In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach.
SOTA for Visual Object Tracking on VOT2017/18
Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.
#8 best model for Visual Object Tracking on VOT2017/18
During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.
#4 best model for Visual Object Tracking on VOT2017/18
Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation.
In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously.
Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent.
Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed.
These regularities are hard to label for training supervised machine learning algorithms; consequently, algorithms need to learn these regularities from the real world in an unsupervised way.
Compared with SRDCF, STRCF with hand-crafted features provides a 5 times speedup and achieves a gain of 5. 4% and 3. 6% AUC score on OTB-2015 and Temple-Color, respectively.
#2 best model for Visual Object Tracking on VOT2017/18