IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 424 citations · 57 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningAction RecognitionDimensionality ReductionFeature DetectionMulti-task LearningObject RecognitionRepresentation LearningActivity RecognitionHuman Activity RecognitionJoint Representation LearningMulti-task Feature LearningMulti-task Learning For Computer VisionMulti-task OptimizationMultitask LearningObject Interaction
In this paper, we focus on heterogeneous features learning for RGB-D activity recognition. We find that features from different channels (RGB, depth) could share some similar hidden structures, and then propose a joint learning model to simultaneously explore the shared and feature-specific components as an instance of heterogeneous multi-task learning. The proposed model formed in a unified framework is capable of: 1) jointly mining a set of subspaces with the same dimensionality to exploit latent shared features across different feature channels, 2) meanwhile, quantifying the shared and feature-specific components of features in the subspaces, and 3) transferring feature-specific intermediate transforms (i-transforms) for learning fusion of heterogeneous features across datasets. To efficiently train the joint model, a three-step iterative optimization algorithm is proposed, followed by a simple inference model. Extensive experimental results on four activity datasets have demonstrated the efficacy of the proposed method. A new RGB-D activity dataset focusing on human-object interaction is further contributed, which presents more challenges for RGB-D activity benchmarking.
57
Sinno Jialin Pan, Qiang Yang · IEEE Transactions on Knowledge and Data Engineering · 2009 · 23.2K citations
Real-time human pose recognition in parts from single depth images
Jamie Shotton, Andrew Fitzgibbon, Mat Cook et al. · 2011 · 3.5K citations
Action recognition by dense trajectories
Heng Wang, Alexander Kläser, Cordelia Schmid et al. · 2011 · 2.2K citations · Full text
Real-time human pose recognition in parts from single depth images
Jamie Shotton, Toby Sharp, Alex Kipman et al. · Communications of the ACM · 2013 · 2.1K citations