Deep Multimodal Representation Learning from Temporal Data
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
In recent years, Deep Learning has been successfully applied to multimodal learning problems, with the aim of learning useful joint representations in data fusion applications. When the available modalities consist of time series data such as video, audio and sensor signals, it becomes imperative to consider their temporal structure during the fusion process. In this paper, we propose the Correlational Recurrent Neural Network (CorrRNN), a novel temporal fusion model for fusing multiple input modalities that are inherently temporal in nature. Key features of our proposed model include: (i) simultaneous learning of the joint representation and temporal dependencies between modalities, (ii) use of multiple loss terms in the objective function, including a maximum correlation loss term to enhance learning of cross-modal information, and (iii) the use of an attention model to dynamically adjust the contribution of different input modalities to the joint representation. We validate our model via experimentation on two different tasks: video-and sensor-based activity classification, and audio-visual speech recognition. We empirically analyze the contributions of different components of the proposed CorrRNN model, and demonstrate its robustness, effectiveness and state-of-the-art performance on multiple datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1×
“…the contribution of different aspects of the CorrRNN design, we also evaluate different model configurations summarized in hidden layer representations obtained from each network are then reduced to 256 dimensions using PCA, and concatenated to obtain a 512 -dimensional fused representation.”
MethodUnsupervised Learning of Video Representations using LSTMs
Srivastava, N., Mansimov, E., & Salakhutdinov, R. (2015) · arXiv · doi:10.48550/arxiv.1502.04681 · Cited by 1,861
Collecting complex activity datasets in highly rich networked sensor environments
Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., Forster, K., Troster, G., Lukowicz, P., Bannach, D., Pirkl, G., Ferscha, A., et al. (2010) · 2010 Seventh International Conference on Networked Sensing Systems (INSS) · doi:10.1109/inss.2010.5573462 · Cited by 788
ModDrop: Adaptive Multi-Modal Gesture Recognition
Neverova, N., Wolf, C., Taylor, G., & Nebout, F. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2461544 · Cited by 420
(2015) · doi:10.1145/2808196.2811642 · Cited by 178
Temporal Multimodal Learning in Audiovisual Speech Recognition
Hu, D., Li, X., & Lu, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.389 · Cited by 108
Research works printed but not linked: 19
- 10.1109/CVPRW.2015.7301344 · DOI
- 10.1109/34.982900 · DOI · Paper page
- ngiam, 2011, Multimodal deep learning, Proceedings of the 28th International Conference on Machine Learning (ICML-11), 689
- patterson, 2002, Cuave: A new audio-visual database for multimodal human-computer interface research, Acoustics Speech and Signal Processing (ICASSP) 2002 IEEE International Conference on, 2, ii-2017
- ren, 2016, Look listen and learn-a multimodal lstm for speaker identification
- sohn, 2014, Improved multimodal deep learning with variation of information, Advances in neural information processing systems, 2141
- chandar, 2015, Correlational neural networks, Neural Computation
- bahdanau, 2014, Neural machine translation by jointly learning to align and translate, ICLR 2015, abs 1409 473
- 10.1162/0899766042321814 · DOI · Paper page
- 10.3115/v1/D14-1179 · DOI · Paper page
- 10.1109/JPROC.2015.2459017 · DOI · Paper page
- andrew, 2013, Deep canonical correlation analysis, Proceedings of the 30th International Conference on Machine Learning, 1247
- kiros, 2014, Multimodal neural language models, Proceedings of the 31st International Conference on Machine Learning (ICML-14), 595
- 10.1109/WACV.2014.6836053 · DOI
- 10.1109/ICCV.2015.26 · DOI
- srivastava, 2012, Multimodal learning with deep boltzmann machines, Advances in neural information processing systems, 2222
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- sutskever, 2014, Sequence to sequence learning with neural networks, Advances in neural information processing systems, 3104
- wang, 2015, On deep multi-view representation learning, Proceedings of the 32nd International Conference on Machine Learning (ICML-15), 1083
Cited by
Multimodal intelligence: Representation learning, information fusion, and applications
Zhang, C., Yang, Z., He, X., & Deng, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987728 · Cited by 511
Audio-Visual Event Localization in Unconstrained Videos
Tian, Y., Shi, J., Li, B., Duan, Z., & Xu, C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01216-8_16 · Cited by 493
Lee, M. A., Zhu, Y., Srinivasan, K., Shah, P., Savarese, S., Fei-Fei, L., Garg, A., & Bohg, J. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793485 · Cited by 349
“A popular representation learning objective is reconstruction of the raw sensory input [11, 27, 33, 57].”
BackgroundState representation learning for control: An overview
Lesort, T., Díaz-Rodríguez, N., Goudou, J.-F., & Filliat, D. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.006 · Cited by 301
A Review on Explainability in Multimodal Deep Neural Nets
Joshi, G., Walambe, R., & Kotecha, K. (2021) · IEEE Access · doi:10.1109/access.2021.3070212 · Cited by 204
“Individual modalities are mapped onto a common shared representation vector space either through joint or coordinated representation [49].”
BackgroundMulti-modal learning from unpaired images: application to multi-organ segmentation in CT and MRI
Valindria, V. V., Pawlowski, N., Rajchl, M., Lavdas, I., Aboagye, E. O., Rockall, A. G., Rueckert, D., & Glocker, B. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00066 · Cited by 146
“In computer vision, previous works have shown that multi modal learning often provides better performance [31, 30, 27].”
BackgroundCross and learn: Cross-modal self-supervision
Sayed, N., Brattoli, B., & Ommer, B. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-12939-2_17 · Cited by 76
Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors
Lee, M. A., Tan, M., Zhu, Y., & Bohg, J. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561847 · Cited by 24
“classification objective for inference tasks [4, 7, 11, 38].”
Metadata
- Authors
- Yang, X., Ramesh, P., Chitta, R., Madhvanath, S., Bernal, E. A., & Luo, J.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 5066-5074
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2613677041
- Cited by
- 104
- References
- 6
- FWCI
- 3.48
- Type
- conference paper
- Language
- en
- Open access
- green
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.