Title
Joint Human Detection and Head Pose Estimation via Multistream Networks for RGB-D Videos.
Abstract
We propose a multistream multitask deep network for joint human detection and head pose estimation in RGB-D videos. To achieve high accuracy, we jointly utilize appearance, shape, and motion information as inputs. Based on the depth information, we generate scale invariant proposals, which are then fed into a novel contextual region of interest pooling (CRP) layer in our deep network. This CRP has...
Year
DOI
Venue
2017
10.1109/LSP.2017.2731952
IEEE Signal Processing Letters
Keywords
Field
DocType
Head,Proposals,Pose estimation,Shape,Videos,Machine learning,Clothing
Computer vision,Contextual information,Pattern recognition,Pooling,Pose,RGB color model,Artificial intelligence,Region of interest,Mathematics
Journal
Volume
Issue
ISSN
24
11
1070-9908
Citations 
PageRank 
References 
7
0.47
32
Authors
5
Name
Order
Citations
PageRank
Guyue Zhang1423.15
Jun Liu267130.44
Hengduo Li3104.23
Yan Qiu Chen446053.35
Larry S. Davis5142012690.83