Distractor Distilled Dataset
DiDi is a distractor-distilled tracking dataset created to address the limitation of low distractor presence in current visual object tracking benchmarks. To enhance the evaluation and analysis of tracking performance amidst distractors, we have semi-automatically distilled several existing benchmarks into the DiDi dataset. The dataset is available for download at this URL: https://go.vicos.si/didi
Variants: DiDi
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Object Tracking | DAM4SAM | A Distractor-Aware Memory for Visual … | 2024-11-26 |
| Visual Object Tracking | SAMURAI | SAMURAI: Adapting Segment Anything Model … | 2024-11-18 |
| Visual Object Tracking | SAM2.1Long | SAM2Long: Enhancing SAM 2 for … | 2024-10-21 |
| Visual Object Tracking | SAM2.1 | SAM 2: Segment Anything in … | 2024-08-01 |
| Visual Object Tracking | AQATrack | Autoregressive Queries for Adaptive Tracking … | 2024-03-15 |
| Visual Object Tracking | ODTrack | ODTrack: Online Dense Temporal Token … | 2024-01-03 |
| Visual Object Tracking | Cutie | Putting the Object Back into … | 2023-10-19 |
| Visual Object Tracking | KeepTrack | Learning Target Candidate Association to … | 2021-03-30 |
| Visual Object Tracking | TransT | Transformer Tracking | 2021-03-29 |
| Visual Object Tracking | AOT | AOT: Appearance Optimal Transport Based … | 2020-11-05 |
Recent papers with results on this dataset: