Temporal Query Networks for Fine-grained Video Understanding
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each query addresses a particular question, and has its own response label set.We make the following four contributions: (i) We propose a new model—a Temporal Query Network—which enables the query-response functionality, and a structural understanding of fine-grained actions. It attends to relevant segments for each query with a temporal attention mechanism, and can be trained using only the labels for each query. (ii) We propose a new way—stochastic feature bank update—to train a network on videos of various lengths with the dense sampling required to respond to fine-grained queries. (iii) we compare the TQN to other architectures and text supervision methods, and analyze their pros and cons. Finally, (iv) we evaluate the method extensively on the FineGym and Diving48 bench-marks for fine-grained action classification and surpass the state-of-the-art using only RGB features. Project page: https://www.robots.ox.ac.uk/~vgg/research/tqn/.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
The Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
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
Self-citationQuo 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
Self-citation3D 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
Research works printed but not linked: 47
- 10.24963/ijcai.2018/513 · DOI
- ng, 2015, Beyond short snippets: Deep networks for video classification, Proc CVPR
- 10.1145/3077136.3080655 · DOI
- zhou, 2018, Temporal relational reasoning in videos, Proc ECCV
- 10.1109/CVPR.2018.00642 · DOI
- 10.1109/CVPR42600.2020.00877 · DOI · Paper page
- li, 2018, Videolstm convolves, attends and flows for action recognition, Computer Vision and Image Understanding, 166, 41, 10.1016/j.cviu.2017.10.011 · DOI · Paper page
- 10.1109/ICCV.2019.00633 · DOI · Paper page
- li, 2018, Resound: To-wards action recognition without representation bias, Proc ECCV
- 10.1609/aaai.v33i01.33018658 · DOI · Paper page
- 10.1145/3343031.3350971 · DOI
- 10.1109/CVPR.2019.00037 · DOI · Paper page
- 10.1109/ICCV.2019.00054 · DOI
- wu, 2020, Context-aware rcnn: A baseline for action detection in videos, Proc ECCV
- 10.1109/CVPR.2019.00853 · DOI
- 10.1109/CVPR.2017.360 · DOI · Paper page
- xie, 2018, Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification, Proc ECCV
- 10.1007/978-3-030-01267-0_41 · DOI
- xiong, 2020, On layer normalization in the transformer architecture, Proc ICML
- 10.1109/CVPR42600.2020.00067 · DOI · Paper page
- 10.1007/978-3-030-58607-2_44 · DOI
- 10.1109/CVPR.2017.149 · DOI · Paper page
- 10.1109/CVPRW.2019.00302 · DOI
- 10.1109/ICCV.2019.00756 · DOI · Paper page
- wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, Proc ECCV
- 10.1109/CVPR42600.2020.00043 · DOI · Paper page
- vaswani, 2017, Attention is all you need, Proc NeurIPS
- 10.1109/TPAMI.2017.2712608 · DOI · Paper page
- 10.1109/TIT.1960.1057571 · DOI · Paper page
- tang, 2018, Non-local netvlad encoding for video classification, Proc ECCV
- 10.1109/ICCV.2019.00718 · DOI · Paper page
- 10.1109/CVPR42600.2020.00028 · DOI · Paper page
- 10.1109/ICCV.2017.563 · DOI · Paper page
- garcia, 2020, Knowledge-based video question answering with unsupervised scene descriptions, Proc ECCV
- 10.1109/CVPR.2019.00033 · DOI
- gong, 2014, Diverse sequential subset selection for supervised video summarization, Proc NeurIPS
- 10.1109/CVPR.2018.00633 · DOI · Paper page
- 10.1109/ICCV.2015.507 · DOI
- chen, 2020, Generative pretraining from pixels, Proc ICML
- choi, 2019, Why can’t i dance in the mall? learning to mitigate scene bias in action recognition, Proc NeurIPS
- 10.1109/CVPR42600.2020.01065 · DOI · Paper page
- 10.1109/CVPR42600.2020.00269 · DOI · Paper page
- simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Proc NeurIPS
- sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity under-standing, Proc ECCV
- luo, 2019, Grouped spatial-temporal aggretation for efficient action recognition, Proc ICCV
- liu, 0, Use what you have: Video retrieval using representations from collaborative experts, Proc BMVC
- 10.1109/CVPR42600.2020.00990 · DOI · Paper page
Cited by
BEVT: BERT Pretraining of Video Transformers
Wang, R., Chen, D., Wu, Z., Chen, Y., Dai, X., Liu, M., Jiang, Y.-G., Zhou, L., & Yuan, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01432 · Cited by 234
AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake
Yang, W., Zhou, X., Chen, Z., Guo, B., Ba, Z., Xia, Z., Cao, X., & Ren, K. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3262148 · Cited by 198
Motion-driven adaptive frame selection strategy for video action recognition
Ding, H., Guo, C., Sun, J., Jiang, X., Shi, H., & Li, J. (2025) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-025-00675-2 · Cited by 9
Metadata
- Authors
- Zhang, C., Gupta, A., & Zisserman, A.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 4484-4494
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3162565403
- Cited by
- 92
- References
- 21
- FWCI
- 6.06
- 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: Temporal Query Networks for Fine-grained Video Understanding. https://app.cochat.ai/papers/10.1109/cvpr46437.2021.00446
- The paper
- Zhang, C., Gupta, A., & Zisserman, A. (2021). Temporal Query Networks for Fine-grained Video Understanding. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr46437.2021.00446
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.