Warping and unioning class activation maps across successive web video frames generates proxy labels that lift weakly supervised segmentation to state-of-the-art mIoU of 67.4 on PASCAL VOC 2012.
Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combine this information with motion cues. The method overcomes the typical problems of weakly supervised/unsupervised video segmentation, such as scenes with no motion, dominant camera motion, and objects that move as a unit. In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object. We report results on four video segmentation datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
Warping and unioning class activation maps across successive web video frames generates proxy labels that lift weakly supervised segmentation to state-of-the-art mIoU of 67.4 on PASCAL VOC 2012.