Related papers: Software-Enhanced Teaching and Visualization Capab…
Watching training videos passively leads to superficial learning. Adding gamification can increase engagement. We study how software engineering students and industry practitioners view gamifying video-based training. We conducted a survey…
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL…
The article deals with the problem of intellectual development of students in learning of physics by means of computer simulation. The main objectives of teaching computer simulation in learning of physics is the general outlook…
The integration of high-resolution image features in modern multimodal large language models has demonstrated significant improvements in fine-grained visual understanding tasks, achieving high performance across multiple benchmarks. Since…
In the last two decades, Interactive White Boards (IWBs) have been widely available as a pedagogic tool. The usability of these boards for teaching disciplines where complex drawings are needed, we consider debatable in multiple regards. In…
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…
This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…
The use of augmented reality (AR) allows for the integration of digital information onto our perception of the physical world. In this article, we present a comprehensive review of previously published literature on the implementation of…
Context: Software development is a complex socio-technical process requiring a deep understanding of various aspects. In order to support practitioners in understanding such a complex activity, repository process metrics, like number of…
The use of computer-aided and web-based educational technologies such as Virtual Learning Environments (VLE) has increased significantly in the recent past. One example of such a VLE is Virtual Interactive Engineering on the Web (VIEW).…
High-resolution perception of visual details is crucial for daily tasks. Current vision pre-training, however, is still limited to low resolutions (e.g., 378 x 378 pixels) due to the quadratic cost of processing larger images. We introduce…
360{\deg} video is attracting an increasing amount of attention in the context of Virtual Reality (VR). Owing to its very high-resolution requirements, existing professional streaming services for 360{\deg} video suffer from severe…
Open Source Software (OSS) has been widely used in the educational environment largely due to its reduced cost of ownership. While OSS has evolved over the years, challenges exist in its implementation and wide adoption. Foremost among…
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on…
This paper asks whether current self-supervised learning methods, if sufficiently scaled up, would be able to reach human-level visual object recognition capabilities with the same type and amount of visual experience humans learn from.…
Computer science education has evolved extensively; however, systemic barriers still prevent students with visual impairments from fully participating. While existing research has developed specialized programming tools and assistive…
Deep learning is one of the fastest growing technologies in computer science with a plethora of applications. But this unprecedented growth has so far been limited to the consumption of deep learning experts. The primary challenge being a…
Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study…
We have developed a Java-based teaching tool, "Appreciating Hubble at Hyper-speed" ($\textit{AHaH}$), intended for use by students and instructors in beginning astronomy and cosmology courses, which we have made available online. This tool…
Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early benchmarks rather than grounded in principled design. In this work, we show that observation…