---
title: "Human Activity Encoding and Recognition Using Low-level Visual Features"
authors:
  - "Zheshen Wang"
  - "Baoxin Li"
doi: ""
url: "https://ijcai.org/proceedings/2009/311"
pdf: "https://ijcai.org/proceedings/2009/0311.pdf"
venue: "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"
year: 2009
pages: "1876-1882"
track: ""
keywords:
---

# Human Activity Encoding and Recognition Using Low-level Visual Features

Zheshen Wang, Baoxin Li

*Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence*, pages 1876-1882.

## Abstract

Automatic recognition of human activities is among the key capabilities of many intelligent systems with vision/perception. Most existing approaches to this problem require sophisticated feature extraction before classification can be performed. This paper presents a novel approach for human action recognition using only simple low-level visual features: motion captured from direct frame differencing. A codebook of key poses is first created from the training data through unsupervised clustering. Videos of actions are then coded as sequences of super-frames, defined as the key poses augmented with discriminative attributes. A weighted-sequence distance is proposed for comparing two super-frame sequences, which is further wrapped as a kernel embedded in a SVM classifier for the final classification. Compared with conventional methods, our approach provides a flexible non-parametric sequential structure with a corresponding distance measure for human action representation and classification without requiring complex feature extraction. The effectiveness of our approach is demonstrated with the widely-used KTH human activity dataset, for which the proposed method outperforms the existing state-of-the-art.Zheshen Wang, Baoxin Li