Convolutional Pose Machines
Autor: | Yaser Sheikh, Varun Ramakrishna, Shih-En Wei, Takeo Kanade |
---|---|
Rok vydání: | 2016 |
Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Inference 020207 software engineering Context (language use) 02 engineering and technology Machine learning computer.software_genre Task (project management) Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Graphical model Artificial intelligence Structured prediction business computer Pose |
Zdroj: | CVPR |
Popis: | Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets. Comment: camera ready |
Databáze: | OpenAIRE |
Externí odkaz: |