Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Mingfei, Yang, Linjie, Chang, Xiaojun, Yao, Lina, Wang, Heng
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.10300
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917912832376832
author Han, Mingfei
Yang, Linjie
Chang, Xiaojun
Yao, Lina
Wang, Heng
author_facet Han, Mingfei
Yang, Linjie
Chang, Xiaojun
Yao, Lina
Wang, Heng
contents A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video summarization, and multi-shot video question answering. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. Nevertheless, the generated imperfect summaries can already achieve competitive performance on existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10300
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
Han, Mingfei
Yang, Linjie
Chang, Xiaojun
Yao, Lina
Wang, Heng
Computer Vision and Pattern Recognition
A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video summarization, and multi-shot video question answering. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. Nevertheless, the generated imperfect summaries can already achieve competitive performance on existing video understanding tasks such as video question-answering, promoting an under-explored setting of video understanding with detailed summaries.
title Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.10300