Online Multi-Expert Learning for Visual Tracking
By Zhetao Li, Wei Wei, Tianzhu Zhang, Meng Wang, Sujuan Hou, Xin Peng. 2020
29 citations recorded by the source corpus.
The correlation filters based trackers have achieved an excellent performance for object tracking in recent years. However, most existing methods use only one filter but ignore the information of the previous filters. In this paper, we propose a novel online multi-expert learning algorithm for visual tracking. In our proposed scheme, there are former trackers which retain the previous filters, and those trackers will give their predictions in each frame. The current tracker represents the filter of current frame, and both the current tracker and the former trackers constitute our expert ensemble. We use an adaptive Second-order Quantile strategy to learn the weights of each expert, which can take full advantage of all the experts. To simplify our model and remove some bad experts, we prune our models via a minimum entropy criterion. Finally, we propose a new update strategy to avoid the model corruption problem. Extensive experimental results on both OTB2013 and OTB2015 benchmarks demonstrate that our proposed tracker performs favorably against state-of-the-art methods.
Subfields: Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning (2021, methodology): “In general, we obtain the refined prototypes θ p under the guidance of relation matrix [16] between the embeddings of new classes and the prototypes of old classes: Specifically, the embeddings and the old prototypes are first transformed into a shared latent space, where f t 1 and f t 2 represents a…”