TransCenter: Transformers With Dense Representations for Multiple-Object Tracking
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets' locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenterexhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and, comparisons to more naive alternatives and concurrent works. The code is made publicly available at https://github.com/yihongxu/transcenter.
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.
Integrity signals
Registry
Cites
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897
The Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 3×
“[10], drastically speeding up the convergence (10 ) and reducing the complexity.”
BackgroundMethodInfluentialDeformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027
Simple online and realtime tracking
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7533003 · Cited by 4,433
CornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_45 · Cited by 3,852
YOLOX: Exceeding YOLO Series in 2021
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021) · arXiv · doi:10.48550/arxiv.2107.08430 · Cited by 2,965
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics
Bernardin, K., & Stiefelhagen, R. (2008) · EURASIP Journal on Image and Video Processing · doi:10.1155/2008/246309 · Cited by 2,918
Pvt v2: Improved baselines with pyramid vision transformer
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0274-8 · Cited by 2,439 · cited 6×
“Instead, TransCenter leverages PVTv2 [73] as its encoder, the so-called PVT-Encoder .”
BackgroundMethodInfluentialMOT16: A Benchmark for Multi-Object Tracking
Milan, A., Leal-Taixe, L., Reid, I., Roth, S., & Schindler, K. (2016) · arXiv · doi:10.48550/arxiv.1603.00831 · Cited by 1,309 · cited 4×
“We use the standard split of the MOT17 [46] and MOT20 [11] datasets and the testset evaluation is obtained by submitting the results to the MOTChallenge web-site.”
BackgroundMethodInfluentialTransReID: Transformer-based Object Re-Identification
He, S., Luo, H., Wang, P., Wang, F., Li, H., & Jiang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01474 · Cited by 1,244
Tracking Without Bells and Whistles
Bergmann, P., Meinhardt, T., & Leal-Taixe, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00103 · Cited by 1,110
TrackFormer: Multi-Object Tracking with Transformers
Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00864 · Cited by 1,081
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
Hui, T.-W., Tang, X., & Loy, C. C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00936 · Cited by 817
MOT20: A benchmark for multi object tracking in crowded scenes
Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., & Leal-Taixé, L. (2020) · arXiv · doi:10.48550/arxiv.2003.09003 · Cited by 779
A mobile vision system for robust multi-person tracking
Ess, A., Leibe, B., Schindler, K., & Van Gool, L. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587581 · Cited by 721 · cited 2×
“All the models are pretrained on CrowdHuman [62] except for Fair-MOT [89] trained also on 5 D 1+ CH datasets, and ByteTrack additionally trained on ETH [14] and CityPersons [86].”
MethodCrowdHuman: A Benchmark for Detecting Human in a Crowd
Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., & Sun, J. (2018) · arXiv · doi:10.48550/arxiv.1805.00123 · Cited by 534 · cited 8×
“All the models are pretrained on CrowdHuman [62] except for Fair-MOT [89] trained also on 5 D 1+ CH datasets, and ByteTrack additionally trained on ETH [14] and CityPersons [86].”
MethodInfluentialChen, L., Ai, H., Zhuang, Z., & Shang, C. (2018) · 2018 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486597 · Cited by 530
Quasi-Dense Similarity Learning for Multiple Object Tracking
Pang, J., Qiu, L., Li, X., Chen, H., Li, Q., Darrell, T., & Yu, F. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00023 · Cited by 480 · cited 1×
“treats the person detection and Re-ID tasks equally and [48] uses quasi-dense proposals from anchor-based detectors to learn Re-ID features for MOT in a dense manner.”
MethodLearning to Track with Object Permanence
Tokmakov, P., Li, J., Burgard, W., & Gaidon, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01068 · Cited by 226
Multiple Object Tracking with Correlation Learning
Wang, Q., Zheng, Y., Pan, P., & Xu, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00387 · Cited by 215
Self-citationGSM: Graph Similarity Model for Multi-Object Tracking
Liu, Q., Chu, Q., Liu, B., & Yu, N. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/74 · Cited by 123
Cited by
ByteTrack: Multi-object Tracking by Associating Every Detection Box
Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20047-2_1 · Cited by 2,470
Metadata
- Authors
- Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., & Alameda-Pineda, X.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-06-01
- Volume
- 45
- Issue
- 6
- Pages
- 7820-7835
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4310467366
- Cited by
- 226
- References
- 30
- FWCI
- 15.22
- Type
- journal article
- 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
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.