Early vs Late Fusion in Multimodal Convolutional Neural Networks
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Combining machine learning in neural networks with multimodal fusion strategies offers an interesting potential for classification tasks but the optimum fusion strategies for many applications have yet to be determined. Here we address this issue in the context of human activity recognition, making use of a state-of-the-art convolutional network architecture (Inception I3D) and a huge dataset (NTU RGB+D). As modalities we consider RGB video, optical flow, and skeleton data. We determine whether the fusion of different modalities can provide an advantage as compared to uni-modal approaches, and whether a more complex early fusion strategy can outperform the simpler late-fusion strategy by making use of statistical correlations between the different modalities. Our results show a clear performance improvement by multi-modal fusion and a substantial advantage of an early fusion strategy.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“This sort of network is basically a 2D image classification CNN which has the advantage of being pre-trainable on Imagenet [4].”
MethodLearning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“In recent years spatio-temporal 3D-CNN were introduced for processing multiple frames directly [5]–[8].”
Method3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148
Temporal Action Detection with Structured Segment Networks
Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., & Lin, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.317 · Cited by 892
Connectionist Temporal Modeling for Weakly Supervised Action Labeling
Huang, D.-A., Fei-Fei, L., & Niebles, J. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_9 · Cited by 226
Cited by
A Comparative Analysis of Early and Late Fusion for the Multimodal Two-Class Problem
Pereira, L. M., Salazar, A., & Vergara, L. (2023) · IEEE Access · doi:10.1109/access.2023.3296098 · Cited by 69
Radiology and multi-scale data integration for precision oncology
Paverd, H., Zormpas-Petridis, K., Clayton, H., Burge, S., & Crispin-Ortuzar, M. (2024) · npj Precision Oncology · doi:10.1038/s41698-024-00656-0 · Cited by 41
Multimodal Data Hybrid Fusion and Natural Language Processing for Clinical Prediction Models
Ye, J., Hai, J., Song, J., & Wang, Z. (2023) · doi:10.1101/2023.08.24.23294597 · Cited by 24
Dimitri, G. M. (2022) · Computers · doi:10.3390/computers11110163 · Cited by 22
Multimodal Fusion Refiner Networks
Sankaran, S., Yang, D., & Lim, S.-N. (2021) · arXiv · doi:10.48550/arxiv.2104.03435 · Cited by 10
“Several choices are available for fusion, including late fusion, mid-fusion or early fusion [14, 33].”
Background
Metadata
- Authors
- Gadzicki, K., Khamsehashari, R., & Zetzsche, C.
- Venue
- 2020 IEEE 23rd International Conference on Information Fusion (FUSION)
- Publisher
- IEEE
- Published
- 2020-07
- Pages
- 1-6
- OpenAlex
- W3086755561
- Cited by
- 232
- References
- 9
- FWCI
- 5.60
- Type
- conference paper
- Language
- en
- Open access
- closed
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.