Detection of Activities and Events without Explicit Categorization

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a method of unsupervised event detection from a video that compares probability distributions of past and current video sequence data in a sequential and hierarchical way. Because estimation of probability distributions is known to be difficult, naively comparing probability distributions via probability distribution estimation tends to be unreliable in practice. To cope with this problem, we use the state-of-the-art machine learning technique called density ratio estimation: The ratio of probability densities is directly estimated without density estimation, and thus probability distributions can be compared in a reliable way. Through experiments on a walking scene and a tennis match, we demonstrate the usefulness of the proposed approach.

著者

• MATSUGU Masakazu

  Canon Inc.

• Sugiyama Masashi

  Graduate School of Information Science and Engineering, Tokyo Institute of Technology

• Yamanaka Masao

  Graduate School of Science and Engineering, Tokyo Institute of Technology

関連論文

• An Image-Filtering LSI Processor Architecture for Face/Object Recognition Using a Sorted Projection-Field Model Based on a Merged/Mixed Analog-Digital Architecture(Analog Circuit and Device Technologies)
• Subject independent facial expression recognition with robust face detection using a convolutional neural network
• SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations
• Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression
• SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations
• Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression
• Detection of Activities and Events without Explicit Categorization
• Salient Object Detection Based on Direct Density-ratio Estimation

スポンサーリンク