An active learning criterion based on graph-cut estimates of false positives and false negatives, exploiting temporal coherence in video, improves frame selection for labeling in video object detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Temporal Coherence for Active Learning in Videos
An active learning criterion based on graph-cut estimates of false positives and false negatives, exploiting temporal coherence in video, improves frame selection for labeling in video object detection.