Event Recognition in Videos by Learning from Heterogeneous Web Sources
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2666-2673
- https://doi.org/10.1109/cvpr.2013.344
Abstract
In this work, we propose to leverage a large number of loosely labeled web videos (e.g., from YouTube) and web images (e.g., from Google/Bing image search) for visual event recognition in consumer videos without requiring any labeled consumer videos. We formulate this task as a new multi-domain adaptation problem with heterogeneous sources, in which the samples from different source domains can be represented by different types of features with different dimensions (e.g., the SIFT features from web images and space-time (ST) features from web videos) while the target domain samples have all types of features. To effectively cope with the heterogeneous sources where some source domains are more relevant to the target domain, we propose a new method called Multi-domain Adaptation with Heterogeneous Sources (MDA-HS) to learn an optimal target classifier, in which we simultaneously seek the optimal weights for different source domains with different types of features as well as infer the labels of unlabeled target domain data based on multiple types of features. We solve our optimization problem by using the cutting-plane algorithm based on group based multiple kernel learning. Comprehensive experiments on two datasets demonstrate the effectiveness of MDA-HS for event recognition in consumer videos.Keywords
This publication has 21 references indexed in Scilit:
- Web-Based Classifiers for Human Action RecognitionIEEE Transactions on Multimedia, 2012
- Healing Sample Selection Bias by Source Classifier SelectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Domain adaptation for object recognition: An unsupervised approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Text-based image retrieval using progressive multi-instance learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Multi-view transfer learning with a large margin approachPublished by Association for Computing Machinery (ACM) ,2011
- What you saw is not what you get: Domain adaptation using asymmetric kernel transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Consumer video understandingPublished by Association for Computing Machinery (ACM) ,2011
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Space-time interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The Cutting-Plane Method for Solving Convex ProgramsJournal of the Society for Industrial and Applied Mathematics, 1960