CoChat

Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos

Fan, Hehe, Yang, Yi, Kankanhalli, Mohan · 2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 210

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

Point cloud videos exhibit irregularities and lack of order along the spatial dimension where points emerge inconsistently across different frames. To capture the dynamics in point cloud videos, point tracking is usually employed. However, as points may flow in and out across frames, computing accurate point trajectories is extremely difficult. Moreover, tracking usually relies on point colors and thus may fail to handle colorless point clouds. In this paper, to avoid point tracking, we propose a novel Point 4D Transformer (P4Transformer) network to model raw point cloud videos. Specifically, P4Transformer consists of (i) a point 4D convolution to embed the spatio-temporal local structures presented in a point cloud video and (ii) a transformer to capture the appearance and motion information across the entire video by performing self-attention on the embedded local features. In this fashion, related or similar local areas are merged with attention weight rather than by explicit tracking. Extensive experiments, including 3D action recognition and 4D semantic segmentation, on four benchmarks demonstrate the effectiveness of our P4Transformer for point cloud video modeling.

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/cvpr46437.2021.01398

Cites

24 of 24 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 24 references

Research works printed but not linked: 45

  1. 10.1109/CVPRW.2013.76 · DOI · Paper page
  2. ng, 2015, Beyond short snippets: Deep networks for video classification, CVPR
  3. 10.1109/CVPR.2017.391 · DOI · Paper page
  4. 10.1109/TIP.2017.2785279 · DOI · Paper page
  5. 10.1109/TPAMI.2019.2898954 · DOI · Paper page
  6. 10.1109/TPAMI.2019.2916873 · DOI · Paper page
  7. liu, 2019, Meteor-net: Deep learning on dynamic 3d point cloud sequences, ICCV
  8. 10.1109/CVPR.2018.00127 · DOI · Paper page
  9. liu, 2021, A universal representation transformer layer for few-shot image classification, ICLRE
  10. 10.1109/CVPR.2019.00985 · DOI · Paper page
  11. 10.1109/CVPR.2014.108 · DOI · Paper page
  12. 10.1016/j.ins.2018.12.050 · DOI
  13. 10.1109/CVPR.2018.00295 · DOI · Paper page
  14. 10.1109/CVPRW.2010.5543273 · DOI · Paper page
  15. 10.1109/ICCV.2019.00730 · DOI · Paper page
  16. 10.1016/j.neunet.2020.11.003 · DOI
  17. 10.1145/3343031.3351040 · DOI
  18. li, 2018, Pointcnn: Convolution on x-transformed points, NeurIPS
  19. 10.1109/AVSS.2019.8909840 · DOI
  20. 10.1007/978-3-030-01234-2_21 · DOI
  21. 10.5244/C.22.99 · DOI · Paper page
  22. 10.1109/CVPR.2019.00371 · DOI · Paper page
  23. li, 2018, Unsupervised learning of view-invariant action representations, NeurIPS
  24. 10.1109/ICCV.2019.00651 · DOI · Paper page
  25. 10.1109/CVPR42600.2020.00059 · DOI
  26. 10.1109/TMM.2018.2818329 · DOI · Paper page
  27. wang, 2016, Temporal segment networks: Towards good practices for deep action recognition, ECCV
  28. 10.1109/CVPR.2012.6247813 · DOI · Paper page
  29. 10.1007/978-3-642-33275-3_31 · DOI · Paper page
  30. vaswani, 2017, Attention is all you need, NeurIPS
  31. 10.1109/CVPR.2018.00675 · DOI · Paper page
  32. du, 2021, VTNet: Visual transformer network for object goal navigation, ICLRE
  33. 10.1109/CVPR.2013.98 · DOI · Paper page
  34. 10.1109/ICCV.2017.86 · DOI
  35. 10.24963/ijcai.2018/98 · DOI
  36. fan, 2021, PSTNet: Point spatio-temporal convolution on point cloud sequences, ICLRE
  37. 10.1109/TCSVT.2021.3058688 · DOI
  38. 10.1109/CVPR.2018.00685 · DOI · Paper page
  39. 10.1109/CVPR.2019.00319 · DOI · Paper page
  40. dai, 2017, Scan-net: Richly-annotated 3d reconstructions of indoor scenes, CVPR
  41. 10.1109/CVPR.2019.00810 · DOI · Paper page
  42. 10.1109/CVPR.2019.00132 · DOI · Paper page
  43. 10.1109/CVPR.2019.01230 · DOI · Paper page
  44. qi, 2017, Pointnet: Deep learning on point sets for 3d classification and segmentation, CVPR
  45. qi, 2017, Pointnet++: Deep hierarchical feature learning on point sets in a metric space, NeurIPS

Cited by

Metadata

Authors
Fan, H., Yang, Y., & Kankanhalli, M.
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2021-06
Pages
14199-14208
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3168718178
Cited by
210
References
24
FWCI
29.60
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.