Instructing people for training gestural interactive systems

By Simon Fothergill, Helena M. Mentis, Pushmeet Kohli, Sebastian Nowozin. 2012

416 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

In Human-Computer Interaction

Citations in the corpus

RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “1 Microsoft research Cambridge-12 kinect gesture dataset Microsoft Research Cambridge created MSRC-12 Gesture dataset [26] in 2012, which includes relevant gestures and their corresponding semantic labels for evaluating gesture recognition and detection systems.”
RGB-D-based action recognition datasets: A survey (2016, neutral): “MSRC-12 MSRC-12 dataset [13] (http://research.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[128] encoded the feature vector by concatenating 35 skeletal joint angles, 35 joint angle velocities, and 60 joint velocities into a 130-dimensional vector at each frame.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, neutral): “MSRC-12 MSRC-12 dataset (Fothergill et al., 2012)(http://research.”
When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, positive): “Namely, we evaluated on MSR-Action3D [20], MSR-Action-Pairs (MSR-pairs) [27], Gaming-3D (G3D) [2], Florence3D [31], UTKinect [40], MSRC-Kinect12 [8], HDM-05 [25] and NTU RGB+D [32].”
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, background): “A large number of RGB-D datasets have been captured and made publicly available for training and benchmarking [56, 34, 50, 65, 79, 83, 74, 4, 58, 81, 15, 55, 1, 68, 30, 51, 21, 48, 43, 92, 80, 61, 72, 93, 36, 16, 35, 57, 40, 29, 70, 52, 45, 95, 75, 9, 33, 85, 71, 32, 3, 10, 78, 2].”
A decision forest based feature selection framework for action recognition from RGB-depth cameras (2013, methodology): “After this selection procedure, we have trained a linear SVM classifier using the 1225 retained features on the set A of MSRC-12.”
A Review of Human Activity Recognition Methods (2015, neutral): “…17 1,920×1,080 Pose TUM Kitchen (Tenorth et al., 2009) 2009 10 4 20 324×288 Two-person interaction (Yun et al., 2012) 2012 8 7 ≈300 640×480 MSRC-12 Kinect gesture (Fothergill et al., 2012) 2012 12 30 594 J-HMDB (Jhuang et al., 2013) 2013 21 1 928 240×320 UPCV Action (Theodorakopoulos et al., 2014)…”
Survey on 3D Hand Gesture Recognition (2016, methodology): “Kinect gesture data set [89], which consists of sequences of human movements, represented as body part locations, and the”
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition (2014, background): “A number of new datasets [6, 7, 8, 28] have provided researchers with the opportunity to design novel representations and algorithms and test them on a much larger number of sequences.”
Grassmannian Representation of Motion Depth for 3D Human Gesture and Action Recognition (2014, background): “The motivation behinds the great interest for action recognition is the large number of possible applications in: consumer interactive entertainment and gaming [1], surveillance systems [2], lifecare systems and smart home systems [3].”
Category-Blind Human Action Recognition: A Practical Recognition System (2015, methodology): “The MSRC12-Gesture dataset was collected by having volunteers perform certain actions either based on ”Video + Text” based instructions or based on ”Image + Text” instructions.”
Exploring the Trade-off Between Accuracy and Observational Latency in Action Recognition (2012, methodology): “(2010) and the MSRC-12 Kinect Gesture dataset (Fothergill et al. 2012).”
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, methodology): “Combining the transitions with the classification term increases the overall performance on MSRC-12.”
3D action recognition using data visualization and convolutional neural networks (2017, methodology): “Datasets and Protocols The MSRC-12 dataset [22] contains 594 sequences, including 719359 frames (nearly 6 hour 40 minutes).”
Robust Action Recognition Based on a Hierarchical Model (2013, methodology): “The proposed model and features are evaluated on two datasets captured by a Kinect: UCFKinect action dataset [9] and Microsoft MSRC-12 gesture dataset [10].”