Authors: Christopher Xie,Yu Xiang,Zaid Harchaoui,Dieter Fox
Where published:
CVPR 2019 6
ArXiv: 1812.02772
Document:
PDF
DOI
Abstract URL: http://arxiv.org/abs/1812.02772v2
We consider the problem of providing dense segmentation masks for object
discovery in videos. We formulate the object discovery problem as foreground
motion clustering, where the goal is to cluster foreground pixels in videos
into different objects. We introduce a novel pixel-trajectory recurrent neural
network that learns feature embeddings of foreground pixel trajectories linked
across time. By clustering the pixel trajectories using the learned feature
embeddings, our method establishes correspondences between foreground object
masks across video frames. To demonstrate the effectiveness of our framework
for object discovery, we conduct experiments on commonly used datasets for
motion segmentation, where we achieve state-of-the-art performance.