Corpus ID: 232135092

Fast Interactive Video Object Segmentation with Graph Neural Networks

@article{Varga2021FastIV,
  title={Fast Interactive Video Object Segmentation with Graph Neural Networks},
  author={Viktor Varga and A. Lorincz},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.03821}
}
Pixelwise annotation of image sequences can be very tedious for humans. Interactive video object segmentation aims to utilize automatic methods to speed up the process and reduce the workload of the annotators. Most contemporary approaches rely on deep convolutional networks to collect and process information from human annotations throughout the video. However, such networks contain millions of parameters and need huge amounts of labeled training data to avoid overfitting. Beyond that, label… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 52 REFERENCES
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks
Video Object Segmentation Using Space-Time Memory Networks
Reducing human efforts in video segmentation annotation with reinforcement learning
Video Segmentation with Just a Few Strokes
LIVEcut: Learning-based interactive video segmentation by evaluation of multiple propagated cues
Interactive Video Object Segmentation Using Global and Local Transfer Modules
...
1
2
3
4
5
...