Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Deep Spatio-Temporal Random Fields for Efficient Video Segmentation

About

In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional Random Fields (GCRFs). Our method, called VideoGCRF is (a) efficient, (b) has a unique global minimum, and (c) can be trained end-to-end alongside contemporary deep networks for video understanding. We experiment with multiple connectivity patterns in the temporal domain, and present empirical improvements over strong baselines on the tasks of both semantic and instance segmentation of videos.

Siddhartha Chandra, Camille Couprie, Iasonas Kokkinos• 2018

Related benchmarks

TaskDatasetResultRank
Video Object SegmentationDAVIS 2016 (val)--
564
Semantic segmentationCamVid (test)
mIoU75.2
411
Video Object SegmentationDAVIS 2016 (test)
mIoU86.5
29
Video Object SegmentationDAVIS (val)--
28
Showing 4 of 4 rows

Other info

Code

Follow for update