VOT2016 is a video dataset for visual object tracking. It contains 60 video clips and 21,646 corresponding ground truth maps with pixel-wise annotation of salient objects.
Source: Video Saliency Detection by 3D Convolutional Neural Networks
Image Source: https://www.researchgate.net/profile/Mohamed_Abdelpakey/publication/327850473/figure/fig3/AS:674547829338114@1537836143562/Visual-results-on-VOT2016-data-set-for-four-sequences.png
Variants: VOT-2016, VOT2016
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Object Tracking | SE-SiamFC | Scale Equivariance Improves Siamese Tracking | 2020-07-17 |
| Visual Object Tracking | SiamMask_E | Fast Visual Object Tracking with … | 2019-07-08 |
| Visual Object Tracking | SiamVGG | SiamVGG: Visual Tracking using Deeper … | 2019-02-07 |
| Visual Object Tracking | SiamRPN+ | Deeper and Wider Siamese Networks … | 2019-01-07 |
| Visual Object Tracking | SiamFC-lu (Ours) | Learning to Update for Object … | 2018-06-19 |
| Visual Object Tracking | CFCF | Good Features to Correlate for … | 2017-04-20 |
Recent papers with results on this dataset:
