MGIT Evaluation Server (OPE Mechanism with Tiny Version, Story Granularity)

Submit your tracking results on MGIT to this website and evaluate the performance. Leaderboard will be updated immediately once the results are evaluated.

Tracker

Short Name:

JointNLT

Long Name:

JointNLT

Method Description:

n/a

Project Page:

n/a

Paper URL:

https://openaccess.thecvf.com/content/CVPR2023/html/Zhou_Joint_Visual_Grounding_and_Tracking_With_Natural_Language_Specification_CVPR_2023_paper.html

Code URL:

https://github.com/lizhou-cs/JointNLT

Hardware:

Titan RTX

Language:

python

Author:

Official

LaTex Bibtex:

@inproceedings{zhou2023joint, title={Joint Visual Grounding and Tracking with Natural Language Specification}, author={Zhou, Li and Zhou, Zikun and Mao, Kaige and He, Zhenyu}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={23151--23160}, year={2023} }

Submissions (OPE Mechanism)

Submmition Count:

1 submissions.

Performance:

Method N-PRE PRE SRIoU SRDIoU SRGIoU Hz Hardware Language Date(UTC)↓ Reports
1 JointNLT 0.773 0.433 0.600 0.588 0.589 7.85 fps Titan RTX python 2024-01-21, 01:31:48 reports.json