A Generative Appearance Model for End-to-end Video Object Segmentation

Johnander, Joakim; Danelljan, Martin; Brissman, Emil; Khan, Fahad Shahbaz; Felsberg, Michael

doi:10.48550/arxiv.1811.11611

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The validation set contains 474 sequences with 65 seen classes in training set and 26 classes which are not included. We compare our results with previous published literature [46,20]. Our results are obtained by submitting to the official evaluation server.…”

Section: The Youtube-vos Benchmarkmentioning

confidence: 92%

Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

Zhou,

Huang,

Huang

et al. 2019

Preprint

View full text Add to dashboard Cite

Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame. Due to the large visual variations of objects in video and the lack of training samples, it remains a difficult task despite the upsurging development of deep learning. Toward solving the VOS problem, we bring in several new insights by the proposed unified framework consisting of object proposal, tracking and segmentation components. The object proposal network transfers objectness information as generic knowledge into VOS; the tracking network identifies the target object from the proposals; and the segmentation network is performed based on the tracking results with a novel dynamic-reference based model adaptation scheme. Extensive experiments have been conducted on the DAVIS'17 dataset and the YouTube-VOS dataset, our method achieves the state-of-the-art performance on several video object segmentation benchmarks. We make the code publicly available at https://github.com/ sydney0zq/PTSNet. * Equal contributions. The work was mainly done during an internship at Horizon Robotics.

show abstract

Section: The Youtube-vos Benchmarkmentioning

confidence: 92%