相关论文: GMS-CAVP: Improving Audio-Video Correspondence wit…

In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the…

Vocoder models have recently achieved substantial progress in generating authentic audio comparable to human quality while significantly reducing memory requirement and inference time. However, these data-hungry generative models require…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less…

How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap…

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension,…

Several multi-modality representation learning approaches such as LXMERT and ViLBERT have been proposed recently. Such approaches can achieve superior performance due to the high-level semantic information captured during large-scale…

Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval…

Visual acoustic matching (VAM) is pivotal for enhancing the immersive experience, and the task of dereverberation is effective in improving audio intelligibility. Existing methods treat each task independently, overlooking the inherent…

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression…

Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

Text-to-video retrieval requires precise alignment between language and temporally rich audio-video signals. However, existing methods often emphasize visual cues while underutilizing audio semantics or relying on coarse fusion strategies,…

Multi-party dialogues, common in collaborative scenarios like brainstorming sessions and negotiations, pose significant challenges due to their complexity and diverse speaker roles. Current methods often use graph neural networks to model…

With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. In particular, we are interested in…

Multi-modal tasks involving vision and language in deep learning continue to rise in popularity and are leading to the development of newer models that can generalize beyond the extent of their training data. The current models lack…

Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement…

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…

Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledged, a rigorous…