Publications

January 1, 2020

Ethics in Design and Communication

Virtual Reality (VR) designers accept the ethical responsibilities of removing a user’s entire world and superseding it with a fabricated reality. These unique immersive design challenges are intensified when virtual experiences become public and socially-driven. As female VR designers in 2018, we see an opportunity to fold the language of consent into the design practice of virtual reality—as a means to design safe, accessible, virtual spaces.

Publication will be made available in 2020.

Areas: AR/VR Human Computer Interaction & UX

June 18, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task – Embodied Question Answering [1] in photo-realistic environments (Matterport 3D).

Areas: Computer Vision Facebook AI Research Machine Learning

June 17, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation.

Areas: Computer Vision Facebook AI Research Machine Learning

June 17, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

Globally modeling and reasoning over relations between regions can be beneficial for many computer vision tasks on both images and videos. Convolutional Neural Networks (CNNs) excel at modeling local relations by convolution operations, but they are typically inefficient at capturing global relations between distant regions and require stacking multiple convolution layers. In this work, we propose a new approach for reasoning globally in which a set of features are globally aggregated over the coordinate space and then projected to an interaction space where relational reasoning can be efficiently computed.

Areas: Computer Vision Facebook AI Research Machine Learning

June 17, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

Areas: Computer Vision Facebook AI Research

June 17, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

We propose and study a task we name panoptic segmentation (PS). Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance). The proposed task requires generating a coherent scene segmentation that is rich and complete, an important step toward real-world vision systems.

Areas: Connectivity Facebook AI Research

June 16, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints.

Areas: Computer Vision

June 16, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today’s VQA models can not read! Our paper takes a first step towards addressing this problem.

Areas: Computer Vision Facebook AI Research Natural Language Processing & Speech

June 16, 2019

CVPR Precognition Workshop

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper we focus on anticipating actions seconds before they start. Our proposed approach is the fusion of a purely anticipatory model with a complementary model constrained to reason about the present.

Areas: Computer Vision Machine Learning

June 16, 2019

Conference Computer Vision and Pattern Recognition (CVPR)

Ideally, 360◦ imagery could inherit the deep convolutional neural networks (CNNs) already trained with great success on perspective projection images. However, existing methods to transfer CNNs from perspective to spherical images introduce significant computational costs and/or degradations in accuracy. We present the Kernel Transformer Network (KTN) to efficiently transfer convolution kernels from perspective images to the equirectangular projection of 360◦ images.

Areas: Computer Vision