SummDiff: Generative Modeling of Video Summarization with Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912639832031232 |
|---|---|
| author | Kim, Kwanseok Hahm, Jaehoon Kim, Sumin Sul, Jinhwan Kim, Byunghak Lee, Joonseok |
| author_facet | Kim, Kwanseok Hahm, Jaehoon Kim, Sumin Sul, Jinhwan Kim, Byunghak Lee, Joonseok |
| contents | Video summarization is a task of shortening a video by choosing a subset of frames while preserving its essential moments. Despite the innate subjectivity of the task, previous works have deterministically regressed to an averaged frame score over multiple raters, ignoring the inherent subjectivity of what constitutes a good summary. We propose a novel problem formulation by framing video summarization as a conditional generation task, allowing a model to learn the distribution of good summaries and to generate multiple plausible summaries that better reflect varying human perspectives. Adopting diffusion models for the first time in video summarization, our proposed method, SummDiff, dynamically adapts to visual contexts and generates multiple candidate summaries conditioned on the input video. Extensive experiments demonstrate that SummDiff not only achieves the state-of-the-art performance on various benchmarks but also produces summaries that closely align with individual annotator preferences. Moreover, we provide a deeper insight with novel metrics from an analysis of the knapsack, which is an important last step of generating summaries but has been overlooked in evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08458 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SummDiff: Generative Modeling of Video Summarization with Diffusion Kim, Kwanseok Hahm, Jaehoon Kim, Sumin Sul, Jinhwan Kim, Byunghak Lee, Joonseok Machine Learning Video summarization is a task of shortening a video by choosing a subset of frames while preserving its essential moments. Despite the innate subjectivity of the task, previous works have deterministically regressed to an averaged frame score over multiple raters, ignoring the inherent subjectivity of what constitutes a good summary. We propose a novel problem formulation by framing video summarization as a conditional generation task, allowing a model to learn the distribution of good summaries and to generate multiple plausible summaries that better reflect varying human perspectives. Adopting diffusion models for the first time in video summarization, our proposed method, SummDiff, dynamically adapts to visual contexts and generates multiple candidate summaries conditioned on the input video. Extensive experiments demonstrate that SummDiff not only achieves the state-of-the-art performance on various benchmarks but also produces summaries that closely align with individual annotator preferences. Moreover, we provide a deeper insight with novel metrics from an analysis of the knapsack, which is an important last step of generating summaries but has been overlooked in evaluation. |
| title | SummDiff: Generative Modeling of Video Summarization with Diffusion |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.08458 |