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

Prevalent efforts have been put in automatically inferring genres of musical items. Yet, the propose solutions often rely on simplifications and fail to address the diversity and subjectivity of music genres. Accounting for these has,…

CLIP (Contrastive Language-Image Pre-Training) is a multimodal neural network trained on (text, image) pairs to predict the most relevant text caption given an image. It has been used extensively in image generation by connecting its output…

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Voice Timbre Attribute Detection (vTAD) plays a pivotal role in fine-grained timbre modeling for speech generation tasks. However, it remains challenging due to the inherently subjective nature of timbre descriptors and the severe label…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation…

Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To…

Recently, the end-to-end approach that learns hierarchical representations from raw data using deep convolutional neural networks has been successfully explored in the image, text and speech domains. This approach was applied to musical…

In this report we present a new model of concepts, based on the framework of variational autoencoders, which is designed to have attractive properties such as factored conceptual domains, and at the same time be learnable from data. The…

Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and…

Generative AI models for music and the arts in general are increasingly complex and hard to understand. The field of eXplainable AI (XAI) seeks to make complex and opaque AI models such as neural networks more understandable to people. One…

The training of controllable text-to-video (T2V) models relies heavily on the alignment between videos and captions, yet little existing research connects video caption evaluation with T2V generation assessment. This paper introduces…

Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such…

The availability of labeled image datasets has been shown critical for high-level image understanding, which continuously drives the progress of feature designing and models developing. However, constructing labeled image datasets is…

Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the…

Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with…

Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often inadequate and…

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic…

The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pre-training. However, these datasets are often collected with overrestrictive…

Understanding another person's creative output requires a shared language of association. However, when training vision-language models such as CLIP, we rely on web-scraped datasets containing short, predominantly literal, alt-text. In this…