# Convolutional Hierarchical Attention Network for Query-Focused Video Summarization

Source: [Convolutional Hierarchical Attention Network for Query-Focused Video Summarization](<https://www.sota2.com/research/paper/68fa701b1e209131cea490e1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:00.107Z

Authors: Shuwen Xiao, Zhou Zhao, Zijian Zhang, Xiaohui Yan, Min Yang

Published: 2020-01-31T04:30:14.000Z

## Abstract

Previous approaches for video summarization mainly concentrate on finding the most diverse and representative visual contents as video summary without considering the user's preference. This paper addresses the task of query-focused video summarization, which takes user's query and a long video as inputs and aims to generate a query-focused video summary. In this paper, we consider the task as a problem of computing similarity between video shots and query. To this end, we propose a method, named Convolutional Hierarchical Attention Network (CHAN), which consists of two parts: feature encoding network and query-relevance computing module. In the encoding network, we employ a convolutional network with local self-attention mechanism and query-aware global attention mechanism to learns visual information of each shot. The encoded features will be sent to query-relevance computing module to generate queryfocused video summary. Extensive experiments on the benchmark dataset demonstrate the competitive performance and show the effectiveness of our approach.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Textual Query-driven Video Summarization on UTE (Textual Query Dataset) Video-1 1.0](<https://www.sota2.com/research/sota/textual-query-driven-video-summarization-on-ute-textual-query-dataset-video-1-1-0.md>): Textual Query-driven Video Summarization; UTE (Textual Query Dataset) Video-1 1.0; Precision: 54.73.

- [Textual Query-driven Video Summarization on UTE (Textual Query Dataset) 1.0 (Video-3)](<https://www.sota2.com/research/sota/textual-query-driven-video-summarization-on-ute-textual-query-dataset-1-0-video-3.md>): Textual Query-driven Video Summarization; UTE (Textual Query Dataset) 1.0 (Video-3); Precision: 59.75.

- [Textual Query-driven Video Summarization on UTE (Textual Query Dataset) Average All Videos 1.0](<https://www.sota2.com/research/sota/textual-query-driven-video-summarization-on-ute-textual-query-dataset-average-all-videos-1-0.md>): Textual Query-driven Video Summarization; UTE (Textual Query Dataset) Average All Videos 1.0; Precision: 46.4.

- [Textual Query-driven Video Summarization on UTE 1.0 (Video-2)](<https://www.sota2.com/research/sota/textual-query-driven-video-summarization-on-ute-1-0-video-2.md>): Textual Query-driven Video Summarization; UTE 1.0 (Video-2); Precision: 0.4592.

- [Textual Query-driven Video Summarization on UTE Textual Query 1.0 (Video-4)](<https://www.sota2.com/research/sota/textual-query-driven-video-summarization-on-ute-textual-query-1-0-video-4.md>): Textual Query-driven Video Summarization; UTE Textual Query 1.0 (Video-4); Precision: 25.23.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.03740>)

[PDF](<https://arxiv.org/pdf/2002.03740.pdf>)