| 摘要: |
| 从图像伴随文本中选择合适动词去描述图像中人物动作对于理解图像语义具有重要意义.现有方法通常学习得到表示图像人物和运动与其标注名词-动词之间概率的生成模型,然后使用这一得到的生成模型对训练集以外图像中人物运动进行识别.但是,这一方法忽略了图像中高维异构特征之间固有存在的组效应.实际上,不同类型异构特征在图像语义理解过程中具有不同区别性,例如手臂特征对人挥手这一动作最具有区别性.为了识别图像中人物运动进而对其进行标注,提出了通过Group LASSO 从高维异构姿势特征中选择最具区别性特征,最终学习得到生成模型的方法.实验结果表明,该方法对姿态变化较大动作进行识别时取得了更好结果. |
| 关键词: Group LASSO 生成模型 组效应动词标注 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.60833006, 61070068 (国家自然科学基金); the
China Postdoctoral Science Foundation under Grant No.20090451448; the National Key Technology R&D Program of China under Grant
No.2007BAH11B05; the Fundamental Research Funds for the Central Universities of China under Grant No.KYJD09008 |
|
| An Approach for Human and Motion Word Annotation with the Grouping Effect of Heterogeneous Features |
|
SHAO Jian, ZHAO Shi-Cong
|
|
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
|
| Abstract: |
| It is very important to select the most suitable motion words from surrounding text to describe the persons’ motion expressed in images during semantic understanding. Traditional approaches often learn a generative model to denote the occurrence probability between visual objects & motion and their corresponding annotated tags, and the learned model is then utilized to recognize persons’ actions in a new image outside training samples. However, all of existing approaches neglect the grouping effect of high-dimensional heterogeneous features inherent in images. In fact, different kinds of heterogeneous features have different intrinsic discriminative power for image understanding. For instance, the features extracted from arms are most discriminative to human waving motion. The selection of groups of discriminative features for motion recognition is hence crucial. In this paper, we propose an approach to select discriminative subgroup visual features from high-dimensional pose features by Group LASSO during the learning of generative model in order to boost the motion recognition. Experiments show that the proposed approach in this paper can obtain better performance for the recognition of motions with large pose change. |
| Key words: Group LASSO generative model group effect motion word annotation |
