This Project Grant award, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, focuses on advancing the field of robotic visual perception by addressing limitations in current artificial intelligence systems. The $174,604 award, effective June 15, 2025 through May 31, 2027, aims to develop novel frameworks for understanding human behaviors and interactions, and creating robust learning mechanisms from sparse data. Key...
The University of Virginia received a $280,754 project grant award from the National Science Foundation under the Computer and Information Science and Engineering federal grant program (CFDA 47.070) to develop a spatiotemporal transformer for activity recognition in video. The University will design computing methods to automatically derive relationships between people and objects in digital video and exploit those correlations to classify human actions. Specifically, the University aims to...
This $1,200,000 Project Grant was awarded on August 15, 2023 by the National Science Foundation (NSF) Division of Information and Intelligent Systems under the Computer and Information Science and Engineering program (CFDA 47.070). The grant supports research at The Pennsylvania State University (Penn State) to develop computer vision algorithms that can accurately estimate biomechanical data like body pose, motion, and forces from video data alone. This will enable the observation of human...
This $348,956 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research at Carnegie Mellon University (CMU) to develop computational systems with an "actionable understanding" of the 3D world. The project aims to bridge the gap between 2D visual perception and 3D reasoning about actions and their effects. Specifically, the research will focus on: a) learning 2D affordances and...
This National Science Foundation (NSF) Project Grant award under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) provides $400,000.00 to the University of California, Berkeley (UC Berkeley) to conduct research on understanding, visualizing, and attributing multimodal generative models - large-scale AI models that generate both text and images. The research aims to develop new systematic frameworks for analyzing the internal mechanisms and...
This $200,000 Project Grant award, provided by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports the development of a novel multi-camera surveillance system for smart city applications. The project aims to create a scalable, efficient, and privacy-preserving real-time system that leverages distributed edge devices and cloud computing to capture and analyze video data. Key technical innovations include advanced...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) provides $111,878 to New York University (NYU) to develop a hybrid, vision-centric framework that integrates intuitive and deliberate visual processing methods to create more robust artificial intelligence (AI) capabilities. The project aims to advance vision-centric parametric knowledge, incorporate human-like non-parametric reasoning mechanisms, and integrate these...
This $400,000 project grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to develop a systematic framework for visualizing, understanding, and rewriting the learned computations of multimodal generative AI models. The key objectives are to: 1) create new methodologies to visualize the internal mechanisms and hierarchical structures of pre-trained multimodal generative models, 2) explore model...
This $600,000 project grant, awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, will support research to develop a new Bayesian diffusion model framework for advanced visual perception and cognition systems. The University of California, San Diego (UCSD) will serve as the primary awardee, with the goal of revisiting the analysis-by-synthesis methodology by integrating generative priors into the learning and inference...
This $377,674 National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) project grant, awarded on June 15, 2025, aims to enhance adaptability in multimodal human-robot interaction. The primary goals are to: 1) develop advanced algorithms to understand human intentions using multimodal data like verbal messages, gestures, eye gaze, and head movements; 2) create new learning and planning methods to help robots align their actions with human intentions; and 3)...
This $341,618 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop a new computational framework for understanding human behavior and activities in 4D (3D over time) from video. The project will create a scalable, transformer-based model that integrates the 4D state of humans with their surrounding environments, social interactions, and object use. This approach accommodates various video inputs, including first-person and third-person perspectives, and will enable applications such as assistive technologies, wearable AI, and data analysis for neuroscience and everyday tasks. The award will also integrate research and education by developing curricula and creating summer research opportunities for students, along with accessible online tools to engage a broader audience. The Regents of the University of California, Berkeley is the prime awardee for this 5-year project, which runs from June 2025 to May 2030.