Project Grant 2211133
- This $600,000 Project Grant awarded by the National Science Foundation (CFDA 47.070 - Computer and Information Science and Engineering) to the University of Illinois aims to advance video understanding capabilities by developing new techniques for analyzing extended video streams. The project will create a framework centered on token selection and context-aware representation to enable intelligent systems to comprehend complex, time-varying visual information from a broad spectrum of video...
- This $250,000 Project Grant from the National Science Foundation (NSF) under the Technology, Innovation, and Partnerships program (CFDA 47.084) will fund the development of an automatic video quality assessment and adjustment software prototype for networked camera systems. The University of Cincinnati will receive the award to design and demonstrate a software tool that can detect various causes of video quality degradation in networked cameras. The prototype will analyze video bitstreams and...
- 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 Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to democratize the use of large visual learning models by reducing the computational, data, and expertise requirements needed to create and deploy such models. The $1.2M award to Georgia Tech Research Corporation will fund research on specialized learning approaches for fast model customization with limited data, efficient inference algorithms...
- The National Science Foundation (NSF) awarded a $493,388 Project Grant under the Computer and Information Science and Engineering (CISE) federal grant program to the University of Illinois to support a collaborative research project titled "LANDS - Learning-Based Adaptive Networked Systems for Delivery of Short Videos". This transformative project aims to improve the efficiency and understanding of short-video streaming systems that deliver videos ranging from a few seconds to a few...
- This $174,176 project grant award from the National Science Foundation's Computer and Information Science and Engineering (CISE) program supports research to develop accessible and responsive video technologies. The project, titled "CRII: HCC: MAKING VIDEOS ACCESSIBLE BY DESIGN", aims to create a taxonomy of common video components and explore the needs and requirements of deaf/hard-of-hearing and blind/low-vision users for responsive video design. The research will generate...
- This Project Grant from the National Science Foundation's $524,474 Computer and Information Science and Engineering program will support the development of artificial intelligence systems capable of understanding general real-world tasks and providing step-by-step visual and language guidance to solve complex problems. Over a three-year period from June 2022 to May 2025, researchers at the University of Minnesota will create a new dataset annotating diverse everyday tasks and solutions,...
- This Project Grant award from the National Science Foundation (NSF), under the Computer and Information Science and Engineering (CFDA 47.070) program, supports the development of adaptive artificial intelligence (AI) systems to make non-speech audio content, such as environmental sounds and music, accessible in online video for deaf, hard-of-hearing, and older adult viewers. The $237,141 project, awarded to New York University (NYU), aims to create captioning tools that can identify and...
- This $285,000 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research on accounting for focus ambiguity in visual question answering (VQA) systems. The project aims to develop a socio-technical solution that empowers users to recognize and resolve ambiguity when asking questions about images, where the language used may refer to multiple parts of the image. The researchers will create an AI model...
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Project Grant award of $599,996 to the Georgia Tech Research Corporation, doing business as the Office of Sponsored Programs, supports the development of a novel video query-by-sketch system. The project aims to enable users to explore and retrieve video clips based on sketched trajectory patterns, overcoming challenges related to varying camera angles, perspectives, and user intent. The research...
This four-year, $1.264 million Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will fund the development of VOCAL, an open-source system for video organization and interactive compositional analytics. VOCAL will consist of domain-agnostic tools to support end-to-end video analytics, including interactively organizing large-scale video data, expressing and executing complex queries, and querying multi-view camera deployments. The University of Washington, as the awardee, will contribute new approaches in databases, computer vision, and artificial intelligence to build VOCAL. Specifically, the project will utilize self-supervised computer vision methods to enable data exploration for large video datasets and allow rapid development of domain-specific video event recognition models. VOCAL will also apply scene graph representations for users to compose complex queries and efficiently execute them across multiple camera views. The project aims to advance video data management capabilities while providing research experiences for students.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $1.3m | 8/22/22 |