Learning Discriminative Representations from RGB-D Video Data

By Li Liu, Ling Shao. 2013

304 citations recorded by the source corpus.

Subfields: Multimodal Learning, Representation & Self-Supervised Learning

How researchers see this paper

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

In Multimodal Learning

1. Hossein Rahmani
2. Jun Liu
3. G. Wang
4. Amir Shahroudy
5. Weishi Zheng
6. J. Lai
7. Jianfang Hu
8. Jianguo Zhang

In Representation & Self-Supervised Learning

1. G. Wang
2. Jun Liu
3. Amir Shahroudy
4. Yun Raymond Fu
5. Tae-Kyun Kim
6. Yu Kong
7. J. Lai
8. Tian-Tsong Ng

Citations in the corpus

• Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, methodology): “An evolutionary programming RGB+D fusion method was proposed by [34].”
• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “This device equipped with intelligent algorithms is contributing to various applications, such as 3D-simultaneous localization and mapping (SLAM) [39, 54], people tracking [69], object recognition [11] and human activity analysis [13, 57], etc.”
• A Survey of Datasets for Human Gesture Recognition (2014, background): “SKIG [26] ‘13 5 Environment 3 Iconic & metaphoric Improve gesture recognition from RGBD data, notably with different illuminations.”
• Fusing Multiple Features for Depth-Based Action Recognition (2015, background): “and the State-of-the-Art Methods on Method NBNN + parts + time [Seidenari Local HON4D [Oreifej and Liu 2013 DCSF [Xia and Aggarwal RGGP + Fusion [Liu and Shao 2013]”
• Working Together: A Review on Safe Human-Robot Collaboration in Industrial Environments (2017, unknown): “Moreover, the work described in [145] proposes an adaptive learningmethodology to extract spatio-temporal features, simultaneously fusing the RGB and depth information.”
• SUN RGB-D: A RGB-D scene understanding benchmark suite (2015, unknown): “There are many existing RGB-D datasets available [54] [47] [1] [25] [44] [60] [49] [45] [29] [66] [57] [52] [46] [16] [21] [73] [35] [67] [3] [41] [10] [63] [42] [64] [65] [48] [12] [33] [8] [50] [26] [6].”
• Survey on 3D Hand Gesture Recognition (2016, background): “The Sheffield Kinect Gesture (SKIG) data set [92] collects ten common categories of 3D hand gestures, which are performed with three hand postures: 1) fist; 2) index; and 3) flat.”
• Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, methodology): “Compared to the closely related methods focusing on feature fusion using deep model [20] and structured sparse model [30], our model outperforms both of them by a considerable margin (more than 9.”
• Bilinear heterogeneous information machine for RGB-D action recognition (2015, background): “Recent work [11] also showed that features of RGB-D data can also be learned using popular deep learning techniques.”
• RGBD Datasets: Past, Present and Future (2016, background): “Sheffield KInect Gesture (SKIG) [69] 6 10 1080 Hand gestures e.”
• Human-Computer Interaction. Advanced Interaction Modalities and Techniques (2014, background): “[26] Demonstrate interface quality hand gesture recognition only with color segmentation means.”
• Evaluating spatiotemporal interest point features for depth-based action recognition (2014, unknown): “RGGP + fusion [38] 85.”
• Super Normal Vector for Activity Recognition Using Depth Sequences (2014, methodology): “The methods [10, 14, 21, 24, 26] based on either motion or shape information alone are significantly inferior to our method and the ones [12, 21] that jointly model the two cues.”
• Recent methods and databases in vision-based hand gesture recognition: A review (2015, methodology): “Sheffield KInect Gesture (SKIG) Dataset SKIG dataset [135] has 10 categories of hand gestures, recorded from 6 subjects using RGB and Kinect cameras.”
• ChaLearn Looking at People RGB-D Isolated and Continuous Datasets for Gesture Recognition (2016, background): “Sheffield Kinect Gesture 1,080 10 108 RGB-D Dataset, 2013 [14] & small-scale learning”
• LaRED: a large RGB-D extensible hand gesture dataset (2014, background): “Moreover, the dataset in [5] is recorded with dynamic gestures.”
• Online Action Recognition via Nonparametric Incremental Learning (2014, methodology): “We assessed our method on some of the most common computer vision benchmarks: Weizmann [17] and KTH [44] (all scenarios) for action recognition, SKIG [30] and MSRGesture3D [50] for gesture recognition, JAPVOW [34] and AUSLAN [22] for sign language recognition (UCI Repository [1]).”