateral view used for gesture recognition in Kinect gaming applications.

Our approach transforms local Kinect 3D data to a common world coordinate system in order to stitch together human trajectories from multiple Kinects, which allows for a scalable and flexible capturing area.

At a testbed with real-world pedestrian traffic we demonstrate that our approach can provide accurate trajectories from three Kinects with a Pedestrian Detection Rate of up to 94% and a Multiple Object Tracking Precision of 4 cm.

Using a comprehensive dataset of 2240 captured human trajectories we calibrate three variations of the Social Force model.

The results of our model validations indicate their particular ability to reproduce the observed crowd behavior in microscopic simulations.

Today I read a paper titled “Neurally-Guided Procedural Models: Learning to Guide Procedural Models with Deep Neural Networks”

The abstract is:
We present a deep learning approach for speeding up constrained procedural modeling.

Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models, but they require many samples to produce desirable results.

In this paper, we show how to create procedural models which learn how to satisfy constraints.

We augment procedural models with neural networks: these networks control how the model makes random choices based on what output it has generated thus far.

We call such a model a neurally-guided procedural model.

As a pre-computation, we train these models on constraint-satisfying example outputs generated via SMC.

They are then used as efficient importance samplers for SMC, generating high-quality results with very few samples.

We evaluate our method on L-system-like models with image-based constraints.

Given a desired quality threshold, neurally-guided models can generate satisfactory results up to 10x faster than unguided models.

Today I read a paper titled “Keypoint Encoding for Improved Feature Extraction from Compressed Video at Low Bitrates”

The abstract is:
In many mobile visual analysis applications, compressed video is transmitted over a communication network and analyzed by a server.

Typical processing steps performed at the server include keypoint detection, descriptor calculation, and feature matching.

Video compression has been shown to have an adverse effect on feature-matching performance.

The negative impact of compression can be reduced by using the keypoints extracted from the uncompressed video to calculate descriptors from the compressed video.

Based on this observation, we propose to provide these keypoints to the server as side information and to extract only the descriptors from the compressed video.

First, we introduce four different frame types for keypoint encoding to address different types of changes in video content.

These frame types represent a new scene, the same scene, a slowly changing scene, or a rapidly moving scene and are determined by comparing features between successive video frames.

Then, we propose Intra, Skip and Inter modes of encoding the keypoints for different frame types.

For example, keypoints for new scenes are encoded using the Intra mode, and keypoints for unchanged scenes are skipped.

As a result, the bitrate of the side information related to keypoint encoding is significantly reduced.

Finally, we present pairwise matching and image retrieval experiments conducted to evaluate the performance of the proposed approach using the Stanford mobile augmented reality dataset and 720p format videos.

The results show that the proposed approach offers significantly improved feature matching and image retrieval performance at a given bitrate.

Today I read a paper titled “Learning from the memory of Atari 2600”

The abstract is:
We train a number of neural networks to play games Bowling, Breakout and Seaquest using information stored in the memory of a video game console Atari 2600.

We consider four models of neural networks which differ in size and architecture: two networks which use only information contained in the RAM and two mixed networks which use both information in the RAM and information from the screen.

As the benchmark we used the convolutional model proposed in NIPS and received comparable results in all considered games.

Quite surprisingly, in the case of Seaquest we were able to train RAM-only agents which behave better than the benchmark screen-only agent.

Mixing screen and RAM did not lead to an improved performance comparing to screen-only and RAM-only agents.

Today I read a paper titled “Predictive No-Reference Assessment of Video Quality”

The abstract is:
Among the various means to evaluate the quality of video streams, No-Reference (NR) methods have low computation and may be executed on thin clients.

Thus, NR algorithms would be perfect candidates in cases of real-time quality assessment, automated quality control and, particularly, in adaptive mobile streaming.

Yet, existing NR approaches are often inaccurate, in comparison to Full-Reference (FR) algorithms, especially under lossy network conditions.

In this work, we present an NR method that combines machine learning with simple NR metrics to achieve a quality index comparably as accurate as the Video Quality Metric (VQM) Full-Reference algorithm.

Our method is tested in an extensive dataset (960 videos), under lossy network conditions and considering nine different machine learning algorithms.

Overall, we achieve an over 97% correlation with VQM, while allowing real-time assessment of video quality of experience in realistic streaming scenarios.