CoChat

Progressive Modality Reinforcement for Human Multimodal Emotion Recognition from Unaligned Multimodal Sequences

Lv, Fengmao, Chen, Xiang, Huang, Yanyong, Duan, Lixin, Lin, Guosheng · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 210

The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.

Abstract

Human multimodal emotion recognition involves time-series data of different modalities, such as natural language, visual motions, and acoustic behaviors. Due to the variable sampling rates for sequences from different modalities, the collected multimodal streams are usually unaligned. The asynchrony across modalities increases the difficulty on conducting efficient multimodal fusion. Hence, this work mainly focuses on multimodal fusion from unaligned multimodal sequences. To this end, we propose the Progressive Modality Reinforcement (PMR) approach based on the recent advances of crossmodal transformer. Our approach introduces a message hub to exchange information with each modality. The message hub sends common messages to each modality and reinforces their features via crossmodal attention. In turn, it also collects the reinforced features from each modality and uses them to generate a reinforced common message. By repeating the cycle process, the common message and the modalities’ features can progressively complement each other. Finally, the reinforced features are used to make predictions for human emotion. Comprehensive experiments on different human multimodal emotion recognition benchmarks clearly demonstrate the superiority of our approach.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr46437.2021.00258

Cites

10 of 10 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 10 references

Research works printed but not linked: 16

  1. 10.1109/CVPR42600.2020.01424 · DOI · Paper page
  2. ngiam, 2011, Multimodal deep learning, ICML, 689
  3. 10.3115/v1/D14-1162 · DOI · Paper page
  4. 10.1109/ICCV.2017.357 · DOI
  5. tien, 2018, Deep spatio-temporal feature fusion with compact bilinear pooling for multimodal emotion recognition, Comput Vis Image Underst, 174, 33, 10.1016/j.cviu.2018.06.005 · DOI · Paper page
  6. tien, 2017, Deep spatio-temporal features for multimodal emotion recognition, WACV, 1215
  7. tsai, 2019, Learning factorized multimodal representations, ICLRE
  8. 10.1109/TMI.2018.2878669 · DOI · Paper page
  9. 10.1109/ICCV.2017.547 · DOI
  10. 10.3115/v1/N15-1016 · DOI · Paper page
  11. 10.18653/v1/P18-1207 · DOI · Paper page
  12. baltrusaitis, 2016, Openface: An open source facial behavior analysis toolkit, WACV, 1
  13. vaswani, 2017, Attention is all you need, NIPS, 5998
  14. 10.1609/aaai.v33i01.33017216 · DOI · Paper page
  15. 10.1109/CVPR.2016.374 · DOI · Paper page
  16. 10.1109/CVPR.2005.77 · DOI · Paper page

Cited by

Metadata

Authors
Lv, F., Chen, X., Huang, Y., Duan, L., & Lin, G.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2021-06
Pages
2554-2562
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3169801598
Cited by
210
References
10
FWCI
31.90
Type
conference paper
Language
en
Open access
closed
Funders
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

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.