Human Activity Recognition with Metric Learning

This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We show that our approach outperforms all state-of-the-art methods on numerous standard datasets for traditional action classification problem. Furthermore, we demonstrate that our method not only can accurately label activities but also can reject unseen activities and can learn from few examples with high accuracy. We finally show that our approach works well on noisy YouTube videos.

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Du Tran, Alexander Sorokin
• Keywords: Action Classification Problem, Computer Vision, ECCV 2008, Learning Based Approach, Noisy Youtube Videos, Numerous Standard Datasets, Reject Unfamiliar Activities