Corpus ID: 218763666

TAO: A Large-Scale Benchmark for Tracking Any Object

@article{Dave2020TAOAL,
  title={TAO: A Large-Scale Benchmark for Tracking Any Object},
  author={Achal Dave and Tarasha Khurana and Pavel Tokmakov and Cordelia Schmid and Deva Ramanan},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10356}
}
  • Achal Dave, Tarasha Khurana, +2 authors Deva Ramanan
  • Published 2020
  • Computer Science
  • ArXiv
  • For many years, multi-object tracking benchmarks have focused on a handful of categories. Motivated primarily by surveillance and self-driving applications, these datasets provide tracks for people, vehicles, and animals, ignoring the vast majority of objects in the world. By contrast, in the related field of object detection, the introduction of large-scale, diverse datasets (e.g., COCO) have fostered significant progress in developing highly robust solutions. To bridge this gap, we introduce… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 78 REFERENCES

    Long-term Tracking in the Wild: A Benchmark

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

    VIEW 2 EXCERPTS

    MOTS: Multi-Object Tracking and Segmentation

    VIEW 2 EXCERPTS

    Detect to Track and Track to Detect

    VIEW 20 EXCERPTS
    HIGHLY INFLUENTIAL

    Siamese Instance Search for Tracking

    VIEW 1 EXCERPT

    Flow-Guided Feature Aggregation for Video Object Detection

    VIEW 1 EXCERPT