Recurrent Network Models for Human Dynamics

By Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Malik. 2015

1,035 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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 Control and Systems Engineering

Citations in the corpus

Generating Videos with Scene Dynamics (2016, background): “Our work is also related to efforts to predict the future in video [33, 22, 44, 51, 42, 17, 8, 55] as well as concurrent work in future generation [6, 15, 20, 50, 56, 43].”
Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “[104] proposed a DNN model called Encoder-Recurrent-Decoder (ERD) for human body pose recognition and motion prediction in videos and motion”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2015, methodology): “As node features we use the raw joint values expressed as exponential map [14], and edge features are concatenation”
Learning to Generate Long-term Future via Hierarchical Prediction (2017, methodology): “We note that Fragkiadaki et al. (2015) developed an LSTM architecture that can straight-forwardly be adapted to our method.”
A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning (2020, result): “This result matches model comparison studies in other ﬁ elds that have shown that GPR predictions of each data point look plausible but far away from the actual situation (Fragkiadaki et al., 2015).”
Who Let the Dogs Out? Modeling Dog Behavior from Visual Data (2018, methodology): “Sequence to sequence learning [38] has been used for different applications in computer vision such as representation learning [37], video captioning [40, 50], human pose estimation [44], motion prediction [20], or body pose labeling and forecasting [8, 44].”
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (2021, methodology): “Prior work has also used RNNs to model the temporal dynamics of 3D human pose [11, 58, 60].”
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks (2016, methodology): “Our used architecture is similar to recent Encoder-Recurrent-Decoder (Fragkiadaki et al. 2015) and similarly to (Shi et al.”
A Review on Deep Learning Techniques for Video Prediction (2020, neutral): “[54] 2017 [208] vED [115], [116] RGB,Po RGB X `2, CE,KL,AL R ? ? ? X 7”
On Human Motion Prediction Using Recurrent Neural Networks (2017, methodology): “We also explore training a single model to predict motion for multiple actions, in contrast to previous work [10, 18], which has focused on building action-specific models.”
Video Object Detection with an Aligned Spatial-Temporal Memory (2017, methodology): “In computer vision, RNNs have been used for image captioning [27,44,12], visual attention [2,32,47], action/object recognition [12,4], human pose estimation [15,6], and semantic segmentation [49].”
Learning Generator Networks for Dynamic Patterns (2019, background): “However, previous works have mostly focused on recognition or classification tasks [14, 6, 30, 32].”
Human Motion Diffusion Model (2022, background): “Some predict motion from its preﬁx poses (Fragkiadaki et al., 2015; Martinez et al., 2017; Hernandez et al., 2019; Guo et al., 2022b).”
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes: The Importance of Multiple Scene Constraints (2018, methodology): “Once the assignment has been resolved between every pair of estimated person models in every successive set of frames, and tracks are built, several motion priors can be used, ranging from a constant velocity model, to more sophisticated auto-regressive processes or deep recursive predictors learned”
Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction (2020, methodology): “Many methods, including the conventional state-based methods [25, 44, 38, 37, 36] and deep-network-based methods [9, 32, 10, 7, 12, 14, 11, 33, 43], have been proposed to Figure 1.”
A Spatio-temporal Transformer for 3D Human Motion Prediction (2020, background): “[11] propose the Encoder-Recurrent-Decoder (ERD) model where an LSTM cell operates in latent space.”
Neural state machine for character-scene interactions (2019, methodology): “LSTMs are considered suitable for time-series models and are applied for reproducing locomotion [Fragkiadaki et al. 2015], kung fu motion [Li et al.”