Adversarial Attention for Human Motion Synthesis
Not on the map. Why?
Abstract (arXiv)
Analysing human motions is a core topic of interest for many disciplines, from Human-Computer Interaction, to entertainment, Virtual Reality and healthcare. Deep learning has achieved impressive results in capturing human pose in real-time. On the other hand, due to high inter-subject variability, human motion analysis models often suffer from not being able to generalise to data from unseen subjects due to very limited specialised datasets available in fields such as healthcare. However, acquiring human motion datasets is highly time-consuming, challenging, and expensive. Hence, human motion synthesis is a crucial research problem within deep learning and computer vision. We present a novel method for controllable human motion synthesis by applying attention-based probabilistic deep adversarial models with end-to-end training. We show that we can generate synthetic human motion over both short- and long-time horizons through the use of adversarial attention. Furthermore, we show that we can improve the classification performance of deep learning models in cases where there is inadequate real data, by supplementing existing datasets with synthetic motions.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 25 Apr 2022.
Builds on
30 of 57 references.
References · 30
- 2016Improved Techniques for Training GANscited by 2,938
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2017Wasserstein GANcited by 635
- 2015Adversarial Autoencoderscited by 359
- 2017On human motion prediction using recurrent neural networkscited by 336
- 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
- 2021Robust Motion In-betweeningcited by 223
- 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
- 2021Character Controllers Using Motion VAEscited by 182
- 2017HP-GAN: Probabilistic 3D human motion prediction via GANcited by 176
18 more
- 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
- 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
- 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
- 2019Context-aware Human Motion Predictioncited by 83
- 2017Learning Human Motion Models for Long-term Predictionscited by 67
- 2018Action-Agnostic Human Pose Forecastingcited by 56
- 2020Socially and Contextually Aware Human Motion and Pose Forecastingcited by 51
- 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
- 2019Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Predictioncited by 46
- 2018Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Controlcited by 39
- 2019Human Motion Prediction via Learning Local Structure Representations and Temporal Dependenciescited by 34
- 2016Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detectioncited by 32
- 2019Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervisioncited by 27
- 2021A Survey on Deep Learning for Skeleton-Based Human Animationcited by 26
- 2021GAN-based Reactive Motion Synthesis with Class-aware Discriminators for Human-human Interactioncited by 18
- 2016Generative Choreography using Deep Learningcited by 12
- 2017Controllable Generative Adversarial Networkcited by 8
- 2021Towards Explainable, Privacy-Preserved Human-Motion Affect Recognitioncited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.