Video Summarization using Denoising Diffusion Probabilistic Model
This addresses the problem of annotation inconsistency in video summarization for researchers and practitioners, offering a novel generative approach that is incremental in improving robustness over discriminative methods.
The paper tackles video summarization by proposing a generative framework using Denoising Diffusion Probabilistic Models (DDPM) to reduce interference from subjective annotation noise, achieving strong generalization and effectiveness across multiple datasets like TVSum, SumMe, and FPVSum.
Video summarization aims to eliminate visual redundancy while retaining key parts of video to construct concise and comprehensive synopses. Most existing methods use discriminative models to predict the importance scores of video frames. However, these methods are susceptible to annotation inconsistency caused by the inherent subjectivity of different annotators when annotating the same video. In this paper, we introduce a generative framework for video summarization that learns how to generate summaries from a probability distribution perspective, effectively reducing the interference of subjective annotation noise. Specifically, we propose a novel diffusion summarization method based on the Denoising Diffusion Probabilistic Model (DDPM), which learns the probability distribution of training data through noise prediction, and generates summaries by iterative denoising. Our method is more resistant to subjective annotation noise, and is less prone to overfitting the training data than discriminative methods, with strong generalization ability. Moreover, to facilitate training DDPM with limited data, we employ an unsupervised video summarization model to implement the earlier denoising process. Extensive experiments on various datasets (TVSum, SumMe, and FPVSum) demonstrate the effectiveness of our method.