HIPPO-Video contributes 2,040 LLM-simulated watch-history and saliency-score pairs, and the HiPHer model uses these histories to beat generic and query-based baselines on the new benchmark.
Scaling up video summarization pretraining with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting
HIPPO-Video contributes 2,040 LLM-simulated watch-history and saliency-score pairs, and the HiPHer model uses these histories to beat generic and query-based baselines on the new benchmark.