Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction

By Gang Yu, Zicheng Liu, Junsong Yuan. 2014

159 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

1. G. Wang
2. Jun Liu
3. Luc Van Gool
4. Ming-Hsuan Yang
5. Xiaogang Wang
6. Alex ChiChung Kot
7. Dacheng Tao
8. Yi Yang

In Human-Computer Interaction

1. Jun Liu
2. G. Wang
3. Amir Shahroudy
4. Sergio Escalera
5. Isabelle M Guyon
6. Hao Zhang
7. Fei Han
8. Alex ChiChung Kot

Citations in the corpus

• NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, neutral): “MSR-Action3D [19] 567 20 10 1 N/A D+3DJoints 2010 CAD-60 [34] 60 12 4 - Kinect v1 RGB+D+3DJoints 2011 RGBD-HuDaAct [23] 1189 13 30 1 Kinect v1 RGB+D 2011 MSRDailyActivity3D [38] 320 16 10 1 Kinect v1 RGB+D+3DJoints 2012 Act4(2) [6] 6844 14 24 4 Kinect v1 RGB+D 2012 CAD-120 [18] 120 10+10 4 - Kinect ”
• Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “As a result, depth sequences provide an exclusive modality of information about the 3D structure of the scene, which suits the problem of activity analysis [41, 47, 65, 73, 74, 79, 83].”
• 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”
• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Many other datasets captured using a Kinect v1 camera were also released to the public, including the MSR Daily Activity 3D [121], MSR Action Pairs [113], Online RGBD Action (ORGBD) [107], UTKinect-Action [124], Florence 3D-Action [118], CMU-MAD [104], UTD-MHAD [103], G3D/G3Di [105], [119], SPHERE [”
• Skeleton-Based Online Action Prediction Using Scale Selection Network (2019, neutral): “research domain [26], [27], and a series of hand-crafted features [28], [29], [30], [31], [32], [33], [34], [35], [36], [37] and deep learning-based approaches [18], [19], [38], [39], [40], [41], [42], [43], [44] have been proposed.”
• Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017, background): “Skeleton-based approaches such as [5, 22, 35, 39, 50] move beyond such sparse grid-like pooling and focus on how to propose good skeletal representations.”
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (2016, background): “Orderlet makes an extension of action-let by including the feature of pairwise joint distance and allowing various sizes of a subset (Yu, Liu, and Yuan 2014).”
• Challenges in multimodal gesture recognition (2016, background): “In (Yu et al., 2014) the authors propose the orderlets to capture discriminative information for gesture recognition from depth maps.”
• Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition (2019, background): “Recent works using neural networks [11] have significantly outperformed traditional approaches that use hand-crafted features [11, 52, 46, 55, 9].”
• Learning hierarchical spatio-temporal pattern for human activity prediction (2016, methodology): “%) of 3D Online Action Dataset.”
• Linear-time online action detection from 3D skeletal data using bags of gesturelets (2015, methodology): “Possible descriptors that capture both pose information and joints kinematics are [11, 14, 20, 22].”
• Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition (2017, background): “In Orderlet [33], interactions between joints are modeled by a few comparisons of joints’ primitive feature, and in action recognition only a subset of joints is involved.”
• Category-Blind Human Action Recognition: A Practical Recognition System (2015, methodology): “As in [11, 22, 25], the optimal θε is chosen such that it minimizes the recognition error, e.”
• Human-object interaction recognition by learning the distances between the object and the skeleton joints (2015, methodology): “This section summarizes our empirical results and provides an analysis of the performance of our proposed approach on ORGBD dataset [1] compared to the state-of-theart approaches.”
• Recognizing Human Actions as the Evolution of Pose Estimation Maps (2018, methodology): “By detecting 3D pose from each depth frame with an accurate body pose estimation method [36], human movements in depth videos can be simplified as 3D pose sequences [52].”