More Like this

1. Can Robots Get Some Human Rights? A Cross-Disciplinary Discussion

   https://doi.org/10.1155/2021/5461703  

   Persaud, Priya; Varde, Aparna S.; Wang, Weitian (September 2021, Journal of Robotics)

   Li, Changsheng (Ed.)

   An autonomous household robot passed a self-awareness test in 2015, proving that the cognitive capabilities of robots are heading towards those of humans. While this is a milestone in AI, it raises questions about legal implications. If robots are progressively developing cognition, it is important to discuss whether they are entitled to justice pursuant to conventional notions of human rights. This paper offers a comprehensive discussion of this complex question through cross-disciplinary scholarly sources from computer science, ethics, and law. The computer science perspective dissects hardware and software of robots to unveil whether human behavior can be efficiently replicated. The ethics perspective utilizes insights from robot ethics scholars to help decide whether robots can act morally enough to be endowed with human rights. The legal perspective provides an in-depth discussion of human rights with an emphasis on eligibility. The article concludes with recommendations including open research issues. 

   more » « less
2. Measuring Temporal Awareness for Human-Aware AI

   https://doi.org/10.1177/21695067231192635  

   Gray, Margaret A.; Yong, Zhuorui; Wasti, Abhijan; Rantanen, Esa M.; Heard, Jamison R. (September 2023, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)

   This research investigated human performance in response to task demands that may be used to convey information about the human to an artificial agent. We performed an experiment with a dynamic time-sharing task to investigate participants development of temporal awareness of the task event unfolding in time. Temporal awareness as an extension, or a special case, of situation awareness, may provide for useful measures of covert mental models applicable to numerous tasks and for input to human-aware AI agents. Temporal awareness measures may be used to classify human performance into the control modes in the contextual control model (COCOM): scrambled, opportunistic, tactical, and strategic. Twenty-one participants participated in a within subjects experiment with an abstract task of resetting four independent timers within their respective windows of opportunity. The results show that temporal measures of task performance are sensitive to changes in task disruptions and difficulty and therefore have promise for human-aware AI. 

   more » « less
3. Learning from Synthetic Human Group Activities

   Chang, Che-Jui; Li, Danrui; Patel, Deep; Goes, Parth; Zhou, Honglu; Moon, Seonghyeon; Sohn, Samuel S; Yoon, Sejong; Pavlovic, Vladimir; Kapadia, Mubbasir (July 2024, The IEEE/CVF Conference on Computer Vision and Pattern Recognition)

   The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world scenarios. To address the limitation, we introduce M3Act, a synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities. Powered by Unity Engine, M3Act features multiple semantic groups, highly diverse and photorealistic images, and a comprehensive set of annotations, which facilitates the learning of human-centered tasks across singleperson, multi-person, and multi-group conditions. We demonstrate the advantages of M3Act across three core experiments. The results suggest our synthetic dataset can significantly improve the performance of several downstream methods and replace real-world datasets to reduce cost. Notably, M3Act improves the state-of-the-art MOTRv2 on DanceTrack dataset, leading to a hop on the leaderboard from 10th to 2nd place. Moreover, M3Act opens new research for controllable 3D group activity generation. We define multiple metrics and propose a competitive baseline for the novel task. Our code and data are available at our project page: http://cjerry1243.github.io/M3Act. 

   more » « less
4. Generalist Multimodal LLMs Gain Biometric Expertise via Human Salience for Iris Presentation Attack Detection

   https://doi.org/10.1109/ACCESS.2026.3691016  

   Piland, Jacob C; Dowling, Byron; Sweet, Christopher; Czajka, Adam (May 2026, IEEE Access)

   Iris presentation attack detection (PAD) is critical for secure biometric deployments, yet developing specialized models faces significant practical barriers: collecting data representing future unknown attacks is impossible, and collecting diverse-enough data, yet still limited in terms of its predictive power, is expensive. Additionally, sharing biometric data raises privacy concerns. Due to rapid emergence of new attack vectors demanding adaptable solutions, we thus investigate in this paper whether general-purpose multimodal large language models (MLLMs) can perform iris PAD when augmented with human expert knowledge, operating under strict privacy constraints that prohibit sending biometric data to public cloud MLLM services. Through analysis of vision encoder embeddings applied to our dataset, we demonstrate that pre-trained vision transformers in MLLMs inherently cluster many iris attack types despite never being explicitly trained for this task. However, where clustering shows overlap between attack classes, we find that structured prompts incorporating human salience (verbal descriptions from subjects identifying attack indicators) enable these models to resolve ambiguities. Testing on an IRB-restricted dataset of 224 iris images spanning seven attack types, using only university-approved services (Gemini 2.5 Pro) or locally-hosted models (e.g., Llama 3.2-Vision), we show that Gemini with expert-informed prompts outperforms both a specialized convolutional neural networks (CNN)-based baseline and human examiners, while the locally-deployable Llama achieves near-human performance. Our results establish that MLLMs deployable within institutional privacy constraints offer a viable path for iris PAD. 

   more » « less
5. Visualizing Life in the Deep: A Creative Pipeline for Data-Driven Animations to Facilitate Marine Mammal Research, Outreach, and Conservation

   https://doi.org/10.1109/VISAP52981.2021.00007  

   Kendall-Bar, Jessica; Kendall-Bar, Nicolas; Forbes, Angus G.; McDonald, Gitte; Ponganis, Paul J.; Williams, Cassondra; Horning, Markus; Hindle, Allyson; Klinck, Holger; Beltran, Roxanne S.; et al (October 2021, 2021 IEEE VIS Arts Program (VISAP))

   In this paper, we introduce a creative pipeline to incorporate physiological and behavioral data from contemporary marine mammal research into data-driven animations, leveraging functionality from industry tools and custom scripts to promote scientific insights, public awareness, and conservation outcomes. Our framework can flexibly transform data describing animals’ orientation, position, heart rate, and swimming stroke rate to control the position, rotation, and behavior of 3D models, to render animations, and to drive data sonification. Additionally, we explore the challenges of unifying disparate datasets gathered by an interdisciplinary team of researchers, and outline our design process for creating meaningful data visualization tools and animations. As part of our pipeline, we clean and process raw acceleration and electrophysiological signals to expedite complex multi-stream data analysis and the identification of critical foraging and escape behaviors. We provide details about four animation projects illustrating marine mammal datasets. These animations, commissioned by scientists to achieve outreach and conservation outcomes, have successfully increased the reach and engagement of the scientific projects they describe. These impactful visualizations help scientists identify behavioral responses to disturbance, increase public awareness of human-caused disturbance, and help build momentum for targeted conservation efforts backed by scientific evidence. 

   more » « less