CoChat

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

Open access
Alwassel, Humam, Giancola, Silvio, Ghanem, Bernard · 2021 · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Cited by 123

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action classification tasks, making such features not necessarily suitable for temporal localization. In this work, we propose a novel supervised pretraining paradigm for clip features that not only trains to classify activities but also considers background clips and global video information to improve temporal sensitivity. Extensive experiments show that using features trained with our novel pretraining strategy significantly improves the performance of recent state-of-the-art methods on three tasks: Temporal Action Localization, Action Proposal Generation, and Dense Video Captioning. We also show that our pretraining approach is effective across three encoder architectures and two pretraining datasets. We believe video feature encoding is an important building block for localization algorithms, and extracting temporally-sensitive features should be of paramount importance in building more accurate models. The code and pretrained models are available on our project website.

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/iccvw54120.2021.00356

Cites

27 of 27 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 27 references

Research works printed but not linked: 64

  1. 10.1109/CVPR.2018.00751 · DOI · Paper page
  2. 10.1109/CVPR.2018.00675 · DOI · Paper page
  3. 10.1109/CVPR.2019.00037 · DOI · Paper page
  4. 10.1007/978-3-030-01252-6_29 · DOI
  5. 10.1109/CVPR.2018.00782 · DOI · Paper page
  6. 10.1007/978-3-319-46484-8_2 · DOI · Paper page
  7. 10.1145/3394171.3413860 · DOI
  8. 10.1109/CVPR.2018.00443 · DOI · Paper page
  9. 10.1109/CVPR.2019.01058 · DOI · Paper page
  10. 10.1109/ICCV.2017.617 · DOI · Paper page
  11. korbar, 2018, Cooperative learning of audio and video models from self-supervised synchronization, NeurIPS
  12. jain, 2020, Action-bytes: Learning from trimmed videos to localize actions, CVPR
  13. 10.1609/aaai.v34i07.6793 · DOI · Paper page
  14. 10.1109/ICCV.2017.83 · DOI · Paper page
  15. 10.1109/ICCV.2019.00633 · DOI · Paper page
  16. ren, 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, NeurIPS
  17. 10.1109/CVPR.2017.155 · DOI · Paper page
  18. 10.18653/v1/P19-1641 · DOI
  19. iashin, 2020, Multi-modal dense video captioning, cvprw
  20. 10.1007/978-3-030-01270-0_10 · DOI · Paper page
  21. iashin, 2020, A better use of audio-visual cues: Dense video captioning with bi-modal transformer, BMVC
  22. 10.1109/CVPR.2016.119 · DOI · Paper page
  23. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Advances in neural information processing systems
  24. 10.1016/j.cviu.2016.10.018 · DOI · Paper page
  25. 10.1109/CVPR42600.2020.01079 · doi:10.1109/cvpr42600.2020.01079 · Paper page
  26. 10.1109/ICCV.2019.00565 · DOI · Paper page
  27. alwassel, 2018, Action search: Spotting targets in videos and its application to temporal action localization, ECCV
  28. alwassel, 2018, Victor Escorcia, and Bernard Ghanem. Diagnosing error in temporal action detectors, ECCV
  29. 10.1109/CVPR.2019.01232 · DOI · Paper page
  30. 10.1109/ICME46284.2020.9102850 · DOI
  31. 10.1109/ICCV.2017.322 · DOI · Paper page
  32. 10.1109/ICCV.2019.00901 · DOI
  33. 10.1109/CVPR.2019.00675 · DOI
  34. 10.1109/ICCV.2019.00900 · DOI
  35. 10.1109/CVPR.2018.00556 · DOI
  36. 10.1109/CVPR.2019.00854 · DOI · Paper page
  37. 10.1007/978-3-030-01225-0_35 · DOI · Paper page
  38. 10.1109/WACV48630.2021.00336 · DOI
  39. 10.1109/CVPR.2014.326 · DOI
  40. 10.1609/aaai.v34i07.6815 · DOI · Paper page
  41. 10.1109/ICCV.2017.610 · DOI · Paper page
  42. 10.1007/978-3-319-46487-9_47 · DOI · Paper page
  43. 10.1109/TPAMI.2013.65 · DOI · Paper page
  44. 10.1007/978-3-030-01216-8_5 · DOI · Paper page
  45. yan, 2019, Stat: spatial-temporal attention mechanism for video captioning, TMM
  46. 10.1609/aaai.v34i07.6711 · DOI
  47. 10.1109/CVPR42600.2020.01017 · DOI · Paper page
  48. 10.1109/CVPR.2016.503 · DOI · Paper page
  49. xu, 2019, Text-to-clip video retrieval with early fusion and re-captioning, AAAI
  50. 10.1109/CVPR.2018.00911 · DOI · Paper page
  51. 10.1109/CVPR.2018.00636 · DOI · Paper page
  52. 10.1109/CVPR.2017.675 · DOI · Paper page
  53. 10.1007/978-3-030-58604-1_8 · DOI
  54. 10.1109/ICCV.2019.00719 · DOI · Paper page
  55. 10.1007/978-3-030-58548-8_25 · DOI
  56. 10.1007/978-3-030-58598-3_32 · DOI · Paper page
  57. 10.1109/CVPR42600.2020.01311 · DOI · Paper page
  58. 10.1109/CVPR.2018.00124 · DOI · Paper page
  59. 10.1109/ICCV.2019.00400 · DOI
  60. 10.1109/CVPR.2019.00372 · DOI · Paper page
  61. 10.1109/CVPR.2017.345 · DOI · Paper page
  62. 10.1109/ICCV.2019.00718 · DOI · Paper page
  63. 10.1609/aaai.v34i07.6829 · DOI · Paper page
  64. lin, 2018, Bsn: Boundary sensitive network for temporal action proposal generation, ECCV

Cited by

See all 123

Metadata

Authors
Alwassel, H., Giancola, S., & Ghanem, B.
Venue
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Publisher
IEEE
Published
2021-10
Pages
3166-3176
OpenAlex
W3107327400
Cited by
123
References
27
FWCI
8.06
Type
conference paper
Language
en
Open access
green
Funders
King Abdullah University of Science and Technology

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: TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks. https://app.cochat.ai/papers/10.1109/iccvw54120.2021.00356
The paper
Alwassel, H., Giancola, S., & Ghanem, B. (2021). TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/iccvw54120.2021.00356

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.