Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/karttikeya/awesome-human-pose-prediction

A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)
https://github.com/karttikeya/awesome-human-pose-prediction

List: awesome-human-pose-prediction

Last synced: about 1 month ago
JSON representation

A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

Awesome Lists containing this project

README 

        
# Awesome-Human-Pose-Prediction

![Version](https://img.shields.io/badge/Version-0.5-ff69b4.svg) [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) ![LastUpdated](https://img.shields.io/badge/LastUpdated-2020.06.04-lightgrey.svg) 

[![HitCount](http://hits.dwyl.io/karttikeya/Awesome-Human-Pose-Prediction.svg)](http://hits.dwyl.io/karttikeya/Awesome-Human-Pose-Prediction)





  




A selection of State Of The Art research papers (and code) on human trajectory prediction (forecasting). Papers marked with [W] are workshop papers. 



**Maintainers**: [Karttikeya Mangalam](http://karttikeya.github.io/)



**Contributing**: Please feel free to [pull requests]() to add new resources or suggest addditions or changes to the list. While proposing a new addition, please keep in mind the following principles:



- The work has been accepted in a reputable peer reviewed publication venue.

- An opensource link to the paper pdf is attached (as far as possible).

- Code for the paper is linked (if made opensource by the **authors**). 



Email: mangalam@cs.{berkeley,stanford).edu



## Datasets

- Human3.6M:

Large Scale Datasets and Predictive Methods

for 3D Human Sensing in Natural Environments [[Paper]](http://vision.imar.ro/human3.6m/pami-h36m.pdf)

- Stanford Drone Dataset (SDD): Learning Social Etiquette: Human Trajectory

Understanding in Crowded Scenes [[Paper]](http://svl.stanford.edu/assets/papers/ECCV16social.pdf) [[Leaderboard]](https://paperswithcode.com/sota/trajectory-prediction-on-stanford-drone)



## Papers 



### As End in Itself

- From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting [[Paper]](https://arxiv.org/pdf/2012.01526)

- It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction [[Paper]](https://arxiv.org/pdf/2004.02025.pdf)

- Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data [[Paper]](https://arxiv.org/pdf/2001.03093)

- Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph [[paper]](https://arxiv.org/pdf/2009.12916.pdf)

- Map-Adaptive Goal-Based Trajectory Prediction [[paper]](https://arxiv.org/pdf/2009.04450.pdf)

- Interaction-Aware Trajectory Prediction based on a 3D Spatio-Temporal Tensor Representation using Convolutional–Recurrent Neural Networks [[paper]](https://ieeexplore.ieee.org/abstract/document/9304846)

- DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning [[Paper]](https://arxiv.org/pdf/1908.00024)

- Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction [[Paper]](http://proceedings.mlr.press/v100/jain20a.html)

- Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians [[Paper]](https://arxiv.org/pdf/2010.09056)

- Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactions [[Paper]](https://arxiv.org/pdf/2012.01027)

- Social NCE: Contrastive Learning of Socially-aware Motion Representations [[Paper]](https://arxiv.org/pdf/2012.11717.pdf)

- Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approach [[Paper]](https://ieeexplore.ieee.org/abstract/document/9286482)

- Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction [[Paper]](https://arxiv.org/pdf/2009.05702.pdf)

- Deep Learning for Vision-based Prediction: A Survey [[Paper]](https://arxiv.org/pdf/2007.00095)

- Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction Using a Graph Vehicle-Pedestrian Attention Network [[Paper]](https://ieeexplore.ieee.org/abstract/document/9123560)

- Semantics for Robotic Mapping, Perception and Interaction: A Survey [[Paper]](https://arxiv.org/pdf/2101.00443.pdf)

- Benchmark for Evaluating Pedestrian Action Prediction[[Paper]](https://openaccess.thecvf.com/content/WACV2021/papers/Kotseruba_Benchmark_for_Evaluating_Pedestrian_Action_Prediction_WACV_2021_paper.pdf)

- Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking [[Paper]](https://arxiv.org/pdf/2012.02337.pdf)

- Pedestrian Behavior Prediction via Multitask Learning and Categorical Interaction Modeling [[Paper]](https://arxiv.org/pdf/2012.03298)

- Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction [[Paper]](https://arxiv.org/pdf/2012.02148.pdf)

