CoChat

Memory-and-Anticipation Transformer for Online Action Understanding

Open access
Wang, Jiahao, Chen, Guo, Huang, Yifei, Wang, Limin, Lu, Tong · 2023 · 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Cited by 61

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Abstract

Most existing forecasting systems are memory-based methods, which attempt to mimic human forecasting ability by employing various memory mechanisms and have progressed in temporal modeling for memory dependency. Nevertheless, an obvious weakness of this paradigm is that it can only model limited historical dependence and can not transcend the past. In this paper, we rethink the temporal dependence of event evolution and propose a novel memory-anticipation-based paradigm to model an entire temporal structure, including the past, present, and future. Based on this idea, we present Memory-and-Anticipation Transformer (MAT), a memory-anticipation-based approach, to address the online action detection and anticipation tasks. In addition, owing to the inherent superiority of MAT, it can process online action detection and anticipation tasks in a unified manner. The proposed MAT model is tested on four challenging benchmarks TVSeries, THUMOS’14, HDD, and EPIC-Kitchens-100, for online action detection and anticipation tasks, and it significantly outperforms all existing methods. Code is available at https://github.com/Echo0125/Memory-and-Anticipation-Transformer.

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/iccv51070.2023.01271

Cites

20 of 20 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 20 references

Research works printed but not linked: 45

  1. Cao, 2022, A circular window-based cascade transformer for online action detection, CoRR, abs/2208.14209 · arXiv
  2. Chen, 2022, Internvideo-ego4d: A pack of champion solutions to ego4d challenges, CoRR, abs/2211.09529 · arXiv
  3. Chen, 2023, Videollm: Modeling video sequence with large language models, CoRR, abs/2305.13292 · arXiv
  4. 10.1109/CVPR52688.2022.01930 · DOI
  5. 10.1007/978-3-319-46454-1_17 · DOI · Paper page
  6. Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
  7. 10.1109/CVPR42600.2020.00089 · DOI
  8. 10.5244/C.31.92 · DOI · Paper page
  9. 10.1109/CVPR46437.2021.00195 · DOI
  10. 10.1109/ICCV48922.2021.01325 · DOI · Paper page
  11. 10.1109/CVPR52688.2022.01563 · DOI · Paper page
  12. Hinton, 2012, Improving neural networks by preventing co-adaptation of feature detectors, CoRR, abs/1207.0580 · arXiv
  13. 10.1109/TIP.2020.3007841 · DOI
  14. 10.1007/978-3-030-01225-0_46 · DOI
  15. 10.1109/CVPR42600.2020.01404 · DOI
  16. 10.1007/978-3-031-19772-7_21 · DOI
  17. Jiang, 2014, THUMOS challenge: Action recognition with a large number of classes
  18. Kay, 2017, The kinetics human action video dataset, CoRR, abs/1705.06950 · arXiv
  19. 10.1109/TPAMI.2022.3204808 · DOI
  20. 10.1109/ICCV51070.2023.00637 · DOI
  21. Lin, 2022, Egocentric video-language pretraining, CoRR, abs/2206.01670 · arXiv
  22. Liu, 2021, End-to-end temporal action detection with transformer, CoRR, abs/2106.10271 · arXiv
  23. 10.1109/CVPR.2018.00803 · DOI · Paper page
  24. 10.1038/445027a · DOI · Paper page
  25. 10.1007/978-3-030-58517-4_10 · DOI
  26. 10.1109/CVPR.2017.155 · DOI · Paper page
  27. 10.1109/ICCV.2015.530 · DOI
  28. Touvron, Training data-efficient image transformers & distillation through attention, 10347
  29. Vaswani, Attention is all you need, 30
  30. 10.1007/978-3-319-46484-8_2 · DOI · Paper page
  31. 10.1007/978-3-031-20053-3_17 · DOI
  32. Wang, Long short-term transformer for online action detection
  33. 10.1109/CVPR52688.2022.01322 · DOI · Paper page
  34. 10.1109/ICCV.2019.00563 · DOI · Paper page
  35. Xu, Long short-term transformer for online action detection
  36. 10.1109/CVPR52688.2022.01240 · DOI
  37. 10.1109/CVPR52688.2022.01595 · DOI
  38. 10.1109/CVPR52688.2022.00316 · DOI
  39. 10.1007/978-3-030-58610-2_30 · DOI · Paper page
  40. 10.1007/978-3-031-19772-7_29 · DOI · Paper page
  41. 10.1007/978-1-4899-7687-1_79 · DOI · Paper page
  42. 10.1109/ICCV48922.2021.01332 · DOI · Paper page
  43. Zhao, 2020, Privileged knowledge distillation for online action detection, CoRR, abs/2011.09158 · arXiv
  44. 10.1007/978-3-031-19830-4_28 · DOI
  45. Zhao, 2022, Learning video representations from large language models, CoRR, abs/2212.04501 · arXiv

Cited by

See all 61

Metadata

Authors
Wang, J., Chen, G., Huang, Y., Wang, L., & Lu, T.
Venue
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2023-10-01
Pages
13778-13789
OpenAlex
W4390873483
Cited by
61
References
20
FWCI
6.94
Type
conference paper
Language
en
Open access
green
Funders
National Natural Science Foundation of China

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: Memory-and-Anticipation Transformer for Online Action Understanding. https://app.cochat.ai/papers/10.1109/iccv51070.2023.01271
The paper
Wang, J., Chen, G., Huang, Y., Wang, L., & Lu, T. (2023). Memory-and-Anticipation Transformer for Online Action Understanding. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.01271

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.