Contrastive Multimodal Fusion with TupleInfoNCE
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
This paper proposes a method for representation learning of multimodal data using contrastive losses. A traditional approach is to contrast different modalities to learn the information shared among them. However, that approach could fail to learn the complementary synergies between modalities that might be useful for downstream tasks. Another approach is to concatenate all the modalities into a tuple and then contrast positive and negative tuple correspondences. However, that approach could consider only the stronger modalities while ignoring the weaker ones. To address these issues, we propose a novel contrastive learning objective, TupleInfoNCE. It contrasts tuples based not only on positive and negative correspondences, but also by composing new negative tuples using modalities describing different scenes. Training with these additional negatives encourages the learning model to examine the correspondences among modalities in the same tuple, ensuring that weak modalities are not ignored. We provide a theoretical justification based on mutual-information for why this approach works, and we propose a sample optimization algorithm to generate positive and negative samples to maximize training efficacy. We find that TupleInfoNCE significantly outperforms previous state of the arts on three different downstream tasks.
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
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 7,831
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020) · arXiv · doi:10.48550/arxiv.2006.09882 · Cited by 2,499
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
SUN RGB-D: A RGB-D scene understanding benchmark suite
Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943 · cited 7×
“Our second experiment investigates how TupleInfoNCE can be used for 3D object detection in the SUN RGB-D dataset [27].”
MethodInfluentialMultimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 3×
“We present results for three popular multi-modality tasks: semantic segmentation on NYUv2 [26], 3D object detection on SUN RGB-D [27], and sentiment analysis on MOSEI [36] and MOSI [35] in Section 5.”
MethodAutoAugment: Learning Augmentation Policies from Data
Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2018) · arXiv · doi:10.48550/arxiv.1805.09501 · Cited by 1,106
MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis
Hazarika, D., Zimmermann, R., & Poria, S. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413678 · Cited by 1,073 · cited 7×
“Table 1 shows that the previous best performing method MISA [9] improves the segmentation mIoU by 3.”
BackgroundMethodInfluentialMultimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.94 · Cited by 852 · cited 3×
“We present results for three popular multi-modality tasks: semantic segmentation on NYUv2 [26], 3D object detection on SUN RGB-D [27], and sentiment analysis on MOSEI [36] and MOSI [35] in Section 5.”
Method
Cited by
OpenScene: 3D Scene Understanding with Open Vocabularies
Peng, S., Genova, K., Jiang, C., Tagliasacchi, A., Pollefeys, M., & Funkhouser, T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00085 · Cited by 395
“A couple of works [36, 47] pretrain the 3D segmentation network using point-pixel pairs via contrastive learning between 2D and 3D features.”
BackgroundSelf-citationCosmo: contrastive fusion learning with small data for multimodal human activity recognition
Ouyang, X., Shuai, X., Zhou, J., Shi, I. W., Xie, Z., Xing, G., & Huang, J. (2022) · Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · doi:10.1145/3495243.3560519 · Cited by 94
CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
Zhang, J., Dong, R., & Ma, K. (2023) · 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw60793.2023.00219 · Cited by 62
Metadata
- Authors
- Liu, Y., Fan, Q., Zhang, S., Dong, H., Funkhouser, T., & Yi, L.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 734-743
- OpenAlex
- W3178535157
- Cited by
- 74
- References
- 18
- FWCI
- 4.33
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Contrastive Multimodal Fusion with TupleInfoNCE. https://app.cochat.ai/papers/10.1109/iccv48922.2021.00079
- The paper
- Liu, Y., Fan, Q., Zhang, S., Dong, H., Funkhouser, T., & Yi, L. (2021). Contrastive Multimodal Fusion with TupleInfoNCE. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.00079
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.