Find Your ASMR: A Perceptual Retrieval Interface for Autonomous Sensory Meridian Response Videos

TL;DR

This paper introduces a perceptual retrieval system for ASMR videos that allows users to find content based on emotional and relaxation goals, improving retrieval satisfaction over traditional keyword methods.

Contribution

It presents a novel perceptual video retrieval interface for ASMR content and constructs a new affective response dataset for improved content matching.

Findings

Users can retrieve satisfactory ASMR videos more easily.

The system outperforms keyword-based retrieval in user satisfaction.

A new dataset with affective annotations is created.

Abstract

Autonomous sensory meridian response (ASMR) is a type of video contents designed to help people relax and feel comfortable. Users usually retrieve ASMR contents from various video websites using only keywords. However, it is challenging to examine satisfactory contents to reflect users' needs for ASMR videos using keywords or content-based retrieval. To solve this issue, we propose a perceptual video retrieval system for ASMR videos and provide a novel retrieval user interface that allows users to retrieve content according to watching purpose and anticipated expectations, such as excitement, calmness, stress and sadness. An ASMR video perception dataset is constructed with annotations on affective responses after watching the videos. To verify the proposed video retrieval system, a user study is conducted showing that users can retrieve satisfactory ASMR contents easily and efficiently compared to conventional keywords-based retrieval systems.