Trajectory Representation Learning

Trajectory Representation Learning is a computational framework within trajectory analysis that learns low-dimensional, semantically meaningful embeddings of spatiotemporal movement data by preserving essential sequential, spatial, and temporal patterns inherent in raw trajectory observations.

547

Publications

36.8K

Citations

1.9K

Authors

530

Institutions

Publications per year

2017–2026

452

Authors

1.9K

  1. GT
    Goce Trajcevski

    Iowa State University, United States

    9 publications · 452 citations

    9

    h-index

  2. FZ
    Fan Zhou

    University of Electronic Science and Technology of China, China

    9 publications · 452 citations

    9

    h-index

  3. KZ
    Kunpeng Zhang

    University of Maryland, College Park, United States

    8 publications · 427 citations

    8

    h-index

  4. RU
    Raquel Urtasun

    University of Toronto, Canada

    8 publications · 904 citations

    8

    h-index

  5. TZ
    Ting Zhong

    University of Electronic Science and Technology of China, China

    6 publications · 353 citations

    6

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 53 publications · 2.1K citations

    27

    h-index

  2. 20

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 969 citations

    12

    h-index

  4. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 13 publications · 506 citations

    12

    h-index

  5. Pattern Recognition

    11 publications · 456 citations

    11

    h-index

1–5