TRIMMER proposes a self-supervised RL method for video summarization that uses entropy-based rewards to capture temporal dynamics and semantic diversity, claiming SOTA results among unsupervised approaches.
Summarizing videos using concentrated attention and considering the uniqueness and diversity of the video frames,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning
TRIMMER proposes a self-supervised RL method for video summarization that uses entropy-based rewards to capture temporal dynamics and semantic diversity, claiming SOTA results among unsupervised approaches.