Double-layer conditional random fields model for human action recognition
作者：
Highlights：
• We formulate a double-layer conditional random fields model with higher order dependencies augmented top layer and intermediate variable representations embedded bottom layer for action recognition task.
• We derive an efficient and exact model inference technique in our designed graph, which can be decomposed into the top linear-chain CRF model and the bottom linear-chain CRF one to be resolved efficiently using dynamic programming approach.
• We suggest that the block-coordinate primal–dual Frank–Wolfe (BCFW) optimization with gap sampling approach be employed to learn effectively and efficiently the assumed DL- CRFs model parameters in a structured support vector machine framework.
摘要
•We formulate a double-layer conditional random fields model with higher order dependencies augmented top layer and intermediate variable representations embedded bottom layer for action recognition task.•We derive an efficient and exact model inference technique in our designed graph, which can be decomposed into the top linear-chain CRF model and the bottom linear-chain CRF one to be resolved efficiently using dynamic programming approach.•We suggest that the block-coordinate primal–dual Frank–Wolfe (BCFW) optimization with gap sampling approach be employed to learn effectively and efficiently the assumed DL- CRFs model parameters in a structured support vector machine framework.
论文关键词：Action recognition,Double-layer CRFs,Graphical model,RGB-D video,Structured SVM
论文评审过程：Received 29 January 2019, Revised 19 October 2019, Accepted 19 October 2019, Available online 25 October 2019, Version of Record 5 November 2019.
论文官网地址：https://doi.org/10.1016/j.image.2019.115672
