Language-Guided Music Recommendation for Video via Prompt Analogies

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F23%3A00372044" target="_blank" >RIV/68407700:21730/23:00372044 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/CVPR52729.2023.01420" target="_blank" >https://doi.org/10.1109/CVPR52729.2023.01420</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52729.2023.01420" target="_blank" >10.1109/CVPR52729.2023.01420</a>

Result language

angličtina

Original language name

Language-Guided Music Recommendation for Video via Prompt Analogies

Original language description

We propose a method to recommend music for an input video while allowing a user to guide music selection with free-form natural language. A key challenge of this problem setting is that existing music video datasets provide the needed (video, music) training pairs, but lack text descriptions of the music. This work addresses this challenge with the following three contributions. First, we propose a text-synthesis approach that relies on an analogy-based prompting procedure to generate natural language music descriptions from a large-scale language model (BLOOM-176B) given pre-trained music tagger outputs and a small number of human text descriptions. Second, we use these synthesized music descriptions to train a new trimodal model, which fuses text and video input representations to query music samples. For training, we introduce a text dropout regularization mechanism which we show is critical to model performance. Our model design allows for the re-trieved music audio to agree with the two input modalities by matching visual style depicted in the video and musical genre, mood, or instrumentation described in the natural language query. Third, to evaluate our approach, we collect a testing dataset for our problem by annotating a subset of 4k clips from the YT8M-Music Video dataset with natural language music descriptions which we make publicly available. We show that our approach can match or exceed the performance of prior methods on video-to-music retrieval while significantly improving retrieval accuracy when using text guidance.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-0130-4

ISSN

1063-6919

e-ISSN

2575-7075

Number of pages

10

Pages from-to

14784-14793

Publisher name

IEEE Computer Society

Place of publication

USA

Event location

Vancouver

Event date

Jun 18, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001062522107011