CoChat

Multi-shot Temporal Event Localization: a Benchmark

Liu, Xiaolong, Hu, Yao, Bai, Song, Ding, Fei, Bai, Xiang, Torr, Philip H.S. · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 79

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In this paper, we propose a new and challenging task called multi-shot temporal event localization, and accordingly, collect a large-scale dataset called MUlti-Shot EventS (MUSES). MUSES has 31,477 event instances for a total of 716 video hours. The core nature of MUSES is the frequent shot cuts, for an average of 19 shots per instance and 176 shots per video, which induces large intra-instance variations. Our comprehensive evaluations show that the state-of-the-art method in temporal action localization only achieves an mAP of 13.1% at IoU=0.5. As a minor contribution, we present a simple baseline approach for handling the intra-instance variations, which reports an mAP of 18.9% on MUSES and 56.9% on THUMOS14 at IoU=0.5. To facilitate research in this direction, we release the dataset and the project code at https://songbai.site/muses/.

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/cvpr46437.2021.01241

Cites

29 of 29 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

Research works printed but not linked: 59

  1. wu, 2020, Context-aware rcnn: A baseline for action detection in videos, ECCV
  2. wang, 2020, Boundary-aware cascade networks for temporal action segmentation, ECCV
  3. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, ECCV, 20
  4. 10.1109/CVPR.2017.678 · DOI · Paper page
  5. 10.1109/ICCV.2017.617 · DOI · Paper page
  6. 10.1109/CVPR42600.2020.01017 · DOI · Paper page
  7. 10.1109/CVPR.2017.634 · DOI · Paper page
  8. 10.1007/978-3-030-58517-4_5 · DOI
  9. xie, 2018, Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification, ECCV, 305
  10. 10.1109/CVPR42600.2020.00067 · DOI · Paper page
  11. 10.1109/CVPR.2019.00035 · DOI
  12. 10.1109/ICCV.2017.472 · DOI · Paper page
  13. shou, 2018, Autoloc: Weakly-supervised temporal action localization in untrimmed videos, ECCV, 154
  14. sigurdsson, 2016, Hollywood in homes: Crowdsourcing data collection for activity understanding, ECCV, 510
  15. 10.1109/CVPR.2016.119 · DOI · Paper page
  16. huang, 2020, Movienet: A holistic dataset for movie understanding, ECCV
  17. 10.1109/ICCV.2017.393 · DOI · Paper page
  18. 10.1109/ICCV.2017.620 · DOI · Paper page
  19. 10.1109/ICCV.2013.396 · DOI · Paper page
  20. 10.1109/CVPR.2018.00675 · DOI · Paper page
  21. alwassel, 2018, Diagnosing error in temporal action detectors, ECCV, 256
  22. 10.1109/TPAMI.2007.70711 · DOI · Paper page
  23. 10.1109/ICCV.2015.169 · DOI · Paper page
  24. 10.1109/CVPR.2018.00633 · DOI · Paper page
  25. hoai, 2014, Thread-safe: Towards recognizing human actions across shot boundaries, ACCV, 222
  26. 10.1109/CVPR.2017.338 · DOI
  27. 10.1109/CVPR.2018.00706 · DOI · Paper page
  28. 10.1109/CVPR.2017.155 · DOI · Paper page
  29. 10.1109/CVPR42600.2020.00269 · DOI · Paper page
  30. 10.1109/ICPR.2004.1334462 · DOI · Paper page
  31. 10.1007/s11263-015-0851-8 · DOI · Paper page
  32. qiu, 2017, Learning spatio-temporal representation with pseudo-3d residual networks, ICCV, 5533
  33. paul, 2018, Wtalc Weakly-supervised temporal activity localization and classification, ECCV
  34. 10.1109/CVPR.2018.00124 · DOI · Paper page
  35. 10.1109/ICCV.2019.00718 · DOI · Paper page
  36. 10.1109/ICCV.2017.610 · DOI · Paper page
  37. escorcia, 2016, Daps: Deep action proposals for action understanding, ECCV, 768
  38. 10.1109/ICCV.2019.00562 · DOI
  39. 10.1109/TPAMI.2006.79 · DOI · Paper page
  40. 10.1109/CVPR.2017.342 · DOI
  41. feichtenhofer, 2016, Spatiotemporal residual networks for video action recognition, NIPS, 3468
  42. 10.1109/CVPR.2016.337 · DOI · Paper page
  43. gao, 2018, Ctap: Complementary temporal action proposal generation, ECCV
  44. 10.1145/2733373.2806221 · DOI
  45. bojanowski, 2014, Weakly supervised action labeling in videos under ordering constraints, ECCV, 628
  46. 10.1109/CVPR.2016.319 · DOI · Paper page
  47. alwassel, 2018, Action search: Spotting actions in videos and its application to temporal action localization, ECCV, 251
  48. 10.1109/CVPR.2017.675 · DOI · Paper page
  49. 10.1109/ICCV.2019.00719 · DOI · Paper page
  50. 10.1109/TPAMI.2019.2901464 · DOI · Paper page
  51. 10.1109/CVPR.2016.211 · DOI · Paper page
  52. 10.1109/ICCV.2019.00876 · DOI · Paper page
  53. 10.1007/978-3-030-58598-3_32 · DOI · Paper page
  54. 10.1109/CVPR.2019.00372 · DOI · Paper page
  55. 10.1109/LSP.2020.3037796 · DOI
  56. 10.1109/CVPR.2016.214 · DOI · Paper page
  57. 10.1145/3123266.3123343 · DOI · Paper page
  58. 10.1109/CVPR.2019.00139 · DOI · Paper page
  59. lin, 2018, Bsn: Boundary sensitive network for temporal action proposal generation, ECCV

Cited by

See all 79

Metadata

Authors
Liu, X., Hu, Y., Bai, S., Ding, F., Bai, X., & Torr, P. H. S.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2021-06
Pages
12591-12601
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3172347581
Cited by
79
References
29
FWCI
5.98
Type
conference paper
Language
en
Open access
closed

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.