Search By Subject

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is an innovative cross-modal task that utilizes a sketch to retrieve corresponding images in the zero-shot learning scene. At present, most algorithms treat ZS-SBIR as a typical image classification ...

Event Detection (ED) is an important task in natural language processing. In the past few years, many datasets have been introduced for advancing ED machine learning models. However, most of these datasets are under-explored because not many tools are ...

Explainable Artificial Intelligence (XAI) is an emerging subdiscipline of Machine Learning (ML) and human-computer interaction. Discriminative models need to be understood. An explanation of such ML models is vital when an AI system makes decisions ...

Over the past few years, rapid developments in AI have resulted in new models capable of generating high-quality images and creative artefacts, most of which seek to fully automate the process of creation. In stark contrast, creative professionals rely ...

Large-scale Text-to-image Generation Models (LTGMs) (e.g., DALL-E), self-supervised deep learning models trained on a huge dataset, have demonstrated the capacity for generating high-quality open-domain images from multi-modal input. Although they can ...

Previous studies regarding the perception of emotions for embodied virtual agents have shown the effectiveness of using virtual characters in conveying emotions through interactions with humans. However, creating an autonomous embodied conversational ...

Presenters often collect audience feedback through practice talks to refine their presentations. In formative interviews, we find that although text feedback and verbal discussions allow presenters to receive feedback, organizing that feedback into ...

Citizens and policy institutions increasingly express their concerns regarding the emerging challenges in the context of Artificial Intelligence (AI) and have concrete demands for the protection of human rights. In parallel, studies in the field of AI ...

As robots become increasingly prevalent in our communities, aligning the values motivating their behavior with human values is critical. However, it is often difficult or impossible for humans, both expert and non-expert, to enumerate values ...

Human skeleton-based gesture classification plays a dominant role in social robotics. Learning the variety of human skeleton-based gestures can help the robot to continuously interact in an appropriate manner in a natural human-robot interaction (HRI). ...

Theory of mind (ToM) corresponds to the human ability to infer other people's desires, beliefs, and intentions. Acquisition of ToM skills is crucial to obtain a natural interaction between robots and humans. A core component of ToM is the ability to ...

Lane changes of autonomous vehicles (AV) should not only succeed in making the maneuver but also provide a positive interaction experience for other drivers. As lane changes involve complex interactions, identification of a set of behaviors for ...

This paper describes a user experience comparison study to explore whether a user's 'cultural background' affects their interaction with in-home pet robots designed for health purposes, e.g. socially-assistive robots (SARs). 11 Koreans and 10 Americans ...

Social robots should deal with uncertainties in unseen environments and situations in an interactive setting. For humans, question-answering is one of the most typical activities for resolving or reducing uncertainty by acquiring additional information, ...

We demonstrate how state-of-art open-source tools for automatic speech recognition (vosk) and dialogue management (rasa) can be integrated on a social robotic platform (PAL Robotics' ARI robot) to provide rich verbal interactions.

Our open-source, ROS-...

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to underestimate a ...

Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction-following agents cannot adapt, lacking the ability to incorporate online ...

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task --- the task "features" --- as well as how to combine these features into a single ...

Recent research in robot learning suggests that implicit human feedback is a low-cost approach to improving robot behavior without the typical teaching burden on users. Because implicit feedback can be difficult to interpret, though, we study different ...

An estimated 20% of patients admitted to hospital wards are affected by delirium. Early detection is recommended to treat underlying causes of delirium, however workforce strain in general wards often causes it to remain undetected. This work proposes a ...