Not stated in source
2018 Needs review
Learning Interaction Grammar for Action Recognition
Abstract
Video action recognition has been in the center of the stage since its introduction in 2004 [SLC04]. During the past 15 years, countless methods had been proposed to understand what human is doing in a video clip. While some works infer action label directly from pixel information, some other works propose to learn multi-level hierarchical structure that composes actions. In this work, we propose the learning of a two-layer grammar model for action recognition that is based on human object interaction. To evaluate the idea, we proposed an interaction grammar for action recognition on video. The model is evaluated by simulated annealing with MCMC and by deep learning.
Keywords
Not available
Specialisations
Similar theses
- Action recognition in videos using deep learning Shiyu Li · Nanyang Technological University · 2026
- Privacy Motivated Models for Deep Learning-based Human Action Recognition in Intelligent Video Surveillance Mickael Willy Jacky Cormier · Karlsruhe Institute of Technology · 2026
- Applied deep learning for human action recognition in video surveillance, healthcare monitoring, and robotics Thean Chun Koh · Nanyang Technological University · 2025
- Multimodal Deep Learning for Zero-Shot Action Recognition Nan WU · 2024
- Deep Learning Methods for Human Action Recognition Zeqi Yu · Auckland University of Technology · 2021
- Robust and efficient deep learning methods for vision-based action recognition Yuecong Xu · Nanyang Technological University · 2021
