Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition

By Zan Gao, Hua Zhang, Guangping Xu, Yanbing Xue. 2015

55 citations recorded by the source corpus.

Subfields: 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 Biomedical Engineering

1. Ioannis A. Kakadiaris
2. Christophoros Nikou
3. Michalis Vrigkas

In Computer Vision and Pattern Recognition

1. Ioannis A. Kakadiaris
2. Christophoros Nikou
3. Michalis Vrigkas
4. Michael J. Black
5. Ronald Poppe
6. Riccardo Satta

Citations in the corpus

• RGB-D-based action recognition datasets: A survey (2016, neutral): “ion [20] 98(insufficient illumination) &100(sufficient illumination) S 50 samples training, rest 100 test UPCV [32] DS-SRC+DTW dissimilarity on annotated UPCV [32] 89.25 S LOSubO 25 DHA [18] 1. MMJRR [87] 2. CHCRF [33] 3. DMPP PHOG [87] 4. DLRMPP PHOG [87] 1. 98.2 2. 95.9 3. 95 4. 95.6 1. C,D 2. C,D”
• A Review of Human Activity Recognition Methods (2015, background): “Low-cost devices, such as Microsoft Kinect and other RGB-D sensors, which provide 3D depth data of a scene, can efficiently leverage these limitations and produce a relatively good estimation of human pose, since they are robust to illumination changes and texture variations (Gao et al., 2015).”