- Haar Wavelet based Block Autoregressive Flows for Trajectories [[Paper]](https://pure.mpg.de/pubman/faces/ViewItemOverviewPage.jsp?itemId=item_3267310)

- Imitative Planning using Conditional Normalizing Flow [[Paper]](https://arxiv.org/pdf/2007.16162.pdf)

- TNT: Target-driveN Trajectory Prediction [[Paper]](https://arxiv.org/pdf/2008.08294.pdf)

- SimAug: Learning Robust Representations from Simulation for Trajectory Prediction [[Paper]](https://link.springer.com/chapter/10.1007/978-3-030-58601-0_17)

- SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints

 [[Paper]](https://openaccess.thecvf.com/content_CVPR_2019/html/Sadeghian_SoPhie_An_Attentive_GAN_for_Predicting_Paths_Compliant_to_Social_CVPR_2019_paper.html)

- Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks [[Paper]](https://openaccess.thecvf.com/content_cvpr_2018/html/Gupta_Social_GAN_Socially_CVPR_2018_paper.html)

- DESIRE: Distant Future Prediction in Dynamic Scenes With Interacting Agents [[Paper]](https://openaccess.thecvf.com/content_cvpr_2017/html/Lee_DESIRE_Distant_Future_CVPR_2017_paper.html)



- Predicting Whole Body Motion Trajectories using Conditional Neural

Movement Primitives [[Paper]](https://motionpredictionicra2020.github.io/posters/lhmp2020_kurtoglu_paper.pdf) [W]

- Anticipating Human Intention for Full-Body Motion Prediction [[Paper]](https://motionpredictionicra2020.github.io/posters/lhmp2020_kratzer_paper.pdf) [W]

- Human Motion Prediction With Graph Neural Networks [[Paper]](https://motionpredictionicra2020.github.io/posters/lhmp2020_guzey_paper.pdf) [W] 

- Action-Agnostic Human Pose Forecasting [[Paper]](https://arxiv.org/pdf/1810.09676.pdf)

- Human Torso Pose Forecasting in the Real World [[Paper]](http://harp.ri.cmu.edu/assets/pubs/mmpc_rss2018_biswas.pdf)

- Imitation Learning for Human Pose Prediction [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Imitation_Learning_for_Human_Pose_Prediction_ICCV_2019_paper.pdf)

- Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision [[Paper]](https://arxiv.org/pdf/1911.01138.pdf)

- Predicting 3D Human Dynamics from Video [[Paper]](https://arxiv.org/pdf/1812.01601.pdf)

- Recurrent Network Models for Human Dynamics [[Paper]](https://arxiv.org/pdf/1508.00271.pdf)

- Structural-RNN: Deep Learning on Spatio-Temporal Graphs [[Paper]](https://arxiv.org/pdf/1511.05298.pdf)

- Learning Trajectory Dependencies for Human Motion Prediction [[Paper]](https://arxiv.org/pdf/1908.05436.pdf) 

- Anticipating many futures: Online human motion prediction and generation

for human-robot interaction [[Paper]](http://www.nada.kth.se/~hedvig/publications/icra_18.pdf)

- Teaching Robots to Predict Human Motion [[Paper]](https://www.ri.cmu.edu/wp-content/uploads/2018/12/yuxiongw_iros18_teaching.pdf)

- Deep representation learning for human motion prediction and classification [[Paper]](https://arxiv.org/pdf/1702.07486.pdf)

- On human motion prediction using recurrent neural networks [[Paper]](https://arxiv.org/pdf/1705.02445.pdf)

- Few-Shot Human Motion Prediction via Meta-learning [[Paper]](https://www.ri.cmu.edu/wp-content/uploads/2018/12/yuxiongw_eccv18_fewshot.pdf)

- Efficient convolutional hierarchical autoencoder for human motion

prediction [[Paper]](https://link.springer.com/content/pdf/10.1007%2Fs00371-019-01692-9.pdf)

- Learning Human Motion Models for Long-term Predictions [[Paper]](https://arxiv.org/pdf/1704.02827.pdf)

- Long-Term Human Motion Prediction by Modeling Motion Context and

Enhancing Motion Dynamic [[Paper]](https://arxiv.org/pdf/1805.02513.pdf)

- Context-aware Human Motion Prediction [[Paper]](https://arxiv.org/pdf/1904.03419.pdf)

