Tracking Any Object Dataset
TAO is a federated dataset for Tracking Any Object, containing 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. A bottom-up approach was used for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks.
The dataset was annotated by labelling tracks for objects that move at any point in the video, and giving names to them post factum.
Source: TAO: A Large-Scale Benchmark for Tracking Any Object
Variants: TAO
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Multi-Object Tracking | AED (Co-DETR) | Associate Everything Detected: Facilitating Tracking-by-Detection … | 2024-09-14 |
| Multi-Object Tracking | AED (RegionCLIP) | Associate Everything Detected: Facilitating Tracking-by-Detection … | 2024-09-14 |
| Multi-Object Tracking | GLEE-Plus | General Object Foundation Model for … | 2023-12-14 |
| Multi-Object Tracking | GLEE-Lite | General Object Foundation Model for … | 2023-12-14 |
| Multi-Object Tracking | GLEE-Pro | General Object Foundation Model for … | 2023-12-14 |
| Multi-Object Tracking | TETer-HTC | Tracking Every Thing in the … | 2022-07-26 |
| Multi-Object Tracking | TETer-SwinT | Tracking Every Thing in the … | 2022-07-26 |
| Multi-Object Tracking | TETer | Tracking Every Thing in the … | 2022-07-26 |
| Multi-Object Tracking | AOA | 1st Place Solution to ECCV-TAO-2020: … | 2021-01-20 |
Recent papers with results on this dataset: