AI, Volume 5, Issue 3 (September 2024) – 3 articles

This narrative review explores the potential, complexities, and consequences of using artificial intelligence (AI) to screen large government-held facial image databases for the early detection of rare genetic diseases. Government-held facial image databases, combined with the power of artificial intelligence, offer the potential to revolutionize the early diagnosis of rare genetic diseases. AI-powered phenotyping, as exemplified by the Face2Gene app, enables highly accurate genetic assessments from simple photographs. This and similar breakthrough technologies raise significant privacy and ethical concerns about potential government overreach augmented with the power of AI. This paper explores the concept, methods, and legal complexities of AI-based phenotyping within the EU. It highlights the transformative potential of such tools for public health while emphasizing the critical need to balance innovation with the protection of individual privacy and ethical boundaries. This comprehensive overview underscores the urgent need to develop robust safeguards around individual rights while responsibly utilizing AI’s potential for improved healthcare outcomes, including within a forensic context. Furthermore, the intersection of AI and sensitive genetic data necessitates proactive cybersecurity measures. Current and future developments must focus on securing AI models against attacks, ensuring data integrity, and safeguarding the privacy of individuals within this technological landscape. Full article

It is natural and efficient to use human natural language (NL) directly to instruct robot task executions without prior user knowledge of instruction patterns. Currently, NL-instructed robot execution (NLexe) is employed in various robotic scenarios, including manufacturing, daily assistance, and health caregiving. It is imperative to summarize the current NLexe systems and discuss future development trends to provide valuable insights for upcoming NLexe research. This review categorizes NLexe systems into four types based on the robot’s cognition level during task execution: NL-based execution control systems, NL-based execution training systems, NL-based interactive execution systems, and NL-based social execution systems. For each type of NLexe system, typical application scenarios with advantages, disadvantages, and open problems are introduced. Then, typical implementation methods and future research trends of NLexe systems are discussed to guide the future NLexe research. Full article

Multi-object tracking (MOT) aims at estimating locations and identities of objects in videos. Many modern multiple-object tracking systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. Tracking by associating detections through motion-based similarity heuristics is the basic way. Motion models aim at utilizing motion information to estimate future locations, playing an important role in enhancing the performance of association. Recently, a large-scale dataset, DanceTrack, where objects have uniform appearance and diverse motion patterns, was proposed. With existing hand-crafted motion models, it is hard to achieve decent results on DanceTrack because of the lack of prior knowledge. In this work, we present a motion-based algorithm named TLtrack, which adopts a hybrid strategy to make motion estimates based on confidence scores. For high confidence score detections, TLtrack employs transformers to predict its locations. For low confidence score detections, a simple linear model that estimates locations through trajectory historical information is used. TLtrack can not only consider the historical information of the trajectory, but also analyze the latest movements. Our experimental results on the DanceTrack dataset show that our method achieves the best performance compared with other motion models. Full article