SOTVerse: A User-defined Task Space of Single Object Tracking

@article{Hu2022SOTVerseAU,
  title={SOTVerse: A User-defined Task Space of Single Object Tracking},
  author={Shi-chang Hu and Xin Zhao and Kaiqi Huang},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.07414}
}
—Single object tracking (SOT) research falls into a cycle – trackers perform well on most benchmarks but quickly fail in challenging scenarios, causing researchers to doubt the insufficient data content and take more effort constructing larger datasets with more challenging situations. However, isolated experimental environments and limited evaluation methods more seriously hinder the SOT research. The former causes existing datasets can not be exploited comprehensively, while the latter… 
[PDF] Semantic Reader

References

SHOWING 1-10 OF 64 REFERENCES
Global Instance Tracking: Locating Target More Like Humans
TLDR
This article proposes the global instance tracking (GIT) task, which is supposed to search an arbitrary user-specified instance in a video without any assumptions about camera or motion consistency, to model the human visual tracking ability and designs a scientific evaluation procedure using human capabilities as the baseline to judge tracking intelligence.
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
TLDR
A large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k, and the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population, which ensures a comprehensive and relatively unbiased coverage of diverse moving objects.
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark
TLDR
The goal in releasing LaSOT is to provide a dedicated high quality platform for both training and evaluation of trackers, and to take advantage of the close connection between visual appearance and natural language, the largest densely annotated tracking benchmark to be presented.
Probabilistic Regression for Visual Tracking
TLDR
This work proposes a probabilistic regression formulation and applies it to tracking, which is capable of modeling label noise stemming from inaccurate annotations and ambiguities in the task and substantially improves the performance.
The Seventh Visual Object Tracking VOT2019 Challenge Results
The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art…
Learning Discriminative Model Prediction for Tracking
TLDR
An end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction, derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations.
The Sixth Visual Object Tracking VOT2018 Challenge Results
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are…
The Visual Object Tracking VOT2016 Challenge Results
TLDR
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
Object Tracking Benchmark
TLDR
An extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria is carried out to identify effective approaches for robust tracking and provide potential future research directions in this field.
Open-Ended Learning Leads to Generally Capable Agents
TLDR
The red player’s goal is to put both the purple cube and the black cube (its own cube) onto its base (the grey floor), while the blue player tries to put them on the blue floor – the cubes are used as flags.
...
...