A Unified Multi-Faceted Video Summarization System

TL;DR

This paper presents a unified, fast, and interactive multi-faceted video summarization system capable of generating various types of summaries, including key-frames, skims, and entity summaries, for videos, streams, and images.

Contribution

The paper introduces a scalable, explainable framework for multi-faceted video summarization that supports interactive, real-time generation of diverse summaries based on user preferences.

Findings

Summarizes hours of video data in a few seconds.

Supports interactive, customizable summaries of various types.

Demonstrates utility of different diversity, coverage, and representation models.

Abstract

This paper addresses automatic summarization and search in visual data comprising of videos, live streams and image collections in a unified manner. In particular, we propose a framework for multi-faceted summarization which extracts key-frames (image summaries), skims (video summaries) and entity summaries (summarization at the level of entities like objects, scenes, humans and faces in the video). The user can either view these as extractive summarization, or query focused summarization. Our approach first pre-processes the video or image collection once, to extract all important visual features, following which we provide an interactive mechanism to the user to summarize the video based on their choice. We investigate several diversity, coverage and representation models for all these problems, and argue the utility of these different mod- els depending on the application. While most of the prior work on submodular summarization approaches has focused on combining several models and learning weighted mixtures, we focus on the explain-ability of different the diversity, coverage and representation models and their scalability. Most importantly, we also show that we can summarize hours of video data in a few seconds, and our system allows the user to generate summaries of various lengths and types interactively on the fly.