Title-based Video Summarization (TVSum) dataset serves as a benchmark to validate video summarization techniques. It contains 50 videos of various genres (e.g., news, how-to, documentary, vlog, egocentric) and 1,000 annotations of shot-level importance scores obtained via crowdsourcing (20 per video).
129 PAPERS • 4 BENCHMARKS
The SumMe dataset is a video summarization dataset consisting of 25 videos, each annotated with at least 15 human summaries (390 in total).
120 PAPERS • 3 BENCHMARKS
Collects dense per-video-shot concept annotations.
4 PAPERS • 1 BENCHMARK