VidTr: Video Transformer Without Convolutions
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatiotemporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3× while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention (pooltopK_std), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“The early research on video based action recognition relies on 2D convolutions [28].”
Background3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Ucf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
SlowFast Networks for Video Recognition
Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00630 · Cited by 4,007
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664 · cited 1×
“Inspired by the R(2+1)D convolution that breaks down 3D convolution kernel to a spatial kernel and a temproal kernel [50], we further introduce our separable-attention, which performs spatial and temporal attention separately.”
MethodViViT: 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 2×
“Some more recent work [2, 4, 4, 16, 40, 42] further studied the multi-scale and different attention factorization methods.”
BackgroundTokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021) · arXiv · doi:10.48550/arxiv.2101.11986 · Cited by 2,415
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415
Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2021) · arXiv · doi:10.48550/arxiv.2106.13230 · Cited by 2,294
Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00320 · Cited by 2,294
Longformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
An Empirical Study of Training Self-Supervised Vision Transformers
Chen, X., Xie, S., & He, K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00950 · Cited by 1,648 · cited 1×
“Further combining the advantage of VidTr and convolution for better local-global action modeling [38, 57] and adopt self-supervised training [9] on large-scaled data will be our future work.”
MethodThe “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.622 · Cited by 1,471
Quantifying Attention Flow in Transformers
Abnar, S., & Zuidema, W. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.385 · Cited by 995
Multi-modal Transformer for Video Retrieval
Gabeur, V., Sun, C., Alahari, K., & Schmid, C. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58548-8_13 · Cited by 615
Neimark, D., Bar, O., Zohar, M., & Asselmann, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00355 · Cited by 551 · cited 1×
“Different from very recent work [41] that extract spatial feature with vision transformer on every video frames and then aggregate feature with attention, our proposed method jointly learns spatio-temporal feature with lower computational cost and higher performance.”
MethodA Short Note on the Kinetics-700-2020 Human Action Dataset
Smaira, L., Carreira, J., Noland, E., Clancy, E., Wu, A., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.10864 · Cited by 334
Cited by
Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00320 · Cited by 2,294
Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2021) · arXiv · doi:10.48550/arxiv.2106.13230 · Cited by 2,294
UniFormer: Unifying Convolution and Self-Attention for Visual Recognition
Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., Li, H., & Qiao, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3282631 · Cited by 616
Human Action Recognition From Various Data Modalities: A Review
Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., & Liu, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183112 · Cited by 601
Multiview Transformers for Video Recognition
Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., & Schmid, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00333 · Cited by 312
“…[52] 79.4 94.4 – – SlowFast R101-NL [23] 79.8 93.9 10 × 3 7.02 X3D-XXL [22] 80.4 94.6 SlowFast R50 [23,77] 61.7 – TimeSformer-HR [6] 62.5 – VidTR [83] 63.0 – ViViT-L FE [3] 65.9 89.9 MViT [21] 67.7 90.9 MFormer-L [51] 68 increasing t for all other views) will roughly reduce the input tokens by…”
Influential
Metadata
- Authors
- Zhang, Y., Li, X., Liu, C., Shuai, B., Zhu, Y., Brattoli, B., Chen, H., Marsic, I., & Tighe, J.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Volume
- 2021
- Pages
- 13557-13567
- OpenAlex
- W3204419213
- Cited by
- 211
- References
- 24
- FWCI
- 14.90
- 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
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.