Research in artificial intelligence (AI)-assisted decision-making is experiencing tremendous growth with a constantly rising number of studies evaluating the effect AI and without techniques from field explainable (XAI) on human performance. However, as tasks experimental setups vary due to different objectives, some report improved user performance through XAI, while others only negligible effects. Therefore, this article, we present an initial synthesis existing research XAI using...

Recent work has proposed artificial intelligence (AI) models that can learn to decide whether make a prediction for an instance of task or delegate it human by considering both parties' capabilities. In simulations with synthetically generated context-independent predictions, delegation help improve the performance human-AI teams -- compared humans AI model completing alone. However, so far, remains unclear how perform and they perceive when are aware delegated instances them. experimental...

In recent years, the rapid development of AI systems has brought about benefits intelligent services but also concerns security and reliability. By fostering appropriate user reliance on an system, both complementary team performance reduced human workload can be achieved. Previous empirical studies have extensively analyzed impact factors ranging from task, behavior trust in context one-step decision making. However, tasks with complex semantics that require multi-step workflows remains...

Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for image classification. However, large labeled data sets are generally needed the training and validation of such models. In many domains, unlabeled is available but labeling expensive, instance when specific expert knowledge required. Active Learning (AL) one approach mitigate problem limited data. Through selecting most informative representative instances labeling, AL can contribute more efficient learning a...

In recent years, companies in the Architecture, Engineering, and Construction (AEC) industry have started exploring how artificial intelligence (AI) can reduce time-consuming repetitive tasks. One use case that benefit from adoption of AI is determination quantities floor plans. This information required for several planning construction steps. Currently, task requires to invest a significant amount manual effort. Either digital plans are not available existing buildings, or formats cannot...

The constantly increasing capabilities of artificial intelligence (AI) open new possibilities for human-AI collaboration. One promising approach to leverage existing complementary is allowing humans delegate individual instances the AI. However, enabling effectively requires them assess both their own and AI's in context given task. In this work, we explore effects providing contextual information on human decisions an We find that participants with significantly improves team performance....

A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths. While this an essential component many surgeries, it involves substantial human effort and prone to inaccuracies. In paper, we develop a novel human-AI-based method for laparoscopic measurements utilizing stereo vision that has been guided by practicing surgeons. Based on holistic qualitative requirements analysis, work proposes...

Recent work has proposed artificial intelligence (AI) models that can learn to decide whether make a prediction for task instance or delegate it human by considering both parties’ capabilities. In simulations with synthetically generated context-independent predictions, delegation help improve the performance of human-AI teams—compared humans AI model completing alone. However, so far, remains unclear how perform and they perceive when individual instances are delegated them an model....

A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths. While this an essential component many surgeries, it involves substantial human effort and prone to inaccuracies. In paper, we develop a novel human-AI-based method for laparoscopic measurements utilizing stereo vision that has been guided by practicing surgeons. Based on holistic qualitative requirements analysis, work proposes...

Recent advances in synthetic imaging open up opportunities for obtaining additional data the field of surgical imaging. This can provide reliable supplements supporting applications and decision-making through computer vision. Particularly image-guided surgery, such as laparoscopic robotic-assisted benefits strongly from image datasets virtual training methods. Our study presents an intuitive approach generating images short text prompts using diffusion-based generative models. We...

Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for supervised computer vision tasks, such as image classification. However, large labeled data sets are generally needed the training and validation of models. In many domains, unlabeled is available but labeling expensive, instance when specific expert knowledge required. Active Learning (AL) one approach mitigate problem limited data. Through selecting most informative representative instances labeling, AL can...