Detect or Track: Towards Cost-Effective Video Object Detection/Tracking

@inproceedings{Luo2019DetectOT,
  title={Detect or Track: Towards Cost-Effective Video Object Detection/Tracking},
  author={Hao Luo and Wenxuan Xie and Xinggang Wang and Wenjun Zeng},
  booktitle={AAAI},
  year={2019}
}
  • Hao Luo, Wenxuan Xie, +1 author Wenjun Zeng
  • Published in AAAI 2019
  • Computer Science
  • State-of-the-art object detectors and trackers are developing fast. Trackers are in general more efficient than detectors but bear the risk of drifting. A question is hence raised – how to improve the accuracy of video object detection/tracking by utilizing the existing detectors and trackers within a given time budget? A baseline is frame skipping – detecting every N-th frames and tracking for the frames in between. This baseline, however, is suboptimal since the detection frequency should… CONTINUE READING
    16 Citations
    Video Object Detection via Object-Level Temporal Aggregation
    • PDF
    Single Shot Video Object Detector
    • 1
    • PDF
    AVOT: Audio-Visual Object Tracking of Multiple Objects for Robotics
    • J. Wilson, M. Lin
    • Computer Science
    • 2020 IEEE International Conference on Robotics and Automation (ICRA)
    • 2020
    • 2
    Rethinking Temporal Object Detection from Robotic Perspectives
    • 1
    • PDF
    A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
    • 9
    • PDF
    Object Guided External Memory Network for Video Object Detection
    • 13
    • PDF
    OmniTrack: Real-Time Detection and Tracking of Objects, Text and Logos in Video
    • 3
    • PDF

    References

    SHOWING 1-10 OF 52 REFERENCES
    Detect to Track and Track to Detect
    • 233
    • Highly Influential
    • PDF
    Flow-Guided Feature Aggregation for Video Object Detection
    • 237
    • PDF
    Object Detection in Videos with Tubelet Proposal Networks
    • 105
    • PDF
    Object Tracking Benchmark
    • 1,836
    • PDF
    Object Detection in Videos by High Quality Object Linking
    • 29
    Seq-NMS for Video Object Detection
    • 131
    • PDF
    MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
    • 441
    • PDF
    Learning to Track: Online Multi-object Tracking by Decision Making
    • 439
    • PDF