Hierarchical Multimodal Transformer to Summarize Videos

Benchmark Model Rank Results
supervised-video-summarization-on-summeHMT–F1-score (Canonical): 44.1F1-score (Augmented): 44.8…
supervised-video-summarization-on-tvsumHMT–F1-score (Canonical): 60.1F1-score (Augmented): 60.3…