TRIM is a self-supervised video summarization framework that uses Markov-driven losses to achieve state-of-the-art unsupervised results on SUMME and TVSUM while rivaling top supervised models.
Pattern Recognition 111, 107677 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
TRIM is a self-supervised video summarization framework that uses Markov-driven losses to achieve state-of-the-art unsupervised results on SUMME and TVSUM while rivaling top supervised models.