Pose-based human action recognition via sparse representation in dissimilarity space
By Ilias Theodorakopoulos, Dimitris Kastaniotis, George Economou, Spiros Fotopoulos. 2014
105 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Wanqing Li
- Pichao Wang
- Philip O. Ogunbona
- Zhimin Gao
- Chang-Fu Tang
- Jing Zhang
- Michael Firman
- Ennio Gambi
In Biomedical Engineering
- Pichao Wang
- Wanqing Li
- Philip O. Ogunbona
- Zhimin Gao
- Chang-Fu Tang
- Ennio Gambi
- Susanna Spinsante
- Enea Cippitelli
In Computer Vision and Pattern Recognition
- Pichao Wang
- Wanqing Li
- Philip O. Ogunbona
- Zhimin Gao
- Chang-Fu Tang
- Ennio Gambi
- Susanna Spinsante
- Enea Cippitelli
Citations in the corpus
- RGB-D-based action recognition datasets: A survey (2016, methodology): “Falling Event [20] structure-motion [20] 98(insufficient illumination) &100(sufficient illumination) S 50 samples training, rest 100 test UPCV [32] DS-SRCþDTW dissimilarity on anno-”
- Mining Mid-Level Features for Action Recognition Based on Effective Skeleton Representation (2014, methodology): “[17] initially processed the skeleton data from sensor coordinate to torso PCA frame in order to gain robust and invariant pose representation.”
- Human Action Recognition From Various Data Modalities: A Review (2020, unknown): “Dataset Year Modality #Class #Subject #Sample #Viewpoint KTH [380] 2004 RGB 6 25 2,391 1 Weizmann [41] 2005 RGB 10 9 90 1 IXMAS [381] 2006 RGB 11 10 330 5 HDM05 [382] 2007 RGB,S 130 5 2,337 1 Hollywood [383] 2008 RGB 8 - 430 Hollywood2 [384] 2009 RGB 12 - 3,669 MSR-Action3D [239] 2010 S,D 20 10 567 ”
- RGBD Datasets: Past, Present and Future (2016, background): “UPCV action dataset [100] 20 10 400 X e.”
- A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, methodology): “For each test conducted on KARD dataset, the sequence of clusters K = [3, 5, 10, 15, 20, 25, 30, 35] has been considered.”
- A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, unknown): “Regarding the experimentation method used by many authors working with the MSR Action3D dataset, it is worth to mention that there is a lack of agreement.”