Memory-and-Anticipation Transformer for Online Action Understanding
Open accessThe 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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 1×
“The shallow gray row denotes the baseline setting without any interaction. tion [51], and token dropping [21].”
BackgroundPyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259 · cited 1×
“Transformers have proven successful in natural language processing [49], and researchers have shown increasing interest in its application to vision tasks [11, 48, 40, 53, 18, 37].”
BackgroundSelf-citationViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767 · cited 1×
“Several meth-ods have been proposed to use transformers for temporal modeling in video-related tasks [1, 2, 6, 28, 35, 36, 39, 52, 55, 65].”
BackgroundActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578
Longformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
Is Space-Time Attention All You Need for Video Understanding?
Bertasius, G., Wang, H., & Torresani, L. (2021) · arXiv · doi:10.48550/arxiv.2102.05095 · Cited by 1,663
Neuroscience-Inspired Artificial Intelligence
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017) · Neuron · doi:10.1016/j.neuron.2017.06.011 · Cited by 1,557 · cited 1×
“Additionally, anticipation may change as ongoing behavior progresses and memory is updated [41, 20].”
BackgroundMultiscale vision transformers
Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00675 · Cited by 1,407 · cited 1×
“MViT [13] builds a feature hierarchy by progressively expanding channel capacity and reducing video spatial-temporal resolution.”
Background
Research works printed but not linked: 45
- Cao, 2022, A circular window-based cascade transformer for online action detection, CoRR, abs/2208.14209 · arXiv
- Chen, 2022, Internvideo-ego4d: A pack of champion solutions to ego4d challenges, CoRR, abs/2211.09529 · arXiv
- Chen, 2023, Videollm: Modeling video sequence with large language models, CoRR, abs/2305.13292 · arXiv
- 10.1109/CVPR52688.2022.01930 · DOI
- 10.1007/978-3-319-46454-1_17 · DOI · Paper page
- Dosovitskiy, An image is worth 16x16 words: Transformers for image recognition at scale
- 10.1109/CVPR42600.2020.00089 · DOI
- 10.5244/C.31.92 · DOI · Paper page
- 10.1109/CVPR46437.2021.00195 · DOI
- 10.1109/ICCV48922.2021.01325 · DOI · Paper page
- 10.1109/CVPR52688.2022.01563 · DOI · Paper page
- Hinton, 2012, Improving neural networks by preventing co-adaptation of feature detectors, CoRR, abs/1207.0580 · arXiv
- 10.1109/TIP.2020.3007841 · DOI
- 10.1007/978-3-030-01225-0_46 · DOI
- 10.1109/CVPR42600.2020.01404 · DOI
- 10.1007/978-3-031-19772-7_21 · DOI
- Jiang, 2014, THUMOS challenge: Action recognition with a large number of classes
- Kay, 2017, The kinetics human action video dataset, CoRR, abs/1705.06950 · arXiv
- 10.1109/TPAMI.2022.3204808 · DOI
- 10.1109/ICCV51070.2023.00637 · DOI
- Lin, 2022, Egocentric video-language pretraining, CoRR, abs/2206.01670 · arXiv
- Liu, 2021, End-to-end temporal action detection with transformer, CoRR, abs/2106.10271 · arXiv
- 10.1109/CVPR.2018.00803 · DOI · Paper page
- 10.1038/445027a · DOI · Paper page
- 10.1007/978-3-030-58517-4_10 · DOI
- 10.1109/CVPR.2017.155 · DOI · Paper page
- 10.1109/ICCV.2015.530 · DOI
- Touvron, Training data-efficient image transformers & distillation through attention, 10347
- Vaswani, Attention is all you need, 30
- 10.1007/978-3-319-46484-8_2 · DOI · Paper page
- 10.1007/978-3-031-20053-3_17 · DOI
- Wang, Long short-term transformer for online action detection
- 10.1109/CVPR52688.2022.01322 · DOI · Paper page
- 10.1109/ICCV.2019.00563 · DOI · Paper page
- Xu, Long short-term transformer for online action detection
- 10.1109/CVPR52688.2022.01240 · DOI
- 10.1109/CVPR52688.2022.01595 · DOI
- 10.1109/CVPR52688.2022.00316 · DOI
- 10.1007/978-3-030-58610-2_30 · DOI · Paper page
- 10.1007/978-3-031-19772-7_29 · DOI · Paper page
- 10.1007/978-1-4899-7687-1_79 · DOI · Paper page
- 10.1109/ICCV48922.2021.01332 · DOI · Paper page
- Zhao, 2020, Privileged knowledge distillation for online action detection, CoRR, abs/2011.09158 · arXiv
- 10.1007/978-3-031-19830-4_28 · DOI
- Zhao, 2022, Learning video representations from large language models, CoRR, abs/2212.04501 · arXiv
Cited by
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Song, E., Chai, W., Wang, G., Zhang, Y., Zhou, H., Wu, F., Chi, H., Guo, X., Ye, T., Zhang, Y., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01725 · Cited by 176
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Song, E., Chai, W., Wang, G., Zhang, Y., Zhou, H., Wu, F., Chi, H., Guo, X., Ye, T., Zhang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.16449 · Cited by 176
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Li, K., Wang, Y., Li, Y., Wang, Y., He, Y., Wang, L., & Qiao, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01826 · Cited by 143
Self-citationOnline Temporal Action Localization with Memory-Augmented Transformer
Song, Y., Kim, D., Cho, M., & Kwak, S. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72655-2_5 · Cited by 3
The AI Hippocampus: How Far are We From Human Memory?
Jia, Z., Li, J., Kang, Y., Wang, Y., Wu, T., Wang, Q., Wang, X., Zhang, S., Shen, J., Li, Q., et al. (2026) · arXiv · doi:10.48550/arxiv.2601.09113
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.