EmoMV dataset collection

The EmoMV dataset collection consisting of three datasets (EmoMV-A, EmoMV-B, and EmoMV-C) is constructed for affective correspondence learning between music and video modalities. This dataset collection was introduced in the paper titled "EmoMV: Affective Music-Video Correspondence Learning Datasets for Classification and Retrieval".

Related Organizations

Goethe University Frankfurt
Germany
Singapore University of Technology and Design
Singapore

Keywords

Multi-task learning deep neural networks, affective audio-visual correspondence learing, emotion-based matching, affective music-video retrieval, EmoMV dataset collection, affective computing

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average