Related papers: Inclusive STEAM Education: A Framework for Teachin…
Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…
We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we randomly crop image regions (exemplars) from an input image…
Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…
Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world. Previous work has primarily focused on domain randomization and system identification to…
We introduce a new challenge to test the STEM skills of neural models. The problems in the real world often require solutions, combining knowledge from STEM (science, technology, engineering, and math). Unlike existing datasets, our dataset…
Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing…
Programming has become an essential component of K-12 education and serves as a pathway for developing computational thinking skills. Given the complexity of programming and the advanced skills it requires, previous research has introduced…
Teachers have tried to teach their students by introducing text books along with verbal instructions in traditional education system. However, teaching and learning methods could be changed for developing Information and Communication…
Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed…
Cerebral Visual Impairment (CVI) is the set to be the leading cause of vision impairment, yet remains underrepresented in assistive technology research. Unlike ocular conditions, CVI affects higher-order visual processing-impacting object…
Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large language models (MLLMs).…
Advances in NLP, knowledge representation and computer graphic technologies can provide us insights into the development of educational tool for Deaf people. Actual education materials and tools for deaf pupils present several problems,…
Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…
Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…
Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…
Educational simulations have long been recognized as powerful tools for enhancing learning outcomes, yet their creation has traditionally required substantial resources and technical expertise. This paper introduces MicroSims a novel…
2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize…
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this…
Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space…
Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…