Deep Spatio-Temporal Random Fields for Efficient Video Segmentation

July 03, 2018 ยท Declared Dead ยท ๐Ÿ› 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Siddhartha Chandra, Camille Couprie, Iasonas Kokkinos arXiv ID 1807.03148 Category cs.CV: Computer Vision Cross-listed cs.LG, stat.ML Citations 70 Venue 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Last Checked 2 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision

Died the same way โ€” ๐Ÿ‘ป Ghosted