Explore Efficient Local Features from RGB-D Data for One-Shot Learning Gesture Recognition

By Jun Wan, Guo-qing Guo, S. Li. 2016

102 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Meta & Continual Learning, 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 Biomedical Engineering

1. Wanqing Li
2. Pichao Wang
3. Philip O. Ogunbona
4. G. Wang
5. Jun Liu
6. Zhimin Gao
7. Alex ChiChung Kot
8. Ling-yu Duan

In Computer Vision and Pattern Recognition

1. Wanqing Li
2. Jun Liu
3. Pichao Wang
4. G. Wang
5. Philip O. Ogunbona
6. Zhimin Gao
7. Alex ChiChung Kot
8. Amir Shahroudy

In Meta & Continual Learning

1. Shuai Zhou
2. Xiaoyuan Guo
3. Jiali Duan
4. Wanqing Li
5. Pichao Wang
6. Zhimin Gao
7. Jun Wan
8. S. Li

In Human-Computer Interaction

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

Citations in the corpus

• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Wan et al. [91] extracted mixed features around the sparse keypoints that are robust to scale, rotation and partial occlusions.”
• Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, neutral): “Table 1 shows the results of six variants of SFAM, and compares them with methods in the literature [45, 46, 1, 52].”
• Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “Method Set Mean Jaccard Index JS MFSK [58] Validation 0.”
• Two streams Recurrent Neural Networks for Large-Scale Continuous Gesture Recognition (2016, background): “MFSK and MFSK+DeepID utilize mixed features around sparse keypoints (MFSK) [34] and Deep hidden IDentity (Deep ID) features [35].”
• Large-scale Isolated Gesture Recognition using pyramidal 3D convolutional networks (2016, methodology): “b The results of the method [2] are reported by the organizer in [7].”
• ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition (2016, methodology): “The results of all the top 14 results [9, 23] on the challenging subsets of CGD, such as translated and scaled data.”
• ChaLearn looking at people: A review of events and resources (2017, background): “A total of 17 papers were published withiin this Special Issue at IEEE TPAMI [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47].”
• Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition (2016, methodology): “On ChaLearn IsoGD, hand-crafted features such as MFSK [34] as well as its variant which combines DeepID feature [36] scores relatively low compared to deep learning based methods such as AMRL [22] which incorporates three representations DDI, DDNI and DDMNI based on bidirectional rank pooling and…”
• Structured Images for RGB-D Action Recognition (2017, unknown): “63% MFSK+BoVW [33] 95.”
• EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition (2018, methodology): “tories (iDT) [24] in RGB channels, Super Normal Vector (SNV) [25] in depth channel, and MFSK [26] in RGB-D channels.”
• Multimodal Gesture Recognition Using 3-D Convolution and Convolutional LSTM (2017, background): “are utilized for gesture recognition [31].”
• Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model (2016, background): “Then they propose the mixed features around sparse keypoints (MFSK) [13] specifically for one shot learning of gesture recognition.”
• A Unified Framework for Multi-Modal Isolated Gesture Recognition (2018, methodology): “The training of SVM takes about 6 hours and the accuracy on IsoGD [Wan et al. 2016] is 53.”