相关论文: Attention Bottlenecks for Multimodal Fusion

Creating a meaningful representation by fusing single modalities (e.g., text, images, or audio) is the core concept of multimodal learning. Although several techniques for building multimodal representations have been proven successful,…

Multimodal sentiment analysis, a pivotal task in affective computing, seeks to understand human emotions by integrating cues from language, audio, and visual signals. While many recent approaches leverage complex attention mechanisms and…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively…

The major challenge in audio-visual event localization task lies in how to fuse information from multiple modalities effectively. Recent works have shown that attention mechanism is beneficial to the fusion process. In this paper, we…

Audio tokenization has emerged as a critical component in end-to-end audio language models, enabling efficient discrete representation learning for both audio understanding and generation tasks. However, existing audio tokenizers face…

Recognizing sounds is a key aspect of computational audio scene analysis and machine perception. In this paper, we advocate that sound recognition is inherently a multi-modal audiovisual task in that it is easier to differentiate sounds…

Humans express their emotions via facial expressions, voice intonation and word choices. To infer the nature of the underlying emotion, recognition models may use a single modality, such as vision, audio, and text, or a combination of…

In vision and linguistics; the main input modalities are facial expressions, speech patterns, and the words uttered. The issue with analysis of any one mode of expression (Visual, Verbal or Vocal) is that lot of contextual information can…

Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers. However, achieving a rather good performance is not an easy task due to the noisy raw data,…

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose critical semantic information when converting 2D…

People perceive the world with different senses, such as sight, hearing, smell, and touch. Processing and fusing information from multiple modalities enables Artificial Intelligence to understand the world around us more easily. However,…

Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using…

Human state recognition is a critical topic with pervasive and important applications in human-machine systems. Multi-modal fusion, the combination of metrics from multiple data sources, has been shown as a sound method for improving the…

With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is computationally efficient but often…

Modern machine learning models often combine multiple input streams of data to more accurately capture the information that informs their decisions. In multimodal machine learning, choosing the strategy for fusing data together requires…

Intelligently reasoning about the world often requires integrating data from multiple modalities, as any individual modality may contain unreliable or incomplete information. Prior work in multimodal learning fuses input modalities only…