About: Training Physical and Geometrical Mid-Points for Multi-person Pose Estimation and Human Detection Under Congestion and Low Resolution

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Training Physical and Geometrical Mid-Points for Multi-person Pose Estimation and Human Detection Under Congestion and Low Resolution Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Training Physical and Geometrical Mid-Points for Multi-person Pose Estimation and Human Detection Under Congestion and Low Resolution
Creator	Ikeda, Hiroo Kawai, Ryo Nishimura, Shoji Pan, Yadong Yoshida, Noboru
Source	PMC
abstract	This paper introduces the design and evaluation of NeoPose which is developed for multi-person pose estimation and human detection. The design of NeoPose is targeting the issue of human detection under congested situation and with low resolution in the image. Under such situations, we compared the performance of different versions of NeoPose as well as other existing algorithms in a human detection task. Throughout the task, the usefulness of two kinds of mid-point (physical and geometrical mid-points) and a deconvolution structure was discussed. Experiment results indicated that NeoPose which applied geometrical mid-points and deconvolution structure performed the best in terms of both precision and recall in the evaluation.
has issue date	2020-06-21(xsd:dateTime)
bibo:doi	10.1007/s42979-020-00217-9
has license	no-cc
sha1sum (hex)	60f65cfa28baec240b3d63e9e88272a768327d64
schema:url	https://doi.org/10.1007/s42979-020-00217-9
resource representing a document's title	Training Physical and Geometrical Mid-Points for Multi-person Pose Estimation and Human Detection Under Congestion and Low Resolution
has PubMed Central identifier	PMC7306187
schema:publication	SN COMPUT
resource representing a document's body	covid:60f65cfa28baec240b3d63e9e88272a768327d64#body_text
is schema:about of	named entity 'human' named entity 'detection' named entity 'geometrical' named entity 'Geometrical' named entity 'USEFULNESS' named entity 'DIFFERENT' named entity 'human' named entity 'congested' named entity 'deconvolution' named entity 'evaluation' named entity 'kinds' named entity 'performed' named entity 'deconvolution' named entity 'Pose Estimation' named entity 'false positive' named entity 'low resolution' named entity 'surface integral' named entity 'image resolution' named entity 'vector' named entity 'PAF' named entity 'human-computer interface' named entity 'deep neural network' named entity 'up-sampling' named entity 'ellipse' named entity 'neural network' named entity 'deconvolution' named entity 'human body' named entity 'MHP' named entity 'human body' named entity 'NEC' named entity 'vector' named entity 'pixels' named entity 'correlation' named entity 'pixels' named entity 'deconvolution' named entity 'vector' named entity 'vector' named entity 'vector' named entity 'deconvolution' named entity 'autonomous driving' named entity 'University of Tsukuba' named entity 'ellipse' named entity 'ground truth' named entity 'Japan' named entity 'NEC' named entity 'PAF' named entity 'vectors' named entity 'pose estimation' named entity 'deep neural network' named entity 'Prof.' named entity 'NEC' named entity 'Associative' named entity 'deconvolution' named entity 'ellipse' named entity 'deep network' named entity 'deconvolution' named entity 'False positive' named entity 'pose estimation' named entity 'correlation' named entity 'correlation' named entity 'low resolution' named entity 'image resolution' named entity 'covid-19' named entity 'pose estimation' named entity 'image resolution' named entity 'image sensing' named entity 'deep neural network' named entity 'Pose estimation' named entity 'ground truth' named entity 'behavior analysis' named entity 'image resolution' named entity 'low resolution' named entity 'human body' named entity 'human body' named entity 'deep neural network' named entity 'NEC' named entity 'pose estimation' named entity 'Associative' named entity 'precision and recall'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software