相关论文: Improving Multimodal Accuracy Through Modality Pre…

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely…

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…

Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come…

The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples…

We propose a framework for multimodal sentiment analysis and emotion recognition using convolutional neural network-based feature extraction from text and visual modalities. We obtain a performance improvement of 10% over the state of the…

Neural networks have seen an explosion of usage and research in the past decade, particularly within the domains of computer vision and natural language processing. However, only recently have advancements in neural networks yielded…

Multimodal sentiment analysis (MSA) draws increasing attention with the availability of multimodal data. The boost in performance of MSA models is mainly hindered by two problems. On the one hand, recent MSA works mostly focus on learning…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…

Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable…

This paper proposes an approach for improving performance of unimodal models with multimodal training. Our approach involves a multi-branch architecture that incorporates unimodal models with a multimodal transformer-based branch. By…

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Recent Transformer-based large-scale pre-trained models have revolutionized vision-and-language (V+L) research. Models such as ViLBERT, LXMERT and UNITER have significantly lifted state of the art across a wide range of V+L benchmarks with…

Sentiment Analysis and Emotion Detection in conversation is key in several real-world applications, with an increase in modalities available aiding a better understanding of the underlying emotions. Multi-modal Emotion Detection and…

Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining…

Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing…

Decoder-only discrete-token language models have recently achieved significant success in automatic speech recognition. However, systematic analyses of how different modalities impact performance in specific scenarios remain limited. In…

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding…

Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue, Mixture-of-Depths (MoD) models have been proposed to…