Improving Sequential Determinantal Point Processes for Supervised Video Summarization
This work addresses the need for efficient video browsing, searching, and indexing by providing incremental improvements to an existing model for supervised video summarization.
The paper tackles the problem of supervised video summarization by improving the sequential determinantal point process (SeqDPP) model, introducing a large-margin algorithm to address exposure bias and a new probabilistic distribution to incorporate user-specified summary length, resulting in enhanced performance on an extended dataset of about 60 hours of videos.
It is now much easier than ever before to produce videos. While the ubiquitous video data is a great source for information discovery and extraction, the computational challenges are unparalleled. Automatically summarizing the videos has become a substantial need for browsing, searching, and indexing visual content. This paper is in the vein of supervised video summarization using sequential determinantal point process (SeqDPP), which models diversity by a probabilistic distribution. We improve this model in two folds. In terms of learning, we propose a large-margin algorithm to address the exposure bias problem in SeqDPP. In terms of modeling, we design a new probabilistic distribution such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary. Moreover, we also significantly extend a popular video summarization dataset by 1) more egocentric videos, 2) dense user annotations, and 3) a refined evaluation scheme. We conduct extensive experiments on this dataset (about 60 hours of videos in total) and compare our approach to several competitive baselines.