Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification
| Autor: | Arash Vahdat, Kevin Cannons, Nataliya Shapovalova, Greg Mori, Tian Lan |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
business.industry
Pattern recognition Latent variable DUAL (cognitive architecture) Machine learning computer.software_genre Class (biology) Support vector machine ComputingMethodologies_PATTERNRECOGNITION Discriminative model Action (philosophy) Region of interest Similarity (psychology) Artificial intelligence business computer Mathematics |
| Zdroj: | Computer Vision – ECCV 2012 ISBN: 9783642337857 ECCV (7) |
| DOI: | 10.1007/978-3-642-33786-4_5 |
| Popis: | We present a novel algorithm for weakly supervised action classification in videos. We assume we are given training videos annotated only with action class labels. We learn a model that can classify unseen test videos, as well as localize a region of interest in the video that captures the discriminative essence of the action class. A novel Similarity Constrained Latent Support Vector Machine model is developed to operationalize this goal. This model specifies that videos should be classified correctly, and that the latent regions of interest chosen should be coherent over videos of an action class. The resulting learning problem is challenging, and we show how dual decomposition can be employed to render it tractable. Experimental results demonstrate the efficacy of the method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|