Papers › Hierarchical Multimodal Transformer to Summarize Videos
Hierarchical Multimodal Transformer to Summarize Videos
Bin Zhao, Maoguo Gong, Xuelong Li
Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance. Transformer is an effective model to deal with this problem, and surpasses RNN-based methods in several sequence modeling tasks, such as machine translation, video captioning, \emph{etc}. Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization, which can capture the dependencies among frame and shots, and summarize the video by exploiting the scene information formed by shots. Furthermore, we argue that both the audio and visual information are essential for the video summarization task. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT). Practically, extensive experiments show that HMT surpasses most of the traditional, RNN-based and attention-based video summarization methods.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Supervised Video Summarization | SumMe | HMT | F1-score (Augmented) | 44.8 | #18 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | HMT | F1-score (Canonical) | 44.1 | #18 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | HMT | Kendall's Tau | 0.079 | #18 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | SumMe | HMT | Spearman's Rho | 0.080 | #18 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | HMT | F1-score (Augmented) | 60.3 | #17 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | HMT | F1-score (Canonical) | 60.1 | #17 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | HMT | Kendall's Tau | 0.096 | #17 of 21 | Archive leaderboard | report |
| Supervised Video Summarization | TvSum | HMT | Spearman's Rho | 0.107 | #17 of 21 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections