Recognising Human-Object Interaction via Exemplar Based Modelling
Authors:
- Jian-Fang HuJHJian-Fang Hu
- Wei-Shi ZhengWZWei-Shi Zheng
- Jianhuang LaiJLJianhuang Lai
- Shaogang GongSGShaogang Gong
- Tao XiangTXTao Xiang
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 3144-3151
Abstract
Human action can be recognised from a single still image by modelling Human-object interaction (HOI), which infers the mutual spatial structure information between human and object as well as their appearance. Existing approaches rely heavily on accurate detection of human and object, and estimation of human pose. They are thus sensitive to large variations of human poses, occlusion and unsatisfactory detection of small size objects. To overcome this limitation, a novel exemplar based approach is proposed in this work. Our approach learns a set of spatial pose-object interaction exemplars, which are density functions describing how a person is interacting with a manipulated object for different activities spatially in a probabilistic way. A representation based on our HOI exemplar thus has great potential for being robust to the errors in human/object detection and pose estimation. A new framework consists of a proposed exemplar based HOI descriptor and an activity specific matching model that learns the parameters is formulated for robust human activity recognition. Experiments on two benchmark activity datasets demonstrate that the proposed approach obtains state-of-the-art performance.Keywords
This publication has 23 references indexed in Scilit:
- Explicit Modeling of Human-Object Interactions in Realistic VideosIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- A database for fine grained activity detection of cooking activities2012
- Discriminative spatial saliency for image classification2012
- Ensemble of exemplar-SVMs for object detection and beyond2011
- Action recognition from a distributed representation of pose and appearance2011
- Recognition using visual phrases2011
- Visual object-action recognition: Inferring object affordances from human demonstrationComputer Vision and Image Understanding, 2011
- Grouplet: A structured image representation for recognizing human and object interactions2010
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Recovering 3D human body configurations using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006