1,720,960 research outputs found
MYFix: Automated Fixation Annotation of Eye-Tracking Videos (Python Code and Sample Data)
No full text<h2>How to cite?</h2>
<p><a href="https://www.mdpi.com/1424-8220/24/9/2666">Alinaghi, N., Hollendonner, S., & Giannopoulos, I. (2024). MYFix: Automated Fixation Annotation of Eye-Tracking Videos. <em>Sensors</em>, <em>24</em>(9), 2666.</a></p>
<h2>Abstract</h2>
<div>In mobile eye-tracking research, the automatic annotation of fixation points is an important yet difficult task, especially in varied and dynamic environments such as outdoor urban landscapes. This complexity is increased by the constant movement and dynamic nature of both the observer and their environment in urban spaces. This paper presents a novel approach that integrates the capabilities of two foundation models, YOLOv8 and Mask2Former, as a pipeline to automatically annotate fixation points without requiring additional training or fine-tuning. Our pipeline leverages YOLO’s extensive training on the MS COCO dataset for object detection and Mask2Former’s training on the Cityscapes dataset for semantic segmentation. This integration not only streamlines the annotation process but also improves accuracy and consistency, ensuring reliable annotations, even in complex scenes with multiple objects side by side or at different depths. Validation through two experiments showcases its efficiency, achieving 89.05% accuracy in a controlled data collection and 81.50% accuracy in a real-world outdoor wayfinding scenario. With an average runtime per frame of 1.61 ± 0.35 s, our approach stands as a robust solution for automatic fixation annotation.</div>
<h2>How to use the code?</h2>
<p>To create the environment execute the following command: </p>
<p>`conda env create -f environment.yml`</p>
<p>Dependencies (which migth require extra attention):</p>
<p>- torch: pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118</p>
<p>- YOLO: conda install -c conda-forge ultralytics</p>
<p>- transformers: conda install -c conda-forge transformers</p>
<p> </p>
<p>To avoid problems with torch and numpy, install torch (which includes numpy anyway) first.</p>
<p>To annotate your eye-tracking data automatically, execute the `annotate.ipynb` file, and reference the data folder in the variable `base_path`, as well as the name of the gaze-data-file in `gaze_file` and the video-file in `video_file`. The following folder structure is mandatory:</p>
<p>```bash</p>
<p>.base_path</p>
<p>├── gaze_file </p>
<p>└── video_file</p>
<p>````</p>
<p>The execution of the script will create files in the following folder structure:</p>
<p>```bash</p>
<p>.base_path</p>
<p>├── extracted_frames</p>
<p>│ ├── frame_0.jpg</p>
<p>│ ├── frame_3.jpg</p>
<p>│ └── ...</p>
<p>│</p>
<p>├── outputs</p>
<p>│ ├── saved_frames_semSeg_yolo</p>
<p>│ │ ├── frame_0.jpg</p>
<p>│ │ ├── frame_3.jpg</p>
<p>│ │ └── ...</p>
<p>│ │</p>
<p>│ ├── confusion_matrix.png </p>
<p>│ ├── labeled_data_semSeg_yolo.csv</p>
<p>│ └── stitched_video.mp4</p>
<p>│</p>
<p>├── video_file</p>
<p>├── fixation_gaze_positions.csv</p>
<p>├── saccades_gaze_positions.csv</p>
<p>└── gaze_file</p>
<p>```</p>
<p>To receive evealuation results, a manual labeling for each frame is necessary. If no manual labeling is provided the script will return an error. Enter this information in the file `labeled_data_semSeg_yolo.csv` in the column `manual`.</p>
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Evaluating sentinel-2 super-resolution algorithms for automated building delineation
Get PDFSuper-Resolution is the result of enhancing the spatial resolution of images while introducing high-resolution details and has been proposed as a way to make satellite data such as Sentinel-2 more useful for real-world applications. It promises higher-resolution imagery at a low cost, as existing image sources can be relied on. While many Super-Resolution models with varying architectures and training datasets have been developed, independent frameworks to evaluate their effectiveness in real-world tasks remain limited. This thesis examines the performance of Super-Resolution for Sentinel-2 imagery on the downstream task of building delineation using a novel high-quality dataset covering Austria, created specifically for the proposed task. The methodology consists of three main steps: first, constructing a spatially and