English
Related papers

Related papers: mir_ref: A Representation Evaluation Framework for…

200 papers

Multimodal representation learning has garnered significant attention in the AI community, largely due to the success of large pre-trained multimodal foundation models like LLaMA, GPT, Mistral, and CLIP. These models have achieved…

Information Retrieval · Computer Science 2025-04-22 Junchen Fu , Xuri Ge , Xin Xin , Haitao Yu , Yue Feng , Alexandros Karatzoglou , Ioannis Arapakis , Joemon M. Jose

The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric…

Sound · Computer Science 2019-09-19 Angelo C. Mendes da Silva , Mauricio A. Nunes , Raul Fonseca Neto

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the…

We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explore representations from Jukebox (Dhariwal et al. 2020): a…

Sound · Computer Science 2021-07-14 Rodrigo Castellon , Chris Donahue , Percy Liang

Performance evaluation in multimedia retrieval, as in the information retrieval domain at large, relies heavily on retrieval experiments, employing a broad range of techniques and metrics. These can involve human-in-the-loop and…

Information Retrieval · Computer Science 2024-10-10 Loris Sauter , Ralph Gasser , Heiko Schuldt , Abraham Bernstein , Luca Rossetto

This paper explores a specific sub-task of cross-modal music retrieval. We consider the delicate task of retrieving a performance or rendition of a musical piece based on a description of its style, expressive character, or emotion from a…

Sound · Computer Science 2024-01-29 Shreyan Chowdhury , Gerhard Widmer

Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering. Existing methods that leverage INRs are…

Machine Learning · Computer Science 2023-06-21 Filip Szatkowski , Karol J. Piczak , Przemysław Spurek , Jacek Tabor , Tomasz Trzciński

Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music…

Sound · Computer Science 2023-07-20 Charilaos Papaioannou , Emmanouil Benetos , Alexandros Potamianos

As digital music production has become mainstream, the selection of appropriate virtual instruments plays a crucial role in determining the quality of music. To search the musical instrument samples or virtual instruments that make one's…

Sound · Computer Science 2022-11-16 Kyungsu Kim , Minju Park , Haesun Joung , Yunkee Chae , Yeongbeom Hong , Seonghyeon Go , Kyogu Lee

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

Machine Learning · Computer Science 2026-05-08 Weien Li , Rui Song , Zeyu Li , Haochen Liu , Gonghao Zhang , Difan Jiao , Zhenwei Tang , Bowei He , Haolun Wu , Xue Liu , Ye Yuan

Word embedding has become an essential means for text-based information retrieval. Typically, word embeddings are learned from large quantities of general and unstructured text data. However, in the domain of music, the word embedding may…

Sound · Computer Science 2024-04-24 SeungHeon Doh , Jongpil Lee , Dasaem Jeong , Juhan Nam

There have been numerous attempts to represent raw data as numerical vectors that effectively capture semantic and contextual information. However, in the field of symbolic music, previous works have attempted to validate their music…

Sound · Computer Science 2023-06-08 Sangjun Han , Hyeongrae Ihm , Woohyung Lim

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive…

Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Tingyu Song , Yanzhao Zhang , Mingxin Li , Zhuoning Guo , Dingkun Long , Pengjun Xie , Siyue Zhang , Yilun Zhao , Shu Wu

Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolving underspecified references or matching compositional…

Information Retrieval · Computer Science 2026-02-10 Jianrui Zhang , Anirudh Sundara Rajan , Brandon Han , Soochahn Lee , Sukanta Ganguly , Yong Jae Lee

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored.…

What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR benchmark is to develop a general-purpose audio representation that provides a…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Sound · Computer Science 2021-04-05 Andres Ferraro , Xavier Favory , Konstantinos Drossos , Yuntae Kim , Dmitry Bogdanov

Towards improving the performance in various music information processing tasks, recent studies exploit different modalities able to capture diverse aspects of music. Such modalities include audio recordings, symbolic music scores,…

Multimedia · Computer Science 2019-02-15 Federico Simonetta , Stavros Ntalampiras , Federico Avanzini

For Music Information Retrieval downstream tasks, the most common audio representation is time-frequency-based, such as Mel spectrograms. In order to identify musical genres, this study explores the possibilities of a new form of audio…