摘要人体行为识别是计算机视觉领域的一个研究热点, 具有重要理论价值和现实意义. 近年来,
为了评价人体行为识别方法的性能, 大量的公开数据集被创建. 本文系统综述了人体行为识别 …

Anomaly detection is still a challenging task for video surveillance due to complex
environments and unpredictable human behaviors. Most existing approaches train offline …

Person re-identification (re-id) consists of associating individual across camera network,
which is valuable for intelligent video surveillance and has drawn wide attention. Although …

Understanding and defining the meaning of “action” is substantial for robotics research. This
becomes utterly evident when aiming at equipping autonomous robots with robust …

Various improved methods based on the strategy of bag of words (BoW) are widely used to
solve the problem of human action recognition. However, the spatial relationship between …

The massive amount of digital content generated daily in the modern world has created the
need for an image retrieval system built on image analysis via image processing and …

Motion video recognition has been well explored in applications of computer vision. In this
paper, we propose a novel video representation, which enhances motion recognition in …

针对颜色纹理特征结合单一分类器的传统识别方法对于多种黄瓜病害的识别精度较低的问题,
该文提出基于词袋特征PCA (principal component analysis) 多子空间自适应融合的黄瓜病害 …

In this paper, we present a novel two-layer video representation for human action
recognition employing hierarchical group sparse encoding technique and spatio-temporal …

This paper presents a novel and efficient framework for human action recognition through
integrating the local consistent group sparse representation with spatio-temporal structure of …