We are pleased to announce that the team behind 1000 Cut Journey, which was awarded our 2018-19 Flagship Magic Grant, has partnered with acclaimed visual studio iNK Stories, to expand their Virtual Reality (VR) experience. The project is a bi-coastal initiative between Professor Courtney Cogburn’s research group at the Columbia University School of Social Work
Innovating with AI
Medium’s Chief Architect Xiao Ma spoke at Stanford on Nov. 5th asking the question: How does technology reshape content discovery and delivery? He unpacked Medium’s on-point recommendation system, a hybrid model that joins collaborative filtering (“How can we recommend content based on your previous history and people similar to you?”) and content-based filtering (“I don’t
Scene Graph Prediction with Limited Labels
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
Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
Authors Apoorva Dornadula, Austin Narcomey, Ranjay Krishna, Michael Bernstein, Li Fei-Fei We introduce a scene graph approach that formulates predicates as learned functions, which result in an embedding space for objects that is effective for few-shot. Our formulation treats predicates as learned semantic and spatial functions, which are trained within a graph convolution network. First,
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,