相关论文: ConceptCaps: a Distilled Concept Dataset for Inter…

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often…

Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided…

Pre-trained flow-based models excel at synthesizing complex scenes yet lack a direct mechanism for disentangling and customizing their underlying concepts from one-shot real-world sources. To demystify this process, we first introduce a…

Finding meaningful concepts in engineering application datasets which allow for a sensible grouping of designs is very helpful in many contexts. It allows for determining different groups of designs with similar properties and provides…

Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…

Automatic cover detection -- the task of finding in a audio dataset all covers of a query track -- has long been a challenging theoretical problem in MIR community. It also became a practical need for music composers societies requiring to…

Automated audio captioning is a task that generates textual descriptions for audio content, and recent studies have explored using visual information to enhance captioning quality. However, current methods often fail to effectively fuse…

Singing voices contain much richer information than common voices, including varied vocal and acoustic properties. However, current open-source audio-text datasets for singing voices capture only a narrow range of attributes and lack…

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution…

Ontologies encompass a formal representation of knowledge through the definition of concepts or properties of a domain, and the relationships between those concepts. In this work, we seek to investigate whether using this ontological…

We present a system for automatic multi-axis perceptual quality prediction of generative audio, developed for Track 2 of the AudioMOS Challenge 2025. The task is to predict four Audio Aesthetic Scores--Production Quality, Production…

This paper presents a novel approach to music representation learning. Triplet loss based networks have become popular for representation learning in various multimedia retrieval domains. Yet, one of the most crucial parts of this approach…

Towards sufficient music searching, it is vital to form a complete set of labels for each song. However, current solutions fail to resolve it as they cannot produce diverse enough mappings to make up for the information missed by the gold…

We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with…

Although conceptualization has been widely studied in semantics and knowledge representation, it is still challenging to find the most accurate concept phrases to characterize the main idea of a text snippet on the fast-growing social…

Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on…

Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even…

Music representation models are widely used for tasks such as tagging, retrieval, and music understanding. Yet, their potential to encode cultural bias remains underexplored. In this paper, we apply Concept Activation Vectors (CAVs) to…

Caption quality has emerged as a critical bottleneck in training high-quality text-to-image (T2I) and text-to-video (T2V) generative models. While visual language models (VLMs) are commonly deployed to generate captions from visual data,…

Generative audio models are rapidly advancing in both capabilities and public utilization -- several powerful generative audio models have readily available open weights, and some tech companies have released high quality generative audio…