Self-supervised learning for multi-person pose estimation and tracking in videos

Self-supervised learning in video involves learning representations without using high-cost labels, which allows us to utilise the vast amount of free unlabelled videos available. As videos are particularly rich in spatio-temporal information, the representations learnt are useful in many downstrea...

Full description

Saved in:

Bibliographic Details
Main Author:	Tan, Jia Min
Other Authors:	Li Boyang
Format:	Student Research Poster
Language:	English
Published:	Nanyang Technological University 2023
Subjects:	Engineering::Computer science and engineering
Online Access:	https://hdl.handle.net/10356/170731
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-170731
record_format	dspace
spelling	sg-ntu-dr.10356-1707312023-10-02T15:39:03Z Self-supervised learning for multi-person pose estimation and tracking in videos Tan, Jia Min Li Boyang School of Computer Science and Engineering boyang.li@ntu.edu.sg Engineering::Computer science and engineering Self-supervised learning in video involves learning representations without using high-cost labels, which allows us to utilise the vast amount of free unlabelled videos available. As videos are particularly rich in spatio-temporal information, the representations learnt are useful in many downstream tasks (action recognition, pose tracking etc.) 2023-09-27T13:20:32Z 2023-09-27T13:20:32Z 2022 Student Research Poster Tan, J. M. (2022). Self-supervised learning for multi-person pose estimation and tracking in videos. Student Research Poster, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/170731 https://hdl.handle.net/10356/170731 en SCSE20133 © 2022 The Author(s). application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering
spellingShingle	Engineering::Computer science and engineering Tan, Jia Min Self-supervised learning for multi-person pose estimation and tracking in videos
description	Self-supervised learning in video involves learning representations without using high-cost labels, which allows us to utilise the vast amount of free unlabelled videos available. As videos are particularly rich in spatio-temporal information, the representations learnt are useful in many downstream tasks (action recognition, pose tracking etc.)
author2	Li Boyang
author_facet	Li Boyang Tan, Jia Min
format	Student Research Poster
author	Tan, Jia Min
author_sort	Tan, Jia Min
title	Self-supervised learning for multi-person pose estimation and tracking in videos
title_short	Self-supervised learning for multi-person pose estimation and tracking in videos
title_full	Self-supervised learning for multi-person pose estimation and tracking in videos
title_fullStr	Self-supervised learning for multi-person pose estimation and tracking in videos
title_full_unstemmed	Self-supervised learning for multi-person pose estimation and tracking in videos
title_sort	self-supervised learning for multi-person pose estimation and tracking in videos
publisher	Nanyang Technological University
publishDate	2023
url	https://hdl.handle.net/10356/170731
_version_	1779156369072455680

Self-supervised learning for multi-person pose estimation and tracking in videos

Similar Items