.png){kind=icon}
返回
Vision-language model guided pose knowledge mining for human pose estimation
.png){kind=icon}
OA
AI
DOI：10.1093/jcde/qwaf079.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Vision-language models with large-scale image-text pairs have shown significant potential on representation learning. Human pose estimation task, which is highly sensitive to pixel-wise transformation, requires effective methods for mining pose-specific knowledge. In this paper, we investigate the homologous human pose retrieval task relying on large-scale annotated datasets to enhance pose knowledge extraction. We propose Pose Prompt (PosePro), which leverages vision-language models to categorize global pose configuration of an image, build compatible design, generate pose embedding as proposals. We then aim to integrate the learned knowledge as visual and textual prompt to facilitate the learning processing of newly unseen tasks. We demonstrate the effectiveness of fundamental PosePro model through extensive experiments on both pose retrieval and human pose estimation, showing significant improvements in accuracy and generalization ability, especially in scenarios with limited samples.
Keyword:
vision-language model
human pose estimation
knowledge
transfer learning
generalization
期刊
IF:
6.1
论文数:
406
被引数:
3.2K
机构
引用论文
Knowledge graph-based multi-granularity tacit design knowledge reuse for product design基于知识图谱的多粒度隐性设计知识重用研究OAAI
OAAI分享收藏Structure-aware human pose estimation with graph convolutional networks基于图卷积网络的结构感知人体姿态估计.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Boosting integral-based human pose estimation through implicit heatmap learning基于隐式热图学习的Boosting基于积分的人体姿态估计NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏SD-Pose: facilitating space-decoupled human pose estimation via adaptive pose perception guidanceSd-pose: 通过自适应姿态感知指导促进空间解耦的人体姿态估计MULTIMEDIA SYSTEMS
MULTIMEDIA SYSTEMSIF3.1
PREAI
分享收藏 没有更多内容
没有更多内容