A real time system for dynamic hand gesture recognition with a depth sensor

By Alexey Kurakin, Z. Zhang, Z. Liu. 2012

307 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Hossein Rahmani
2. Jun Liu
3. Amir Shahroudy
4. Ajmal Saeed Mian
5. Pichao Wang
6. Zehua Sun
7. Fei Han
8. G. Wang

Citations in the corpus

• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “The curves under the images are the accelerometer data at 50 Hz of devices attached to the knife, the mixing spoon, the small spoon, the peeler, the glass, the oil bottle, and the pepper dispenser mentioned datasets above, another 26 extra RGB-D datasets for different applications are also added int”
• Action Classification with Locality-Constrained Linear Coding (2014, methodology): “For depth data, we use three standard datasets including the MSRAction3D [8], [10], MSRGesture3D [6], [12], and MSRActionPairs3D [7].”
• A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, unknown): “MSR Gesture3D [9] 12 10 2 or 3 336 25 2012 LIRIS Human Activities [10] 10 21 24 2012”
• Informative joints based human action recognition using skeleton contexts (2015, background): “However, the 3D human skeletons, generated via skeleton tracking from the depth map sequences, are generally very noisy and unreliable.”
• Grassmannian Representation of Motion Depth for 3D Human Gesture and Action Recognition (2014, methodology): “[20], the protocol used for evaluation is Leave-one-subject-out-cross-validation.”
• RGBD Datasets: Past, Present and Future (2016, background): “Actions being performed include sign language [59], Italian hand gestures [26] and common daily actions such as standing up, drinking and reading [100, 58, 82, 106, 65, 16].”
• A Survey of Datasets for Human Gesture Recognition (2014, background): “MSRGesture3D [28] ‘12 17 Environment 3 Sign language Sign language recognition from hand depth data.”
• Robust 3D Action Recognition with Random Occupancy Patterns (2012, methodology): “805 Action Graph on Silhouette Features [24] 0.”
• Video-based Sign Language Recognition without Temporal Segmentation (2018, background): “Previous researches (Tang et al. 2015; Kurakin, Zhang, and Liu 2012; Sun et al. 2013) on posture/gesture models rely heavily on collected depth maps from Kinect-style RGB-D sensors, which provides a convenient way in 3D modeling.”
• Real time action recognition using histograms of depth gradients and random decision forests (2014, methodology): “The proposed algorithm is evaluated on three standard databases including MSR Action 3D [6, 13], MSR Gesture 3D [5, 12], and MSR Daily Activity 3D [13].”
• Human Action Recognition and Prediction: A Survey (2018, unknown): “KTH [180] 2004 599 1 6 25 RGB Controlled Weizmann [10] 2005 90 1 10 9 RGB Controlled INRIA XMAS [233] 2006 390 5 13 10(3 times) RGB Controlled IXMAS [264] 2006 1,148 5 11 RGB Controlled UCF Sports [171] 2008 150 10 RGB Uncontrolled Hollywood [114] 2008 8 RGB Uncontrolled Hollywood2 [137] 2009 3,669 ”
• Human-Computer Interaction. Advanced Interaction Modalities and Techniques (2014, background): “[28] Also state that Gaussian mixture models are lower to histogram based approaches.”
• Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition (2013, methodology): “[30] use action graph classifiers on the MSRGesture3D dataset and apply leave-one-subject-out cross validation but only on 5 random subjects.”