Computer Vision. Director of Research @Salesforce @SFResearch, Adjunct Professor @Stanford @StanfordSVL.
Jun 21, 2022 • 10 tweets • 6 min read
In our #CVPR2022 Oral, we introduce the atemporal probe (ATP) to analyze *atemporal* (single frame) bias in video-language, with surprising results! (see 🧵)
1/10
The promise of videos is the potential to go *beyond* image-centric understanding (people, objects, scenes, etc.) towards event temporality, causality, and dynamics. Ideally, we want video-language benchmarks and models to realize this promise.
2/10
Oct 11, 2021 • 6 tweets • 4 min read
Excited to introduce a new generation of privacy protecting smart cameras in our #ICCV2021 Oral paper by @CarlosH_93, @henarfu and myself 🇺🇸🇨🇴. See 🧵 below for details!
@StanfordAILab
Our cameras introduce optical distortions at acquisition time, capturing images that protect the identity of people in the scene while enabling vision algorithms to perform inference accurately.