CoChat
Sign Up
Cited by 1,428Video Surveillance and Tracking MethodsAutonomous Vehicle Technology and SafetyAdvanced Neural Network Applications

Tracking Objects as Points

Open access
Zhou, Xingyi, Koltun, Vladlen, Krähenbühl, Philipp·2020·Lecture Notes in Computer Science
DOI 10.1007/978-3-030-58548-8_28
Open this paper in CoChat — free accountOpen PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1007/978-3-030-58548-8_28

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Each public detection can possibly initialize a single track but only if its center point falls in the bounding box area of the corresponding track.

    “Each public detection can possibly initialize a single track but only if its center point falls in the bounding box area of the corresponding track.”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [69]

    Section 5.3 (p. 10) says a new trajectory is initialized only when it is near a public detection, and Appendix A.2 (p. 18) describes the condition as being near a provided bounding box. Neither passage specifies that a public detection initializes at most one track or that its center must fall inside the track’s bounding box. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • The authors of CenterTrack filter detections based on bounding box center distances (CD).

    “The authors of CenterTrack [69] filter detections based on bounding box center distances (CD).”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [69]

  • TrackFormer's frame association with track queries avoids postprocessing with heuristic greedy matching procedures or additional graph optimization.

    “Furthermore, the frame association with track queries avoids postprocessing with heuristic greedy matching procedures [69] or additional graph optimization [29].”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [69]

  • TrackFormer and point-based methods such as CenterTrack require a procedure for filtering track initializations by public detections in a comparable manner.

    “However, TrackFormer and point-based methods such as CenterTrack [69] require a procedure for filtering track initializations by public detections in a comparable manner.”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [69]

  • Removing track queries and training only for object detection, with tracks associated via greedy center distance matching as in [69], results in a drop of 3.0 MOTA and 14.1 IDF1.

    “The last row also removes track queries and is only trained for object detection. Tracks are associated via greedy center distance matching as in [69] resulting in a huge drop of -3.0 MOTA and -14.1 IDF1.”

    From TrackFormer: Multi-Object Tracking with Transformers (2022) · cites this paper as [69]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 41

