Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition

By Di Wu, Lionel Pigou, Pieter-Jan Kindermans, N. Le, Ling Shao, Joni Dambre, Jean-Marc Odobez. 2016

437 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “Activities, gestures and multimodal data — Recent gesture and human activity recognition methods dealing with several modalities typically process 2D+T RGB and/or depth data as 3D. Sequences of frames are stacked into volumes and fed into convolutional layers at the ﬁrst stages [3, 22, 40, 41, 57].”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “In a RGB, depth and skeleton fusion method, Wu et al. (2016) adopted Gaussian–Bernouilli Deep Belief Network (DBN) to extract high-level skeletal joint features and the learned representation is used to estimate the emission probability needed to infer gesture sequences.”
Pose-conditioned Spatio-Temporal Attention for Human Action Recognition (2017, background): “Sequences of frames are stacked into volumes and fed into convolutional layers at first stages [3, 15, 27, 28, 40].”
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].”
A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training (2019, methodology): “Convolutional neural networks (CNNs) [25], [26] and 3D convolutional neural networks (3D-CNNs) [4], [9], [10] have also been em-”
Deep Multimodal Learning: A Survey on Recent Advances and Trends (2017, methodology): “To capture temporal structures and relationships, deep multimodal learning approaches typically use temporal components such as LSTMs or hidden Markov models combined with visual representation learning layers like CNNs or 3-D-CNNs [42], [43].”
Quantifying and Alleviating the Language Prior Problem in Visual Question Answering (2019, background): “In order to achieve simultaneous gesture segmentation and recognition, authors in [36] integrated the emission probabilities estimated from different inputs (i.”
Visualizations of Deep Neural Networks in Computer Vision: A Survey (2017, background): “[75] 2016 General understanding Pixel displays Recognition DBN ChaLearn LAP”
Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization (2017, methodology): “The neural network methods adopted in gesture analysis include CNNs [17, 18, 26], 3D CNNs [21, 23, 30] and temporal convolutions [26].”
Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges (2018, methodology): “In [59], dynamic deep neural networks (D2NN) were introduced, which were a type of feed-forward deep neural network that selected and executed a subset of D2NN neurons based on the input.”
A Survey of Model Compression and Acceleration for Deep Neural Networks (2017, methodology): “In [59], dynamic deep neural networks (D2NN) were introduced, which were a type of feed-forward deep neural network that selected and executed a subset of D2NN neurons based on the input.”
Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks (2018, methodology): “[41] adopted a 3D ConvNet to extract features from depth data, which requires a large amount of train-”
Human Action Recognition: Pose-Based Attention Draws Focus to Hands (2017, background): “Sequences of RGB frames are stacked into volumes and fed into convolutional layers at first stages [3, 15, 27, 28, 38].”
A Low Power, Fully Event-Based Gesture Recognition System (2017, methodology): “Multimodal systems [46, 31, 33, 15] have also been used to improve performance.”
End-to-End Multimodal Emotion Recognition Using Deep Neural Networks (2017, methodology): “In [17], the authors use skeletal information and”