Human Action Recognition Across Datasets by Foreground-weighted Histogram Decomposition

CVPR 2014  ·  Waqas Sultani, Imran Saleemi ·

This paper attempts to address the problem of recognizing human actions while training and testing on distinct datasets, when test videos are neither labeled nor available during training. In this scenario, learning of a joint vocabulary, or domain transfer techniques are not applicable. We first explore reasons for poor classifier performance when tested on novel datasets, and quantify the effect of scene backgrounds on action representations and recognition. Using only the background features and partitioning of gist feature space, we show that the background scenes in recent datasets are quite discriminative and can be used classify an action with reasonable accuracy. We then propose a new process to obtain a measure of confidence in each pixel of the video being a foreground region, using motion, appearance, and saliency together in a 3D MRF based framework. We also propose multiple ways to exploit the foreground confidence: to improve bag-of-words vocabulary, histogram representation of a video, and a novel histogram decomposition based representation and kernel. We used these foreground confidences to recognize actions trained on one data set and test on a different data set. We have performed extensive experiments on several datasets that improve cross dataset recognition accuracy as compared to baseline methods.

PDF Abstract

Datasets


Results from the Paper


Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Domain Adaptation HMDBsmall-to-UCF W. Sultani et al. Accuracy 68.67 # 3
Domain Adaptation Olympic-to-HMDBsmall W. Sultani et al. Accuracy 47.91 # 3
Domain Adaptation UCF-to-HMDBsmall W. Sultani et al. Accuracy 68.70 # 3
Domain Adaptation UCF-to-Olympic W. Sultani et al. Accuracy 33.33 # 3

Methods


No methods listed for this paper. Add relevant methods here