Related papers: Sharing Linkable Learning Objects with the use of …
In this paper, we propose a novel approach for generalized zero-shot learning in a multi-modal setting, where we have novel classes of audio/video during testing that are not seen during training. We use the semantic relatedness of text…
The online fusion and tracking of static objects from heterogeneous sensor detections is a fundamental problem in robotics, autonomous systems, and environmental mapping. Although classical data association approaches such as JPDA are well…
Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However,…
Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…
The paper illustrates the research result of the application of semantic technology to ease the use and reuse of digital contents exposed as Linked Data on the web. It focuses on the specific issue of explorative research for the resource…
This paper explores the potential developments of self-directed learning in the metaverse in response to Education 4.0 and the Fourth Industrial Revolution. It highlights the importance of education keeping up with technological…
Although several RDF knowledge bases are available through the LOD initiative, the ontology schema of such linked datasets is not very rich. In particular, they lack object properties. The problem of finding new object properties (and their…
This is the era of Information and Communication Technology (ICT). Nowadays, there is no limit to learn, people can learn anywhere and anytime with the enhancement of technology. Electronic Learning (E-learning) and Mobile Learning…
Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction. Using noisy labels in single-task learning increases the risk of over-fitting. Auxiliary tasks…
Recently, e-learning platforms have grown as a place where students can post doubts (as a snap taken with smart phones) and get them resolved in minutes. However, the significant increase in the number of student-posted doubts with high…
In an effort to foster learning by teaching, we propose the development of a canvas system that makes composing e-learning modules intuitive. We try to empower and liberate non-technical module users by lowering the bar for turning them…
One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations,…
In order to effectively prepare the next generation of IT professionals and systems analysts, it is important to incorporate cloud based online collaboration tools into the coursework for developing the students' cooperative skills as well…
Bloom taxonomy is a common paradigm for categorizing educational learning objectives into three learning levels: cognitive, affective, and psychomotor. For the optimization of educational programs, it is crucial to design course learning…
What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data. In this paper, we introduce unsupervised learning under…
Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), notably GPT-4, have shown great promises in labelling data with…
Federated fine-tuning offers a promising solution for adapting Large Language Models (LLMs) to downstream tasks while safeguarding data privacy. However, its high computational and communication demands hinder its deployment on…
Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking…
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings,…
Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have…