mlsanityData to 7 Oct 2026

CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking

arXiv 2205.04261 ↗First posted 9 May 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking scenarios. Instead, long-term tracking settings have been substantially ignored by the solutions. In this paper, we explicitly consider long-term tracking scenarios and provide a framework, named CoCoLoT, that combines the characteristics of complementary visual trackers to achieve enhanced long-term tracking performance. CoCoLoT perceives whether the trackers are following the target object through an online learned deep verification model, and accordingly activates a decision policy which selects the best performing tracker as well as it corrects the performance of the failing one. The proposed methodology is evaluated extensively and the comparison with several other solutions reveals that it competes favourably with the state-of-the-art on the most popular long-term visual tracking benchmarks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

27 of 47 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  3. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  4. 2018LaSOT: A High-quality Benchmark for Large-scale Single Object Trackingcited by 424
  5. 2021Transformer Trackingcited by 412
  6. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  7. 2019Learning Discriminative Model Prediction for Trackingcited by 344
  8. 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
  9. 2016ECO: Efficient Convolution Operators for Trackingcited by 239
  10. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  11. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  12. 2019Siam R-CNN: Visual Tracking by Re-Detectioncited by 174
15 more
  1. 2017Need for Speed: A Benchmark for Higher Frame Rate Object Trackingcited by 137
  2. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  3. 2016Learning to Track at 100 FPS with Deep Regression Networkscited by 89
  4. 2020High-Performance Long-Term Tracking with Meta-Updatercited by 79
  5. 2020Graph Attention Trackingcited by 70
  6. 2019GlobalTrack: A Simple and Strong Baseline for Long-term Trackingcited by 57
  7. 2019'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Trackingcited by 34
  8. 2021Is First Person Vision Challenging for Object Tracking?cited by 21
  9. 2017Long-Term Visual Object Tracking Benchmarkcited by 11
  10. 2021Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophycited by 11
  11. 2021Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillationcited by 9
  12. 2019Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstratorcited by 8
  13. 2015Online Adaptive Hidden Markov Model for Multi-Tracker Fusioncited by 4
  14. 2020Robust Long-Term Object Tracking via Improved Discriminative Model Predictioncited by 4
  15. 2018Parallel Tracking and Verifyingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Tracking Skiers from the Top to the Bottomcited by 6
  2. 2023Visualizing Skiers' Trajectories in Monocular Videoscited by 1