computer-vision-7
Zero-Shot Single Object Tracking
3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in zero-shot-single-object-tracking-7
Trend
Dataset
Best Model
Actions
LaSOT
LaSOT
Libraries
iUse these libraries to find zero-shot-single-object-tracking-7 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Elysium: Exploring Object-level Perception in Videos via MLLM
Yongjie Ye, Hang Wang, Yanjie Wang, Yuxiang Nie, Can Huang•Sun Mar 24 2024
The proposed approach, Elysium: Exploring Object-level Perception in Videos via MLLM, is an end-to-end trainable MLLM that attempts to conduct object-level tasks in videos without requiring any additional plug-in or expert models.
39