2013 · 35 citations · 26 references
ComputingComputer ScienceComputer VisionMachine VisionRobot VisionAction RecognitionAction RepresentationMulti-task LearningPose EstimationScene UnderstandingCross-view Action RecognitionJoint Representation LearningLatent LearningMulti-task Learning For Computer VisionMultitask LearningViews
This paper presents an approach to view-invariant action recognition, where human poses and motions exhibit large variations across different camera viewpoints. When each viewpoint of a given set of action classes is specified as a learning task then multitask learning appears suitable for achieving view invariance in recognition. We extend the standard multitask learning to allow identifying: (1) latent groupings of action views (i.e., tasks), and (2) discriminative action parts, along with joint learning of all tasks. This is because it seems reasonable to expect that certain distinct views are more correlated than some others, and thus identifying correlated views could improve recognition. Also, part-based modeling is expected to improve robustness against self-occlusion when actors are imaged from different views. Results on the benchmark datasets show that we outperform standard multitask learning by 21.9%, and the state-of-the-art alternatives by 4.5-6%.
26
Rich Caruana · Machine Learning · 1997 · 6.3K citations · Full text
Action recognition by dense trajectories
Heng Wang, Alexander Kläser, Cordelia Schmid et al. · 2011 · 2.2K citations · Full text
Mining actionlet ensemble for action recognition with depth cameras
Jiang Wang, Zicheng Liu, Ying Wu et al. · 2012 · 1.6K citations · Full text
Convex multi-task feature learning
Andreas A. Argyriou, Theodoros Evgeniou, Massimiliano Pontil · Machine Learning · 2008 · 1.4K citations · Full text