Human Motion Analysis with Deep Metric Learning
arXiv:1807.11176
Abstract
Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as L2 distance or Dynamic Time Warping based on hand-crafted local pose metrics fail to appropriately capture the semantic relationship across motions and, as such, are not suitable for being employed as metrics within these tasks. This work addresses this limitation by means of a triplet-based deep metric learning specifically tailored to deal with human motion data, in particular with the prob- lem of varying input size and computationally expensive hard negative mining due to motion pair alignment. Specifically, we propose (1) a novel metric learn- ing objective based on a triplet architecture and Maximum Mean Discrepancy; as well as, (2) a novel deep architecture based on attentive recurrent neural networks. One benefit of our objective function is that it enforces a better separation within the learned embedding space of the different motion categories by means of the associated distribution moments. At the same time, our attentive recurrent neural network allows processing varying input sizes to a fixed size of embedding while learning to focus on those motion parts that are semantically distinctive. Our ex- periments on two different datasets demonstrate significant improvements over conventional human motion metrics.
arXiv commentTo appear in ECCV 2018
References in corpus (13)
- A Structured Self-attentive Sentence Embedding
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Stacked Hourglass Networks for Human Pose Estimation
- Layer Normalization
- Generative Moment Matching Networks
- Working hard to know your neighbor's margins: Local descriptor learning loss
- A kernel for time series based on global alignments
- Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
- Multi-Context Attention for Human Pose Estimation
- Learning Feature Pyramids for Human Pose Estimation
- No Fuss Distance Metric Learning using Proxies
- Compositional Human Pose Regression
- Modeling Time Series Similarity with Siamese Recurrent Networks