Method and device for video dubbing

Applicant

TikTok

Auteurs

N/A

Titre

Method and device for video dubbing

Patent Number

CN111767431

Publication Date

2020

uri

https://patents.google.com/patent/CN111767431

Description

The embodiment of the invention discloses a method and device for video music matching. A specific embodiment of the method comprises the steps of obtaining a to-be-matched music video; inputting the to-be-matched video into a pre-trained video emotion classification model to obtain at least one piece of emotion classification information corresponding to the to-be-matched video and a probability corresponding to the emotion classification information; acquiring a to-be-recalled music information set corresponding to the to-be-matched music video, wherein each piece of music information in the to-be-recalled music information set corresponds to at least one emotion label; and generating a recalled music information list based on matching of the at least one piece of emotion classification information and probability corresponding to the to-be-matched music video and the emotion tags corresponding to the music information in the to-be-recalled music information set. According to the embodiment, the emotion dimension information of the video and the gameplay is fully utilized, so that the matching degree of the video music matching is effectively improved.

keywords

Emotion

Domaine de recherche

Computer Vision

Sentiment Analysis

Software Development

Données collectées (type source)

Image

Audio

Video

Concepts clés

Emotion

Méthode

Using image features extracted from the video, emotion is detected by performing a similarity comparison with preset classification features corresponding to the emotion classification information. The generated similarity may be used as the probability corresponding to the emotion classification information

Dispositif

Device

Objectifs du brevet

Determine/Identify Content Emotion

Personalize/Improve with emotion information