The Tor network allows individuals to secure their online identities by encrypting their traffic, however it is vulnerable to fingerprinting attacks that threaten users' online privacy. In this paper, the authors develop a new video fingerprinting model to explore how well video streaming can be fingerprinted in Tor. They found that their model could distinguish which one of 50 videos a user was hypothetically watching on the Tor network with 85% accuracy, demonstrating that video fingerprinting is a serious threat to the privacy of Tor users.
In this study, the authors share their work on improving the frame rate of videos to reduce data sent to users with both 2D and 3D footage. This work helps improve the experience for both types of footage!
Playing video games may improve mental performance by encouraging practicing logical reasoning skills. Students who played video games in between two tests tended to perform better on the second test than those that did not play video games.
Intelligent vehicles utilize a combination of video-enabled object detection and radar data to traverse safely through surrounding environments. However, since the most momentary missteps in these systems can cause devastating collisions, the margin of error in the software for these systems is small. In this paper, we hypothesized that a novel object detection system that improves detection accuracy and speed of detection during adverse weather conditions would outperform industry alternatives in an average comparison.
The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.
Reaching one’s maximum jump height requires optimizing one’s jump techniques. In order to find this optimal jump technique, three high school participants with varying vertical jump (VJ) abilities recorded videos of themselves with varying degrees of maximum/minimum shoulder, knee, and hip angles—with or without respect to the horizontal—at the isometric phase of a regular countermovement (CM) VJ or countermovement jump (CMJ). Results showed that the shoulder angle without respect to the horizontal (SA), knee angle with respect to the horizontal (KAH), and the hip angle with respect to the horizontal (HAH) possessed a more consistent correlation with VJ height across the subjects compared to the same respective angles with opposite relations to the horizontal.
Here, the authors investigated engagement with #GMOFOODS, a hashtag on TikTok. They hypothesized that content focused on the negative effects of genetically modified organisms would receive more interaction driven by consumers. They found that the most common cateogry focused on the disadvantages of GMOs related to nutrition and health with the number of views determining if the video would be provided to users.
Dynamic viscosity is a quantity that describes the magnitude of a fluid’s internal friction or thickness. Traditionally, scientists measure this quantity by either calculating the terminal velocity of a falling sphere or the time a liquid takes to flow through a capillary tube. However, they have yet to conduct much research on finding this quantity through viscous damped simple harmonic motion. The present study hypothesized that the relationship between the dynamic viscosity and the damping coefficient is positively correlated.
The COVID-19 pandemic has caused disruption in social interactions. In this study, the authors tested if walking a dog will change human interactions and found that walking with a dog increased social interaction.
