File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
Title | PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation |
---|---|
Authors | |
Issue Date | 2022 |
Publisher | Ortra Ltd. |
Citation | European Conference on Computer Vision (Hybrid), Tel Aviv, Israel, October 23-27, 2022. In Proceedings of the European Conference on Computer Vision (ECCV), 2022 How to Cite? |
Abstract | Human pose estimation aims to accurately estimate a wide variety of human poses. However, existing datasets often follow a long-tailed distribution that unusual poses only occupy a small portion, which further leads to the lack of diversity of rare poses. These issues result in the inferior generalization ability of current pose estimators. In this paper, we present a simple yet effective data augmentation method, termed Pose Transformation (PoseTrans), to alleviate the aforementioned problems. Specifically, we propose Pose Transformation Module (PTM) to create new training samples that have diverse poses and adopt a pose discriminator to ensure the plausibility of the augmented poses. Besides, we propose Pose Clustering Module (PCM) to measure the pose rarity and select the 'rarest' poses to help balance the long-tailed distribution. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method, especially on rare poses. Also, our method is efficient and simple to implement, which can be easily integrated into the training pipeline of existing pose estimation models. |
Persistent Identifier | http://hdl.handle.net/10722/315556 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jiang, W | - |
dc.contributor.author | Jin, S | - |
dc.contributor.author | Liu, W | - |
dc.contributor.author | Qian, C | - |
dc.contributor.author | Luo, P | - |
dc.contributor.author | Liu, S | - |
dc.date.accessioned | 2022-08-19T09:00:05Z | - |
dc.date.available | 2022-08-19T09:00:05Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | European Conference on Computer Vision (Hybrid), Tel Aviv, Israel, October 23-27, 2022. In Proceedings of the European Conference on Computer Vision (ECCV), 2022 | - |
dc.identifier.uri | http://hdl.handle.net/10722/315556 | - |
dc.description.abstract | Human pose estimation aims to accurately estimate a wide variety of human poses. However, existing datasets often follow a long-tailed distribution that unusual poses only occupy a small portion, which further leads to the lack of diversity of rare poses. These issues result in the inferior generalization ability of current pose estimators. In this paper, we present a simple yet effective data augmentation method, termed Pose Transformation (PoseTrans), to alleviate the aforementioned problems. Specifically, we propose Pose Transformation Module (PTM) to create new training samples that have diverse poses and adopt a pose discriminator to ensure the plausibility of the augmented poses. Besides, we propose Pose Clustering Module (PCM) to measure the pose rarity and select the 'rarest' poses to help balance the long-tailed distribution. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method, especially on rare poses. Also, our method is efficient and simple to implement, which can be easily integrated into the training pipeline of existing pose estimation models. | - |
dc.language | eng | - |
dc.publisher | Ortra Ltd. | - |
dc.relation.ispartof | Proceedings of the European Conference on Computer Vision (ECCV), 2022 | - |
dc.title | PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.doi | 10.48550/arXiv.2208.07755 | - |
dc.identifier.hkuros | 335608 | - |
dc.publisher.place | Israel | - |