From Human Pose Similarity Metric to 3D Human Pose Estimator : Temporal Propagating LSTM Networks

Predicting a 3D pose directly from a monocular image is a challenging problem. Most pose estimation methods proposed in recent years have shown 'quantitatively' good results (below  ∼ 50mm). However, these methods remain 'perceptually' flawed because their performance is only mea...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 2 vom: 01. Feb., Seite 1781-1797
Auteur principal: Lee, Kyoungoh (Auteur)
Autres auteurs: Kim, Woojae, Lee, Sanghoon
Format: Article en ligne
Langue:English
Publié: 2023
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000caa a22002652c 4500
001 NLM339076925
003 DE-627
005 20250303053214.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2022.3164344  |2 doi 
028 5 2 |a pubmed25n1130.xml 
035 |a (DE-627)NLM339076925 
035 |a (NLM)35377839 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Lee, Kyoungoh  |e verfasserin  |4 aut 
245 1 0 |a From Human Pose Similarity Metric to 3D Human Pose Estimator  |b Temporal Propagating LSTM Networks 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 07.04.2023 
500 |a Date Revised 05.05.2023 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a Predicting a 3D pose directly from a monocular image is a challenging problem. Most pose estimation methods proposed in recent years have shown 'quantitatively' good results (below  ∼ 50mm). However, these methods remain 'perceptually' flawed because their performance is only measured via a simple distance metric. Although this fact is well understood, the reliance on 'quantitative' information implies that the development of 3D pose estimation methods has been slowed down. To address this issue, we first propose a perceptual Pose SIMilarity (PSIM) metric, by assuming that human perception (HP) is highly adapted to extracting structural information from a given signal. Second, we present a perceptually robust 3D pose estimation framework: Temporal Propagating Long Short-Term Memory networks (TP-LSTMs). Toward this, we analyze the information-theory-based spatio-temporal posture correlations, including joint interdependency, temporal consistency, and HP. The experimental results clearly show that the proposed PSIM metric achieves a superior correlation with users' subjective opinions than conventional pose metrics. Furthermore, we demonstrate the significant quantitative and perceptual performance improvements of TP-LSTMs compared to existing state-of-the-art methods 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Kim, Woojae  |e verfasserin  |4 aut 
700 1 |a Lee, Sanghoon  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 2 vom: 01. Feb., Seite 1781-1797  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:45  |g year:2023  |g number:2  |g day:01  |g month:02  |g pages:1781-1797 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2022.3164344  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 2  |b 01  |c 02  |h 1781-1797