Object Discovery in Videos as Foreground Motion Clustering
arXiv:1812.02772
Abstract
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.
References in corpus (12)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Semantic Instance Segmentation with a Discriminative Loss Function
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- Semantic Instance Segmentation via Deep Metric Learning
- FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos
- Delving Deeper into Convolutional Networks for Learning Video Representations
- Learning Video Object Segmentation with Visual Memory
- A Detailed Rubric for Motion Segmentation
- Learning Features by Watching Objects Move
- Super-Trajectory for Video Segmentation
- Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation