Authors Vincent Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Re, Li Fei-Fei Our semi-supervised method automatically generates probabilistic relationship labels to train any scene graph model. Abstract Visual knowledge bases such as Visual Genome power numerous applications in computer vision, like visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene
A Taxonomy for VR
Eve Weston, CEO and founder of Los-Angeles based VR studio Exelauno told Stanford students that she has developed a way to talk about VR — what she calls a “taxonomy” for VR. This taxonomy unpacks the emotional intensity of the VR experience into its key parts: Narrative (1st person, 2nd person, 3rd person?) Visual Options (Embodied
Office Hours Announced for CJS Students
The Brown Institute is pleased to announce appointment-based office hours for students needing help in all things digital. This includes (but is not limited to) students seeking assistance with data and statistics, visualization, mapping, natural language processing, web products, immersive media, and the Adobe Creative Suite. Please book office hours at brwn.co/office-hours or by using
View-Dependent Video Textures for 360° Video
Authors Sean J. Liu, Maneesh Agrawala, Stephen DiVerdi, Aaron Hertzmann In 360◦ video, viewers can look anywhere at any time. In the opening scene of Invasion!, a rabbit emerges from a cave (a). In sequential playback, a viewer looking at the cave (green box) will see the rabbit emerge, whereas a viewer not looking at
Rethinking Audio @ Stanford with Google News
Rethinking Audio: Michael Mellody and Liz Gannes, Google News The rise of virtual assistants increasingly allows us to be informed, enlightened and entertained when our hands and eyes are busy. Demand is high: home assistants commanded a 40 percent year over year growth. Increasingly, people want news through these mediums, throughout the day – especially
AI-based Request Augmentation to Increase Crowdsourcing Participation
Authors Junwon Park, Ranjay Krishna, Pranav Khadpe, Li Fei-Fei, Michael Bernstein Abstract To support the massive data requirements of modern supervised machine learning (ML) algorithms, crowdsourcing systems match volunteer contributors to appropriate tasks. Such systems learn “what” types of tasks contributors are interested to complete. In this paper, instead of focusing on “what” to ask,
Stanford Welcomes Washington Post’s Director of Engineering
Stanford welcomed Jeremy Bowers, Director of Engineering, at The Washington Post. Bowers and his team are ramping up for the 2020 election, focusing on political data projects including election restyles, congressional votes and campaign finance. Bowers spoke on October 15 to an interdisciplinary group of Stanford students (compute science, engineering and business, among others). He
“Democracy Fighters” – Coverage in Mexican Media
On the evening of October 9, Alejandra Ibarra Chaoul unveiled her project “Democracy Fighters” at Casa Refugio Citlaltépetl in Mexico City. The launch event was picked up by news outlets in Mexico. Mexico City’s leading daily newspaper, La Jornada, posted a video, featuring an interview with Alejandra. “Defensores de la Democracia reúne el trabajo de
Stephanie Hankey of Tactical Tech Speaks at Columbia
On October 10, 2019, Brown at Columbia hosted Stephanie Hankey for its inaugural 2019-2020 Distinguished Lecture in Computational Innovation. Stephanie Hankey is a designer, technologist, and social entrepreneur who has worked internationally at the intersection of technology and human rights for the past 20 years. She is the co-founder and Executive Director of Tactical Tech,