CoChat

Temporal Query Networks for Fine-grained Video Understanding

Open access
Zhang, Chuhan, Gupta, Ankush, Zisserman, Andrew · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 92

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr46437.2021.00446

Cites

21 of 21 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 21 references

Research works printed but not linked: 47

  1. 10.24963/ijcai.2018/513 · DOI
  2. ng, 2015, Beyond short snippets: Deep networks for video classification, Proc CVPR
  3. 10.1145/3077136.3080655 · DOI
  4. zhou, 2018, Temporal relational reasoning in videos, Proc ECCV
  5. 10.1109/CVPR.2018.00642 · DOI
  6. 10.1109/CVPR42600.2020.00877 · DOI · Paper page
  7. 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
  8. 10.1109/ICCV.2019.00633 · DOI · Paper page
  9. li, 2018, Resound: To-wards action recognition without representation bias, Proc ECCV
  10. 10.1609/aaai.v33i01.33018658 · DOI · Paper page
  11. 10.1145/3343031.3350971 · DOI
  12. 10.1109/CVPR.2019.00037 · DOI · Paper page
  13. 10.1109/ICCV.2019.00054 · DOI
  14. wu, 2020, Context-aware rcnn: A baseline for action detection in videos, Proc ECCV
  15. 10.1109/CVPR.2019.00853 · DOI
  16. 10.1109/CVPR.2017.360 · DOI · Paper page
  17. xie, 2018, Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification, Proc ECCV
  18. 10.1007/978-3-030-01267-0_41 · DOI
  19. xiong, 2020, On layer normalization in the transformer architecture, Proc ICML
  20. 10.1109/CVPR42600.2020.00067 · DOI · Paper page
  21. 10.1007/978-3-030-58607-2_44 · DOI
  22. 10.1109/CVPR.2017.149 · DOI · Paper page
  23. 10.1109/CVPRW.2019.00302 · DOI
  24. 10.1109/ICCV.2019.00756 · DOI · Paper page
  25. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, Proc ECCV
  26. 10.1109/CVPR42600.2020.00043 · DOI · Paper page
  27. vaswani, 2017, Attention is all you need, Proc NeurIPS
  28. 10.1109/TPAMI.2017.2712608 · DOI · Paper page
  29. 10.1109/TIT.1960.1057571 · DOI · Paper page
  30. tang, 2018, Non-local netvlad encoding for video classification, Proc ECCV
  31. 10.1109/ICCV.2019.00718 · DOI · Paper page
  32. 10.1109/CVPR42600.2020.00028 · DOI · Paper page
  33. 10.1109/ICCV.2017.563 · DOI · Paper page
  34. garcia, 2020, Knowledge-based video question answering with unsupervised scene descriptions, Proc ECCV
  35. 10.1109/CVPR.2019.00033 · DOI
  36. gong, 2014, Diverse sequential subset selection for supervised video summarization, Proc NeurIPS
  37. 10.1109/CVPR.2018.00633 · DOI · Paper page
  38. 10.1109/ICCV.2015.507 · DOI
  39. chen, 2020, Generative pretraining from pixels, Proc ICML
  40. choi, 2019, Why can’t i dance in the mall? learning to mitigate scene bias in action recognition, Proc NeurIPS
  41. 10.1109/CVPR42600.2020.01065 · DOI · Paper page
  42. 10.1109/CVPR42600.2020.00269 · DOI · Paper page
  43. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Proc NeurIPS
  44. sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity under-standing, Proc ECCV
  45. luo, 2019, Grouped spatial-temporal aggretation for efficient action recognition, Proc ICCV
  46. liu, 0, Use what you have: Video retrieval using representations from collaborative experts, Proc BMVC
  47. 10.1109/CVPR42600.2020.00990 · DOI · Paper page

Cited by

See all 92

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.