Video segmentation by detection for the 2019 Unsupervised DAVIS Challenge

Conference item

In this work, we present a new framework, video segmentation by detection (VSD), for tackling the problem of unsupervised video multi-object segmentation. Our model employs an object detector for automatic target discovery and a set of single-object trackers for the simultaneous tracking of all targets. While addressing the object re-identification problem, we observe that many of the objects of interest in the dataset are humans or human centric such as bicycles. As such, following a design philosophy that special purpose algorithms will always be better than general purpose ones, we explore whether we can leverage the rich existing research efforts on re-identifying humans to improve the results or exploit the spatial relations of human-centric objects to humans. The proposed method achieves the highest J -Mean of 0.535 and an overall second place in the unsupervised track of the 2019 DAVIS Challenge.

Authors: Yang, Z; Wang, Q; Bai, S; Hu, W; Torr, P

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: DAVIS: Densely Annotated VIdeo Segmentation
• Host title: 2019 DAVIS Challenge on Video Object Segmentation - CVPR Workshops, 2019
• Journal: 2019 DAVIS Challenge on Video Object Segmentation - CVPR Workshops, 2019
• Publication date: 2019-06-17
• Acceptance date: 2019-06-03
• Keywords: FFR