Attention Mechanism for Human Motion Prediction
The DOI matches its Crossref record; 19 of the 20 references it cites were found in a registry or an index.
Abstract
Human motion prediction aims to forecast the most likely future frames of motion conditioned on a given sequence of frames. Because of its importance to many applications especially robotics, it has received a lot of interest and has become an active area of research. Since humans are very flexible in nature, human motion prediction is very challenging Recently, deep learning methods have been dominant in many tasks due to their successful results. Particularly, Recurrent Neural Networks (RNNs) have shown excellent performance on human motion prediction task and other tasks that depend on sequential data, where preserving the order of the sequence items is crucial. The well-known Sequence-to-Sequence (Seq2Seq) architectures have been used for sequence learning where two RNNs namely the encoder and the decoder work cooperatively to transform one sequence to another. In the context of neural machine translation, the use of attention decoders yields state-of-the-art results. This work employs a simple but efficient Seq2Seq model with attention decoder. Both encoder and decoder are trained jointly to predict 15 different categories of human motion. Our experiments have shown that the attention decoder clearly outperforms earlier methods and achieves state-of-the-art results in the short-term (500ms) motion prediction which stays as high even after 1000ms of prediction.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“Bidirectional RNN was invented to fulfill that need [9].”
MethodEffective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653 · cited 1×
“6) dataset [10, 11] is used in the experimentation of this work as in previous works.”
MethodStructural-RNN: Deep Learning on Spatio-Temporal Graphs
Jain, A., Zamir, A. R., Savarese, S., & Saxena, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.573 · Cited by 1,133 · cited 6×
“An early work of [13] suggested a conditional restricted Boltzmann machine (CRBM) to model motion where sampling is needed for inference [2].”
BackgroundMethodInfluentialOn Human Motion Prediction Using Recurrent Neural Networks
Martinez, J., Black, M. J., & Romero, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.497 · Cited by 984
Recurrent Network Models for Human Dynamics
Fragkiadaki, K., Levine, S., Felsen, P., & Malik, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.494 · Cited by 860
Modeling Human Motion Using Binary Latent Variables
Taylor, G. W., Hinton, G. E., & Roweis, S. T. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0173 · Cited by 689
Adversarial Geometry-Aware Human Motion Prediction
Gui, L.-Y., Wang, Y.-X., Liang, X., & Moura, J. M. F. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_48 · Cited by 276 · cited 3×
“The work of [1] has achieved state-of-the-art results in human motion prediction.”
BackgroundLatent structured models for human pose estimation
Ionescu, C., Li, F., & Sminchisescu, C. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126500 · Cited by 258
QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Pavllo, D., Grangier, D., & Auli, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06485 · Cited by 174
Modeling Human Motion with Quaternion-Based Neural Networks
Pavllo, D., Feichtenhofer, C., Auli, M., & Grangier, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01245-6 · Cited by 152
Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamics
Tang, Y., Ma, L., Liu, W., & Zheng, W.-S. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/130 · Cited by 129
Research works printed but not linked: 6
- amidi, 0, Recurrent Neural Networks cheatsheet Star, CS 230 - Recurrent Neural Networks Cheatsheet
- 2020, Google Colaboratory
- goodfellow, 2016, Deep Learning
- butepage, 0, Deep Representation Learning for Human Motion Prediction and
- paszke, 2019, PyTorch: An Imperative Style, HighPerformance Deep Learning Library, Advances in Neural IInformation Processing Systems, 8024
- robertson, 0, NLP From Scratch Translation with a Sequence to Sequence Network and Attention
Cited by
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
Dang, L., Nie, Y., Long, C., Zhang, Q., & Li, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01127 · Cited by 257
“Although RNN-based methods like [9, 34, 41, 42, 37, 11, 5, 2] have advantages in dealing with time-related tasks, the discontinuity and error accumulation problems often happen because of the frame-byframe prediction manner.”
BackgroundMethodCollaborative Multi-Dynamic Pattern Modeling for Human Motion Prediction
Tang, J. H., Zhang, J., Ding, R., Gu, B., & Yin, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3239322 · Cited by 53
“Al-aqel and Khan [20] implemented an attention mechanism to RNN for focusing on keyframes.”
BackgroundLearning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction
Fu, J., Yang, F., Dang, Y., Liu, X., & Yin, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3277476 · Cited by 51
“…deep-learning techniques for human motion prediction, such as convolution neural network (CNN) [8], [9], recurrent neural network (RNN) [8], [10], [11], [12], [12], [13], [14], [15], [16], [17], [18], generative adversarial network (GAN) [19], [20], [21], [22], [23] and transformer [24],…”
BackgroundMSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion PredictionPreprint
Dang, L., Nie, Y., Long, C., Zhang, Q., & Li, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.07152 · Cited by 14
“Although RNN-based methods like [9, 34, 41, 42, 37, 11, 5, 2] have advantages in dealing with time-related tasks, the discontinuity and error accumulation problems often happen because of the frame-byframe prediction manner.”
BackgroundMethodChen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9
Metadata
- Authors
- Al-aqel, A. F., & Ali Khan, M.
- Affiliations
- Umm al-Qura University (SA)
- Venue
- 2020 3rd International Conference on Computer Applications & Information Security (ICCAIS)
- Publisher
- IEEE
- Published
- 2020-03
- Pages
- 1-6
- OpenAlex
- W3027068812
- Cited by
- 7
- References
- 20
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 1 · 2023: 2 · 2021: 2
- FWCI
- 1.50
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Conference on Computer Applications & Information Security (ICCAIS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Social Sciences › Psychology › Social Psychology › Action Observation and Synchronization
- Keywords
- human motion prediction, attention mechanism, sequence-to-sequence models, recurrent neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.