- Adversarial Geometry-Aware Human Motion Prediction [[Paper]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Liangyan_Gui_Adversarial_Geometry-Aware_Human_ECCV_2018_paper.pdf)

- Convolutional Sequence to Sequence Model for Human Dynamics [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Convolutional_Sequence_to_CVPR_2018_paper.pdf)

- QuaterNet: A Quaternion-based Recurrent Model for Human Motion [[Paper]](https://arxiv.org/pdf/1805.06485.pdf)

- BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN [[Paper]](https://arxiv.org/pdf/1812.02591.pdf)

- Human Motion Modeling using DVGANs [[Paper]](https://arxiv.org/pdf/1804.10652.pdf)

- Human Motion Prediction using Semi-adaptable Neural Networks [[Paper]](https://arxiv.org/pdf/1810.00781.pdf)

- A Neural Temporal Model for Human Motion Prediction [[Paper]](http://openaccess.thecvf.com/content_CVPR_2019/papers/Gopalakrishnan_A_Neural_Temporal_Model_for_Human_Motion_Prediction_CVPR_2019_paper.pdf)

- Modeling Human Motion with Quaternion-based Neural Networks [[Paper]](https://arxiv.org/pdf/1901.07677.pdf)

- Human Motion Prediction via Learning Local Structure Representations and

Temporal Dependencies [[Paper]](https://arxiv.org/pdf/1902.07367.pdf)

- VRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction [[Paper]](https://arxiv.org/pdf/1906.06514.pdf)

- EAN: Error Attenuation Network for Long-term Human Motion Prediction [[Paper]](https://ieeexplore.ieee.org/abstract/document/8901951)

- Structured Prediction Helps 3D Human Motion Modelling [[Paper]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Aksan_Structured_Prediction_Helps_3D_Human_Motion_Modelling_ICCV_2019_paper.pdf)

- Forecasting Human Dynamics from Static Images [[Paper]](https://arxiv.org/pdf/1704.03432.pdf) 

- HP-GAN: Probabilistic 3D human motion prediction via GAN [[Paper]](http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w29/Barsoum_HP-GAN_Probabilistic_3D_CVPR_2018_paper.pdf)

- Learning Latent Representations of 3D Human Pose with Deep Neural Networks [[Paper]](https://infoscience.epfl.ch/record/252823/files/main_paper.pdf)

- A Recurrent Variational Autoencoder for

Human Motion Synthesis [[Paper]](http://www.ipab.inf.ed.ac.uk/cgvu/0414.pdf)

- Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling [[Paper]](https://arxiv.org/abs/1908.07214)

- Combining Recurrent Neural Networks and

Adversarial Training for Human Motion Synthesis and Control [[Paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8826012)

- PISEP2: Pseudo Image Sequence Evolution based 3D Pose Prediction [[Paper]](https://arxiv.org/pdf/1909.01818.pdf)

- Human Motion Prediction via Spatio-Temporal Inpainting [[Paper]](https://arxiv.org/pdf/1812.05478.pdf)

- Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction [[Paper]](https://arxiv.org/pdf/1909.13245.pdf)

- Human Pose Forecasting via Deep Markov Models [[Paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227441)

- Auto-Conditioned Recurrent Networks For Extended Complex Human Motion Synthesis [[Paper]](https://openreview.net/pdf?id=r11Q2SlRW)

- Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network [[Paper]](https://arxiv.org/pdf/1911.02404.pdf)



### As a Subtask 

- The Pose Knows: Video Forecasting by Generating Pose Futures [[Paper]](https://arxiv.org/pdf/1705.00053.pdf)

- I-Planner: Intention-Aware Motion

Planning Using Learning Based Human

Motion Prediction [[Paper]](http://gamma.cs.unc.edu/SafeMP/papers/ijrr18.pdf)

- Language2Pose: Natural Language Grounded Pose Forecasting [[Paper]](https://arxiv.org/pdf/1907.01108.pdf)

- Long-Term Video Generation of Multiple Futures Using Human Poses [[Paper]](https://arxiv.org/pdf/1904.07538.pdf)

- Predicting body movements for person identification under different walking conditions [[Paper]](https://reader.elsevier.com/reader/sd/pii/S0379073818304109?token=76C0C8F3C9DCB97DD1D9C1EB6985414D0E842BCDBB9F3E35389B3CA504BED12F86181D8AACBFB4572674B83842C5A31A)