CoChat

Audiovisual Masked Autoencoders

Open access
Georgescu, Mariana-Iuliana, Fonseca, Eduardo, Ionescu, Radu Tudor, Lucic, Mario, Schmid, Cordelia, Arnab, Anurag · 2023 · 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Cited by 44

The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.

Abstract

Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pre-training architectures and objectives within the masked autoencoding framework, motivated by the success of similar methods in natural language and image understanding. We show that we can achieve significant improvements on audiovisual downstream classification tasks, surpassing the state-of-the-art on VGGSound and AudioSet. Furthermore, we can leverage our audiovisual pretraining scheme for multiple unimodal downstream tasks using a single audiovisual pretrained model. We additionally demonstrate the transferability of our representations, achieving state-of-the-art audiovisual results on Epic Kitchens without pre-training specifically for this dataset.

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/iccv51070.2023.01479

Cites

33 of 33 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 33 references

Research works printed but not linked: 43

  1. Akbari, VATT: Transformers for multimodal self-supervised learning from raw video, audio and text
  2. Alayrac, Self-supervised multimodal versatile networks
  3. 10.1109/ICCV.2017.73 · DOI · Paper page
  4. 10.1007/978-3-030-01246-5_27 · DOI · Paper page
  5. Asano, Labelling unlabelled videos from scratch with multi-modal self-supervision
  6. Asano, Self-labelling via simultaneous clustering and representation learning
  7. Bao, BEiT: BERT pre-training of image transformers
  8. 10.1109/ICASSP40776.2020.9053174 · DOI · Paper page
  9. Chen, A simple framework for contrastive learning of visual representations
  10. 10.1109/ICASSP49357.2023.10095691 · DOI
  11. 10.1109/CVPR52688.2022.02070 · DOI
  12. Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
  13. 10.24963/ijcai.2020/78 · DOI · Paper page
  14. 10.1109/CVPR52729.2023.01003 · DOI
  15. 10.1109/CVPR52688.2022.01563 · DOI · Paper page
  16. 10.1109/ICPR48806.2021.9413035 · DOI · Paper page
  17. 10.2478/eletel-2014-0042 · DOI · Paper page
  18. 10.1109/CVPR42600.2020.00975 · DOI · Paper page
  19. Jaegle, Perceiver IO: A general architecture for structured inputs & outputs
  20. 10.1109/CVPR.2014.223 · DOI · Paper page
  21. 10.1109/ICASSP39728.2021.9413376 · DOI
  22. Korbar, Cooperative learning of audio and video models from self-supervised synchronization
  23. Lee, Compressive visual representations
  24. 10.1109/ICCV.2019.00718 · DOI · Paper page
  25. 10.1007/978-3-030-01216-8_12 · DOI · Paper page
  26. 10.1109/CVPR42600.2020.00990 · DOI · Paper page
  27. Nagrani, Attention bottlenecks for multimodal fusion
  28. 10.1109/CVPR.2016.278 · DOI · Paper page
  29. 10.1109/ICCV48922.2021.00944 · DOI
  30. Patrick, Keeping your eye on the ball: Trajectory attention in video transformers
  31. Radford, Learning transferable visual models from natural language super-vision
  32. Ramazanova, OWL (observe, watch, listen): Localizing actions in egocentric video via audiovisual temporal context, 10.1109/CVPRW59228.2023.00516 · DOI
  33. 10.1016/j.plrev.2010.04.006 · DOI · Paper page
  34. Simonyan, Two-stream convolutional networks for action recognition in videos
  35. 10.1109/CVPR52688.2022.01519 · DOI · Paper page
  36. 10.1109/ICASSP49357.2023.10096532 · DOI
  37. 10.1109/CVPR.2016.308 · DOI · Paper page
  38. 10.1007/978-3-030-01216-8_16 · DOI · Paper page
  39. Vaswani, Attention is all you need
  40. 10.1145/1390156.1390294 · DOI · Paper page
  41. 10.1109/CVPR42600.2020.01271 · DOI · Paper page
  42. Zellers, MERLOT: Multimodal neural script knowledge models
  43. 10.1007/978-3-319-46487-9_40 · DOI · Paper page

Cited by

See all 44

Metadata

Authors
Georgescu, M.-I., Fonseca, E., Ionescu, R. T., Lucic, M., Schmid, C., & Arnab, A.
Venue
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2023-10-01
Pages
16098-16108
OpenAlex
W4390874283
Cited by
44
References
33
FWCI
9.73
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: Audiovisual Masked Autoencoders. https://app.cochat.ai/papers/10.1109/iccv51070.2023.01479
The paper
Georgescu, M.-I., Fonseca, E., Ionescu, R. T., Lucic, M., Schmid, C., & Arnab, A. (2023). Audiovisual Masked Autoencoders. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.01479

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.