Standard
SemTrack: Large-Scale Dataset for Semantic Tracking in the Wild. / Wang, Pengfei; Hui, Xiaofei; Wu, Jing et al.
Computer Vision -- ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXIV. ed. / Aleš Leonardis; Elissa Ricci; Stefan Roth; Olga Russakovsky; Torsten Sattler; Gül Varol. Cham: Springer, 2024. p. 486-504 (Lecture Notes in Computer Science; Vol. 15082).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Wang, P, Hui, X, Wu, J, Yang, Z, Ong, KE, Zhao, X, Lu, B, Huang, D, Ling, E, Chen, W, Ma, KT, Hur, M
& Liu, J 2024,
SemTrack: Large-Scale Dataset for Semantic Tracking in the Wild. in A Leonardis, E Ricci, S Roth, O Russakovsky, T Sattler & G Varol (eds),
Computer Vision -- ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXIV. Lecture Notes in Computer Science, vol. 15082, Springer, Cham, pp. 486-504.
https://doi.org/10.1007/978-3-031-72691-0_27APA
Wang, P., Hui, X., Wu, J., Yang, Z., Ong, K. E., Zhao, X., Lu, B., Huang, D., Ling, E., Chen, W., Ma, K. T., Hur, M.
, & Liu, J. (2024).
SemTrack: Large-Scale Dataset for Semantic Tracking in the Wild. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.),
Computer Vision -- ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXIV (pp. 486-504). (Lecture Notes in Computer Science; Vol. 15082). Springer.
https://doi.org/10.1007/978-3-031-72691-0_27Vancouver
Wang P, Hui X, Wu J, Yang Z, Ong KE, Zhao X et al.
SemTrack: Large-Scale Dataset for Semantic Tracking in the Wild. In Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G, editors, Computer Vision -- ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXIV. Cham: Springer. 2024. p. 486-504. (Lecture Notes in Computer Science). Epub 2024 Nov 3. doi: 10.1007/978-3-031-72691-0_27
Author
Wang, Pengfei ; Hui, Xiaofei ; Wu, Jing et al. /
SemTrack : Large-Scale Dataset for Semantic Tracking in the Wild. Computer Vision -- ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXIV. editor / Aleš Leonardis ; Elissa Ricci ; Stefan Roth ; Olga Russakovsky ; Torsten Sattler ; Gül Varol. Cham : Springer, 2024. pp. 486-504 (Lecture Notes in Computer Science).
Bibtex
@inproceedings{9bbdb7cb4fea409599e36b9f37a86fd4,
title = "SemTrack: Large-Scale Dataset for Semantic Tracking in the Wild",
abstract = "Knowing merely where the target is located is not sufficient for many real-life scenarios. In contrast, capturing rich details about the tracked target via its semantic trajectory, i.e. who/what this target is interacting with and when, where, and how they are interacting over time, is especially crucial and beneficial for various applications (e.g., customer analytics, public safety). We term such tracking as Semantic Tracking and define it as tracking the target based on the user{\textquoteright}s input and then, most importantly, capturing the semantic trajectory of this target. Acquiring such information can have significant impacts on sales, public safety, etc. However, currently, there is no dataset for such comprehensive tracking of the target. To address this gap, we create SemTrack, a large and comprehensive dataset containing annotations of the target{\textquoteright}s semantic trajectory. The dataset contains 6.7 million frames from 6961 videos, covering a wide range of 52 different interaction classes with 115 different object classes spanning 10 different supercategories in 12 types of different scenes, including both indoor and outdoor environments. We also propose SemTracker, a simple and effective method, and incorporate a meta-learning approach to better handle the challenges of this task. Our dataset and code can be found at https://sutdcv.github.io/SemTrack.",
author = "Pengfei Wang and Xiaofei Hui and Jing Wu and Zile Yang and Ong, {Kian Eng} and Xinge Zhao and Beijia Lu and Dezhao Huang and Evan Ling and Weiling Chen and Ma, {Keng Teck} and Minhoe Hur and Jun Liu",
year = "2024",
month = dec,
day = "7",
doi = "10.1007/978-3-031-72691-0_27",
language = "English",
isbn = "9783031726910",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "486--504",
editor = "Leonardis, {Ale{\v s} } and Elissa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and G{\"u}l Varol",
booktitle = "Computer Vision -- ECCV 2024",
}
RIS
TY - GEN
T1 - SemTrack
T2 - Large-Scale Dataset for Semantic Tracking in the Wild
AU - Wang, Pengfei
AU - Hui, Xiaofei
AU - Wu, Jing
AU - Yang, Zile
AU - Ong, Kian Eng
AU - Zhao, Xinge
AU - Lu, Beijia
AU - Huang, Dezhao
AU - Ling, Evan
AU - Chen, Weiling
AU - Ma, Keng Teck
AU - Hur, Minhoe
AU - Liu, Jun
PY - 2024/12/7
Y1 - 2024/12/7
N2 - Knowing merely where the target is located is not sufficient for many real-life scenarios. In contrast, capturing rich details about the tracked target via its semantic trajectory, i.e. who/what this target is interacting with and when, where, and how they are interacting over time, is especially crucial and beneficial for various applications (e.g., customer analytics, public safety). We term such tracking as Semantic Tracking and define it as tracking the target based on the user’s input and then, most importantly, capturing the semantic trajectory of this target. Acquiring such information can have significant impacts on sales, public safety, etc. However, currently, there is no dataset for such comprehensive tracking of the target. To address this gap, we create SemTrack, a large and comprehensive dataset containing annotations of the target’s semantic trajectory. The dataset contains 6.7 million frames from 6961 videos, covering a wide range of 52 different interaction classes with 115 different object classes spanning 10 different supercategories in 12 types of different scenes, including both indoor and outdoor environments. We also propose SemTracker, a simple and effective method, and incorporate a meta-learning approach to better handle the challenges of this task. Our dataset and code can be found at https://sutdcv.github.io/SemTrack.
AB - Knowing merely where the target is located is not sufficient for many real-life scenarios. In contrast, capturing rich details about the tracked target via its semantic trajectory, i.e. who/what this target is interacting with and when, where, and how they are interacting over time, is especially crucial and beneficial for various applications (e.g., customer analytics, public safety). We term such tracking as Semantic Tracking and define it as tracking the target based on the user’s input and then, most importantly, capturing the semantic trajectory of this target. Acquiring such information can have significant impacts on sales, public safety, etc. However, currently, there is no dataset for such comprehensive tracking of the target. To address this gap, we create SemTrack, a large and comprehensive dataset containing annotations of the target’s semantic trajectory. The dataset contains 6.7 million frames from 6961 videos, covering a wide range of 52 different interaction classes with 115 different object classes spanning 10 different supercategories in 12 types of different scenes, including both indoor and outdoor environments. We also propose SemTracker, a simple and effective method, and incorporate a meta-learning approach to better handle the challenges of this task. Our dataset and code can be found at https://sutdcv.github.io/SemTrack.
U2 - 10.1007/978-3-031-72691-0_27
DO - 10.1007/978-3-031-72691-0_27
M3 - Conference contribution/Paper
SN - 9783031726910
T3 - Lecture Notes in Computer Science
SP - 486
EP - 504
BT - Computer Vision -- ECCV 2024
A2 - Leonardis, Aleš
A2 - Ricci, Elissa
A2 - Roth, Stefan
A2 - Russakovsky, Olga
A2 - Sattler, Torsten
A2 - Varol, Gül
PB - Springer
CY - Cham
ER -
