-
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions from Single Panoramas [Abstract]
-
CAHIR: Co-Attentive Hierarchical Image Representations for Visual Place Recognition [Abstract]
-
Monocular Visual-Inertial Depth Estimation [Abstract]
-
KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation [Abstract]
-
Online Consistent Video Depth with Gaussian Mixture Representation [Abstract]
-
Deep Masked Graph Matching for Correspondence Identification in Collaborative Perception [Abstract]
-
Operative Action Captioning for Estimating System Actions [Abstract]
-
Deep Unsupervised Visual Odometry Via Bundle Adjusted Pose Graph Optimization [Abstract]
-
Pose Relation Transformer : Refine Occlusions for Human Pose Estimation [Abstract]
-
Question Generation for Uncertainty Elimination of Referring Expression in 3D Environment [Abstract]
-
A New Efficient Eye Gaze Tracker for Robotic Applications [Abstract]
-
A Deep Learning Human Activity Recognition Framework for Socially Assistive Robots to Support Reablement of Older Adults [Abstract]