Hierarchical Multimodal Transformer to Summarize Videos
Open paper
Benchmark
Model
Rank
Results
supervised-video-summarization-on-summe
HMT
–
F1-score (Canonical): 44.1
F1-score (Augmented): 44.8
…
supervised-video-summarization-on-tvsum
HMT
–
F1-score (Canonical): 60.1
F1-score (Augmented): 60.3
…
Rank counts only results with a code link.