Sequential Deep Learning for Human Action Recognition

By Moez Baccouche, Franck Mamalet, Christian Wolf, Christophe Garcia, Atilla Baskurt. 2011

814 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Long-term recurrent convolutional networks for visual recognition and description (2014, background): “A large body of recent work has proposed deep architectures for activity recognition ([16, 33, 13, 2, 1]).”
Beyond short snippets: Deep networks for video classification (2015, background): “Encouraged by these positive results several approaches have been proposed recently to apply CNNs to video and action classification tasks [2, 13, 14, 19].”
Lifelong learning of human actions with deep neural network self-organization (2017, methodology): “2%) and Baccouche et al. (2011) combining a 3D-CNNwith a long shortterm memory (LSTM, 94.”
Differential Recurrent Neural Networks for Action Recognition (2015, methodology): “In particular, [3] developed a 3D convolutional neural network that extends the conventional CNN by taking spacetime volume as input.”
Video Representation Learning Using Discriminative Pooling (2018, background): “This problem may be tackled using recurrent models [1, 8, 9, 25, 45, 60], however such models are usually harder to train [32].”
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, background): “[5] tackled the problem of action recognition through a cascade of 3D CNN and LSTM, in which the two networks were trained separately.”
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection (2017, methodology): “[2] firstly used a 3D CNN to learn spatio-temporal features from video and in the next step they employed an LSTM to classify video 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].”
VideoLSTM convolves, attends and flows for action recognition (2016, background): “[8] model sequential memories both in the long and in the short term, which makes them relevant for various sequential tasks [9,10,25,26]. Where early adopters used traditional features as LSTM input [27,28], more recently both Ng et al. [10] and Donahue et al. [9] propose LSTMs that explicitly mode”
Learnable pooling with Context Gating for video classification (2017, methodology): “More recent methods extract deep convolutional neural network activations computed from individual frames or blocks of frames using spatial [6], [25], [26], [27] or spatio-temporal [5], [10], [11], [12], [13], [14] convolutions.”
Hierarchical recurrent neural network for skeleton based action recognition (2015, methodology): “Considering that LSTM-RNNs employed in [1] and [11] are both unidirectional with only one hidden layer, Lefebvre et al .”
Large-Scale Video Classification with Convolutional Neural Networks (2014, background): “The activations from both streams are concatenated and fed into the first fully connected layer with dense connections.”
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description (2017, background): “Research on CNN models for video processing has considered learning 3D spatio-temporal filters over raw sequence data [1], [2], and learning of frame-to-frame representations which incorporate instantaneous optic flow or trajectory-based models aggregated over fixed windows or video shot segments…”
Neural Networks and Deep Learning (2018, neutral): “Another common idea for video classification is to combine convolutional neural networks with recurrent neural networks [17, 100, 356, 455].”
Symbiotic human-robot collaborative assembly (2019, methodology): “Recently, deep learning has gained attentions as a reliable and practical method for human motions recognition and prediction for timely context awareness [14,208,131].”