skip to main content


This content will become publicly available on October 1, 2024

Title: Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Award ID(s):
2229873 2239840
NSF-PAR ID:
10488357
Author(s) / Creator(s):
; ; ; ; ; ;
Publisher / Repository:
IEEE
Date Published:
Journal Name:
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Page Range / eLocation ID:
15908 to 15918
Format(s):
Medium: X
Location:
Paris, France
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Considerable attention has focused on studying reviewer agreement via inter-rater reliability (IRR) as a way to assess the quality of the peer review process. Inspired by a recent study that reported an IRR of zero in the mock peer review of top-quality grant proposals, we use real data from a complete range of submissions to the National Institutes of Health and to the American Institute of Biological Sciences to bring awareness to two important issues with using IRR for assessing peer review quality. First, we demonstrate that estimating local IRR from subsets of restricted-quality proposals will likely result in zero estimates under many scenarios. In both data sets, we find that zero local IRR estimates are more likely when subsets of top-quality proposals rather than bottom-quality proposals are considered. However, zero estimates from range-restricted data should not be interpreted as indicating arbitrariness in peer review. On the contrary, despite different scoring scales used by the two agencies, when complete ranges of proposals are considered, IRR estimates are above 0.6 which indicates good reviewer agreement. Furthermore, we demonstrate that, with a small number of reviewers per proposal, zero estimates of IRR are possible even when the true value is not zero. 
    more » « less
  2. Enhanced and controlled light absorption as well as field confinement in an optically thin material are pivotal for energy-efficient optoelectronics and nonlinear optical devices. Highly doped transparent conducting oxide (TCO) thin films with near-zero permittivity can support ENZ modes in the so-called epsilon near zero (ENZ) frequency region, which can lead to perfect light absorption and ultra-strong electric field intensity enhancement (FIE) within the films. To achieve full control over absorption and FIE, one must be able to tune the ENZ material properties as well as the film thickness. Here, we experimentally demonstrate engineered absorption and FIE in aluminum doped zinc oxide (AZO) thin films via control of their ENZ wavelengths, optical losses, and film thicknesses, tuned by adjusting the atomic layer deposition (ALD) parameters such as dopant ratio, deposition temperature, and number of macro-cycles. We also demonstrate that under ENZ mode excitation, though the absorption and FIE are inherently related, the film thickness required for observing maximum absorption differs significantly from that for maximum FIE. This study on engineering ENZ material properties by optimizing the ALD process will be beneficial for the design and development of next- generation tunable photonic devices based on flat, zero-index optics. 
    more » « less