Human Motion Analysis With Deep Metric Learning
2018 · Huseyin Coskun, David Joseph Tan, Sailesh Conjeti, et al.
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
Authors
(none)
Tags
Stats
Related papers
- Deephums: Deep Human Motion Signature For 3D Skeletal Sequences (2019)2.26
- Deep Metric Learning Beyond Binary Supervision (2019)14.39
- Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
- Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
- Dynamic Sampling For Deep Metric Learning (2020)5.84
- Loop: Looking For Optimal Hard Negative Embeddings For Deep Metric Learning (2021)8.82
- Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
- SL-DML: Signal Level Deep Metric Learning For Multimodal One-shot Action Recognition (2020)11.29