• Corpus ID: 221818840

Discriminative Segmentation Tracking Using Dual Memory Banks

@article{Xie2020DiscriminativeST,
  title={Discriminative Segmentation Tracking Using Dual Memory Banks},
  author={Fei Xie and Wankou Yang and Bo Liu and Kaihua Zhang and Wanli Xue and Wangmeng Zuo},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.09669}
}
Existing template-based trackers usually localize the target in each frame with bounding box, thereby being limited in learning pixel-wise representation and handling complex and non-rigid transformation of the target. Further, existing segmentation tracking methods are still insufficient in modeling and exploiting dense correspondence of target pixels across frames. To overcome these limitations, this work presents a novel discriminative segmentation tracking architecture equipped with dual… 
1 Citations
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
TLDR
A dynamic compact memory embedding is proposed to enhance the discrimination of the segmentation-based deformable visual tracking method and employs a point-to-global matching strategy to measure the correlation between the pixel-wise query features and the whole template, so as to capture more detailed deformation information.

References

SHOWING 1-10 OF 47 REFERENCES
D3S – A Discriminative Single Shot Segmentation Tracker
TLDR
Without per-dataset finetuning and trained only for segmentation as the primary output, D3S outperforms all trackers on VOT2016, VOT2018 and GOT-10k benchmarks and performs close to the state-of-the-artTrackers on the TrackingNet.
Learning Dynamic Memory Networks for Object Tracking
TLDR
A dynamic memory network to adapt the template to the target's appearance variations during tracking, which can be easily enlarged as the memory requirements of a task increase, which is favorable for memorizing long-term object information.
Learning Video Object Segmentation from Static Images
TLDR
It is demonstrated that highly accurate object segmentation in videos can be enabled by using a convolutional neural network (convnet) trained with static images only, and a combination of offline and online learning strategies are used.
Video Object Segmentation Using Space-Time Memory Networks
TLDR
This work proposes a novel solution for semi-supervised video object segmentation by leveraging memory networks and learning to read relevant information from all available sources to better handle the challenges such as appearance changes and occlussions.
Siamese Box Adaptive Network for Visual Tracking
TLDR
SiamBAN views the visual tracking problem as a parallel classification and regression problem, and thus directly classifies objects and regresses their bounding boxes in a unified FCN, making SiamB Ban more flexible and general.
High Performance Visual Tracking with Siamese Region Proposal Network
TLDR
The Siamese region proposal network (Siamese-RPN) is proposed which is end-to-end trained off-line with large-scale image pairs for visual object tracking and consists of SiAMESe subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch.
Fast Online Object Tracking and Segmentation: A Unifying Approach
TLDR
This method improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task, and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second.
Fast and Accurate Online Video Object Segmentation via Tracking Parts
TLDR
This paper proposes a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images, and performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.
Learning Discriminative Model Prediction for Tracking
TLDR
An end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction, derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations.
Hierarchical Representations with Discriminative Meta-filters in Dual Path Network for Tracking
TLDR
A novel dual path network with discriminative meta-filters and hierachical representations with superior performance compared with other state-of-the-arts methods is proposed.
...
...