temporally aligned dataset with orthophotos as high-resolution references, Sentinel-2 images as lower-resolution inputs, and cadastral masks as ground-truth labels; second, applying Super-Resolution models to super-resolve Sentinel-2 images from a spatial resolution of 10 meter to 2.5 meter. In parallel, the Sentinel-2 images are upsampled to 2.5 meter using interpolation methods to provide a deterministic baseline for evaluating the Super-Resolution results; and third, training UNet models for building delineation on both super-resolved outputs and interpolated Sentinel-2 images. Three main findings emerge: first, orthophoto-based building delineation achieves the best results; second, models trained on interpolated images outperform those using Super-Resolution outputs; third, the differences between Super-Resolution models demonstrate that their choice of training data and architecture has a considerable influence on performance. These results suggest that, for building delineation, Super-Resolution currently offers no advantage over interpolation methods, and further development is needed to justify its real-world application. Furthermore, using original high-resolution image sources allows the most accurate result, if such data is available. More broadly, the outcomes highlight the importance of structured evaluation frameworks for benchmarking Super-Resolution on downstream tasks. Extending such evaluations to include diverse real-world applications will be essential for advancing Super-Resolution towards robust and task-oriented models capable of delivering reliable super-resolved satellite imagery
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dataset for Evaluating Sentinel-2 Super-Resolution Algorithms for Automated Building Delineation
No full text<h2>Evaluating Sentinel-2 Super-Resolution Algorithms for Automated Building Delineation</h2>
<p>This dataset is associated with the Master's Thesis "Evaluating Sentinel-2 Super-Resolution Algorithms for Automated Building Delineation" and includes all relevant datasets that were created to facilitate experiments conducted. The thesis included the evaluation of SR algorithms on the downstream task of building delineation on the example of Austria. To achieve this, several datasets had to be accessed and created, which are featured in this repository. Further information regarding the process involved, code repositories, and the published thesis are accessible under the GitHub repository: <a href="https://github.com/Zerhigh/Evaluating_Sentinel-2_Super-Resolution_Algorithms_for_Automated_Building_Delineation">https://github.com/Zerhigh/Evaluating_Sentinel-2_Super-Resolution_Algorithms_for_Automated_Building_Delineation</a></p>
<h2>Structure & Processing Details</h2>
<p>All image files are processed similarly: </p>
<ul>
<li>Remote sensing images are saved as geotiffs with provided spatial transformation parameters. When using these images, retain their spatial attributes. </li>
<li>Images are processed and annotated with <a href="https://stacspec.org/en">STAC</a> metadata, with each folder containing its own collection.</li>
</ul>
<p>The following datasets are available:</p>
<ul>
<li>main datasets:
<ul>
<li>hr_masks: 2.5m resolution cadastral masks with building footprints</li>
<li>hr_orthophoto: 2.5m resolution orthophotos of Austria</li>
<li>lr_s2: 10m resolution Sentinel-2 images of Austria (temporally and spatially aligned with the other data sources)</li>
</ul>
</li>
<li>image_samples: samples dataset representing the structure of this data repository</li>
<li>building_delineation_inference: building delineation masks extracted from super-resolved or interpolated Sentinel-2 and orthophoto images</li>
<li>metric_results: results from the conducted experiments on presented metrics</li>
<li>stratification_tables: train/validation/test splits for different dataset configurations</li>
<li>super_resolved: super-resolved Sentinel-2 images (from lr_s2) output from all used SR models</li>
<li>tracasa_evaluation: dataset to achieve evaluation on a small subset for proprietary SR models</li>
<li>thesis_figures: figures and plots featured in the written thesis</li>
</ul>
<p>This dataset contains only the image data and results, code repositories are available on the linked GitHub repository.</p>
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
