213 citations · 963 across the 50 of their papers we have counts for
8 papers · 1 filter
Error Diagnosis of Deep Monocular Depth Estimation Models
Jagpreet Chawla, Nikhil Thakurdesai, Anuj Godase +3
Estimating depth from a monocular image is an ill-posed problem: when the camera projects a 3D scene onto a 2D plane, depth information is inherently and permanently lost. Neverthe…
Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
Zheng Chen, Zhengming Ding, David Crandall +1
Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments. In this work, we treat visual navigable space segmentation a…
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, Andrew Westbury, Eugene Byrne +82
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outd…
A Survey on Deep Learning Technique for Video Segmentation
Tianfei Zhou, Fatih Porikli, David Crandall +2
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects…
Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers
Satoshi Tsutsui, David Crandall, Chen Yu
We analyze egocentric views of attended objects from infants. This paper shows 1) empirical evidence that children's egocentric views have more diverse distributions compared to ad…
How to Accelerate Capsule Convolutions in Capsule Networks
Zhenhua Chen, Xiwen Li, Qian Lou +1
How to improve the efficiency of routing procedures in CapsNets has been studied a lot. However, the efficiency of capsule convolutions has largely been neglected. Capsule convolut…