Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 405

The DOI matches its Crossref record; 263 of the 263 references it cites were found in a registry or an index.

Deep Learning for Visual Tracking: A Comprehensive Survey

Open access
Marvasti-Zadeh, Seyed Mojtaba, Cheng, Li, Ghanei-Yakhdan, Hossein, Kasaei, Shohreh · 2022 · IEEE Transactions on Intelligent Transportation Systems

Abstract

Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years – predominantly by recentdeep learning(DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental characteristics, primary motivations, and contributions of DL-based methods are summarized from nine key aspects of: network architecture, network exploitation, network training for visual tracking, network objective, network output, exploitation of correlation filter advantages, aerial-view tracking, long-term tracking, and online tracking. Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized. Third, the state-of-the-art DL-based methods are comprehensively examined on a set of well-established benchmarks of OTB2013, OTB2015, VOT2018, LaSOT, UAV123, UAVDT, and VisDrone2019. Finally, by conducting critical analyses of these state-of-the-art trackers quantitatively and qualitatively, their pros and cons under various common scenarios are investigated. It may serve as a gentle use guide for practitioners to weigh when and under what conditions to choose which method(s). It also facilitates a discussion on ongoing issues and sheds light on promising research directions.

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/tits.2020.3046478

Cites

263 of 263 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

Items 201–263 of 263

Research works printed but not linked: 11

  1. 10.3390/s18010112 · doi:10.3390/s18010112
  2. 10.1007/978-3-540-76856-2_46 · doi:10.1007/978-3-540-76856-2_46
  3. 10.1109/ICIP.2018.8451332 · doi:10.1109/icip.2018.8451332
  4. Pu, Deep attentive tracking via reciprocative learning, 1931
  5. Jiang, Deep collaborative tracking networks, 87
  6. Ma, Multi-scale recurrent tracking via pyramid recurrent network and optical flow, 242
  7. 10.1109/CVPR42600.2020.00661 · DOI · Paper page
  8. 10.1109/ICRA40945.2020.9196943 · DOI
  9. Li, BUAA-PRO: A tracking dataset with pixel-level annotation, 249
  10. Li, Explicit inductive bias for transfer learning with convolutional networks, 2825
  11. Yoon, Lifelong learning with dynamically expandable networks, 1

Cited by

See all 405

Metadata

Authors
Marvasti-Zadeh, S. M., Cheng, L., Ghanei-Yakhdan, H., & Kasaei, S.
Venue
IEEE Transactions on Intelligent Transportation Systems
Published
2022-05
Volume
23
Issue
5
Pages
3943-3968
ISSN
  • 1524-9050 (ISSN-L)
  • 1558-0016
OpenAlex
W2990187711
Cited by
405
References
263
FWCI
26.54
Type
journal article
Language
en
Open access
green
Funders
  • University of Alberta Start-Up Grant, the NSERC Discovery (RGPIN-2019-04575)
  • University of Alberta–Huawei Joint Innovation Collaboration Grants

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.