2014 · 73 citations · 27 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionAction RecognitionMotion AnalysisMotion EstimationRepresentation LearningScene UnderstandingVideo AnalysisActivity RecognitionCross-dataset Action RecognitionCross-dataset ValidationCross-domain TransferHistogram AnalysisHuman ActionVideo Action Recognition
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.
27
HMDB: A large video database for human motion recognition
Hilde Kuehne, Hueihan Jhuang, Estíbaliz Garrote et al. · 2011 · 3.9K citations · Full text
Learning realistic human actions from movies
Ivan Laptev, Marcin Marszałek, Cordelia Schmid et al. · 2008 · 3.5K citations · Full text
Recognizing human actions: A local SVM approach
2004 · 2.9K citations