  1. [1]1. Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: ICCV (2019)
  2. [5]5. Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: ECCV (2010)
  3. [6]6. Evangelidis, G.D., Psarakis, E.Z.: Parametric image alignment using enhanced correlation coefficient maximization. TPAMI (2008)
  4. [7]7. Fang, K., Xiang, Y., Li, X., Savarese, S.: Recurrent autoregressive networks for online multiobject tracking. In: WACV (2018)
  5. [10]10. Feng, W., Hu, Z., Wu, W., Yan, J., Ouyang, W.: Multi-object tracking with multiple cues and switcher-aware classification. arXiv:1901.06129 (2019) · arXiv
  6. [11]11. Fieraru, M., Khoreva, A., Pishchulin, L., Schiele, B.: Learning to refine human pose estimation. In: CVPR Workshops (2018)
  7. [12]12. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)
  8. [15]15. Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: Evolution of optical flow estimation with deep networks. In: CVPR (2017)
  9. [16]16. Kang, K., Li, H., Xiao, T., Ouyang, W., Yan, J., Liu, X., Wang, X.: Object detection in videos with tubelet proposal networks. In: CVPR (2017)
  10. [18]18. Karunasekera, H., Wang, H., Zhang, H.: Multiple object tracking with attention to appearance, structure, motion and size. IEEE Access (2019)
  11. [19]19. Keuper, M., Tang, S., Andres, B., Brox, T., Schiele, B.: Motion segmentation & multiple object tracking by correlation co-clustering. TPAMI (2018)
  12. [20]20. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. ICLR (2015)
  13. [21]21. Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: Fast encoders for object detection from point clouds. In: CVPR (2019)
  14. [22]22. Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: ECCV (2018)
  15. [23]23. Leal-Taix´ e, L., Canton-Ferrer, C., Schindler, K.: Learning by tracking: Siamese cnn for robust target association. In: CVPR Workshops (2016)
  16. [24]24. Leal-Taix´ e, L., Milan, A., Schindler, K., Cremers, D., Reid, I., Roth, S.: Tracking the trackers: an analysis of the state of the art in multiple object tracking. arXiv:1704.02781 (2017) · arXiv
  17. [27]27. Luiten, J., Fischer, T., Leibe, B.: Track to reconstruct and reconstruct to track. arXiv:1910.00130 (2019) · arXiv
  18. [29]29. Moon, G., Chang, J., Lee, K.M.: Posefix: Model-agnostic general human pose refinement network. In: CVPR (2019)
  19. [30]30. Ren, J., Chen, X., Liu, J., Sun, W., Pang, J., Yan, Q., Tai, Y .W., Xu, L.: Accurate single stage detector using recurrent rolling convolution. In: CVPR (2017)
  20. [31]31. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)
  21. [32]32. Sadeghian, A., Alahi, A., Savarese, S.: Tracking the untrackable: Learning to track multiple cues with long-term dependencies. In: ICCV (2017)
  22. [33]33. Schulter, S., Vernaza, P., Choi, W., Chandraker, M.: Deep network flow for multi-object tracking. In: CVPR (2017)
  23. [35]35. Sharma, S., Ansari, J.A., Murthy, J.K., Krishna, K.M.: Beyond pixels: Leveraging geometry and shape cues for online multi-object tracking. In: ICRA (2018)
  24. [36]36. Shi, J., Tomasi, C.: Good features to track. In: CVPR (1994)
  25. [37]37. Shi, S., Wang, X., Li, H.: Pointrcnn: 3D object proposal generation and detection from point cloud. In: CVPR (2019)
  26. [38]38. Simonelli, A., Bul` o, S.R.R., Porzi, L., L´ opez-Antequera, M., Kontschieder, P.: Disentangling monocular 3d object detection. In: ICCV (2019)
  27. [39]39. Son, J., Baek, M., Cho, M., Han, B.: Multi-object tracking with quadruplet convolutional neural networks. In: CVPR (2017)
  28. [41]41. Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person re-identification. In: CVPR (2017)
  29. [44]44. Tu, Z.: Auto-context and its application to high-level vision tasks. In: CVPR (2008)
  30. [46]46. Weng, X., Kitani, K.: A baseline for 3d multi-object tracking. arXiv:1907.03961 (2019) · arXiv
  31. [48]48. Xiang, Y., Alahi, A., Savarese, S.: Learning to track: Online multi-object tracking by decision making. In: ICCV (2015)
  32. [49]49. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: ECCV (2018)
  33. [50]50. Xu, J., Cao, Y., Zhang, Z., Hu, H.: Spatial-temporal relation networks for multi-object tracking. In: ICCV (2019)
  34. [51]51. Yang, F., Choi, W., Lin, Y.: Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers. In: CVPR (2016)
  35. [52]52. Yu, F., Li, W., Li, Q., Liu, Y ., Shi, X., Yan, J.: Poi: Multiple object tracking with high performance detection and appearance feature. In: ECCV Workshops (2016)
  36. [53]53. Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: CVPR (2018)
  37. [54]54. Zhang, W., Zhou, H., Sun, S., Wang, Z., Shi, J., Loy, C.C.: Robust multi-modality multiobject tracking. In: ICCV (2019)
  38. [55]55. Zhang, Z., Cheng, D., Zhu, X., Lin, S., Dai, J.: Integrated object detection and tracking with tracklet-conditioned detection. arXiv:1811.11167 (2018) · arXiv
  39. [56]56. Zhou, X., Wang, D., Kr¨ ahenb¨ uhl, P.: Objects as points. arXiv:1904.07850 (2019) · arXiv
  40. [57]57. Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv:1908.09492 (2019) · arXiv
  41. [58]58. Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., Yang, M.H.: Online multi-object tracking with dual matching attention networks. In: ECCV (2018)

Cited by

Sorted by citations

Authors
Zhou, X., Koltun, V., & Krähenbühl, P.
Affiliations
  • The University of Texas at Austin (US)
  • Intel (United States) (US)
Corresponding author
Zhou, Xingyi
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Published
2020
Pages
474-490
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-030-58548-8_28
OpenAlex
W3095753995
Cited by
1,428
References
13
Citations by year
2026: 139 · 2025: 260 · 2024: 302 · 2023: 262 · 2022: 266 · 2021: 181 · 2020: 18
FWCI
56.06
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Science Foundation (1845485)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
object tracking, temporal association, online tracking, real-time tracking, MOT17

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