2.2k citations
- University of WashingtonUS72 papers
- Carnegie Mellon UniversityUS25 papers
- University of PennsylvaniaUS14 papers
- Bar-Ilan UniversityIL13 papers
- Allen InstituteUS11 papers
- California University of PennsylvaniaUS9 papers
- Stanford UniversityUS8 papers
- Hebrew University of JerusalemIL7 papers
- Microsoft (United States)US7 papers
- University of Illinois Urbana-ChampaignUS6 papers
- Cornell UniversityUS5 papers
- Google (United States)US5 papers
Showing 2018 · cs.CVShow all
3 papers · 2 filters
cs.CV2018★ 31 cited
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
Tianlu Wang, Jieyu Zhao, Mark Yatskar +2
In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that train…
cs.CV2018
Actor and Observer: Joint Modeling of First and Third-Person Videos
Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid +2
Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and se…
cs.CV2018★ 21 cited
ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks
Tae-Hoon Kim, Jonghyun Choi
We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called Screen…