Multi-layered gesture recognition with Kinect

By Feng Jiang, Shengping Zhang, Shen Wu, Yang Gao, Debin Zhao. 2015

102 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Human-Computer Interaction

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

1. Wanqing Li
2. Pichao Wang
3. Philip O. Ogunbona
4. Zhimin Gao
5. Chang-Fu Tang
6. Jun Wan
7. S. Li
8. Jian Cheng

In Developmental and Educational Psychology

1. Sergio Escalera
2. Isabelle M Guyon
3. Jun Wan
4. Vassilis Athitsos
5. Guo-qing Guo
6. S. Li
7. Liang Wang
8. Hongsong Wang

In Human-Computer Interaction

1. Pichao Wang
2. Wanqing Li
3. Philip O. Ogunbona
4. Zhimin Gao
5. Sergio Escalera
6. Jun Wan
7. Chang-Fu Tang
8. Shuai Zhou

Citations in the corpus

• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “quantity of movement (QOM) (Jiang et al., 2015), and then adopted improved DMM (IDMM) to encode the dynamics of depth sequences into texture images for large-scale continuous gesture recognition. To improve the encoding quality of depth sequences, Wang et al. (2018a) proposed three simple, compact y”
• EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition (2018, methodology): “Temporal pre-segmentation: this method is proposed in [38] which employs the quantity of movement (QOM) feature [39] to”
• Challenges in multimodal gesture recognition (2016, methodology): “The proposed method did not do as well as the previous methods (Konecny and Hagara, 2014; Wan et al., 2013; Jiang et al., 2015) on the CDG 2011 dataset, but nonetheless it contributes novel ideas for transfer learning, that can be useful when the number of training examples per class is limited.”
• Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition (2016, methodology): “As shown in Table 1 (see the fifth and sixth columns), temporal segmentation and gesture recognition are not done simultaneously in most of the published papers [9], [11], [16], [17], [20], [28], [29], [30], [37], [38].”
• Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “frames of each action is detected based on quantity of movement (QOM) [33] by assuming that all actions starts from a similar pose.”
• ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition (2016, methodology): “In the validation set, we correctly compute 2977 out of 4179 videos by the temporal segmentation method [12].”